[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-69029b1d4492097c-engineering-agentic-models-insights-from-minimax-summary":3,"summaries-facets-categories":117,"summary-related-69029b1d4492097c-engineering-agentic-models-insights-from-minimax-summary":6151},{"id":4,"title":5,"ai":6,"body":13,"categories":75,"created_at":77,"date_modified":77,"description":69,"extension":78,"faq":77,"featured":79,"kicker_label":77,"meta":80,"navigation":96,"path":97,"published_at":98,"question":77,"scraped_at":99,"seo":100,"sitemap":101,"source_id":102,"source_name":103,"source_type":104,"source_url":105,"stem":106,"tags":107,"thumbnail_url":112,"tldr":113,"tweet":114,"unknown_tags":115,"__hash__":116},"summaries\u002Fsummaries\u002F69029b1d4492097c-engineering-agentic-models-insights-from-minimax-summary.md","Engineering Agentic Models: Insights from MiniMax",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","google\u002Fgemini-3.1-flash-lite",8279,661,3744,0.00306125,{"type":14,"value":15,"toc":68},"minimark",[16,21,25,28,32,35,38,61,65],[17,18,20],"h2",{"id":19},"the-architecture-of-agentic-models","The Architecture of Agentic Models",[22,23,24],"p",{},"MiniMax’s M3 model demonstrates that agentic capabilities—such as computer use and game development—are best achieved by training for multimodality from scratch. By training text and vision modalities simultaneously, the model avoids the common pitfall of \"modality collapse,\" where one modality degrades after training. This integrated approach allows the model to naturally align text and visual tokens, enabling it to \"see\" and interact with environments like websites or operating systems more effectively.",[22,26,27],{},"For long-horizon tasks, such as replicating 12-hour research runs or complex coding workflows, the key lies in environment design and reward formulation. Researchers must move beyond simple chat-based evaluation to rigorous, iterative testing. This includes using the model to build its own evaluation harnesses and employing validation\u002Ftest splits to ensure the model is genuinely improving rather than \"hacking\" the environment.",[17,29,31],{"id":30},"optimizing-the-inference-stack","Optimizing the Inference Stack",[22,33,34],{},"Serving agentic models requires a shift from standard chat-based inference to handling massive, multi-turn tool calls. This evolution forces changes in how developers manage the KV cache and routing. As context windows grow to 1 million tokens, the inference stack begins to resemble a distributed database or file system, requiring sophisticated management of where the cache is stored and how it is retrieved.",[22,36,37],{},"To achieve day-zero readiness for new model launches, engineering teams must:",[39,40,41,49,55],"ul",{},[42,43,44,48],"li",{},[45,46,47],"strong",{},"Write custom GPU kernels:"," Standard kernels often fail to capture the efficiency gains possible with unique model architectures (e.g., specific sparse attention patterns).",[42,50,51,54],{},[45,52,53],{},"Iterative Benchmarking:"," Use tools like \"Parallel Kernel Bench\" to identify unsolved performance bottlenecks. The goal is to treat benchmarks as a source of truth for optimization rather than just a marketing metric.",[42,56,57,60],{},[45,58,59],{},"Continuous Tuning:"," Performance optimization is a daily, not monthly, process. Inference engines should be tuned continuously post-launch to reduce latency and improve throughput as usage patterns evolve.",[17,62,64],{"id":63},"the-future-of-open-models","The Future of Open Models",[22,66,67],{},"There is a clear trend toward the closing gap between closed-source frontier models and open-weight models. The industry is currently underutilizing GPU hardware, with significant room for improvement in both training and inference efficiency. The next three years will likely see a shift toward more specialized, agentic-first architectures where models are not just passive responders but active participants in development, testing, and infrastructure optimization.",{"title":69,"searchDepth":70,"depth":70,"links":71},"",2,[72,73,74],{"id":19,"depth":70,"text":20},{"id":30,"depth":70,"text":31},{"id":63,"depth":70,"text":64},[76],"AI & LLMs",null,"md",false,{"content_references":81,"triage":91},[82,87],{"type":83,"title":84,"url":85,"context":86},"tool","Parallel Kernel Bench","https:\u002F\u002Fgithub.com\u002Ftogethercomputer\u002Fparallel-kernel-bench","recommended",{"type":88,"title":89,"context":90},"other","OS World","mentioned",{"relevance":92,"novelty":93,"quality":93,"actionability":93,"composite":94,"reasoning":95},5,4,4.35,"Category: AI & LLMs. The article provides in-depth insights into building production-ready AI agents, addressing specific pain points like optimizing model architecture and inference stacks for long-horizon tasks. It offers actionable strategies such as writing custom GPU kernels and iterative benchmarking, making it highly relevant for developers looking to implement AI features.",true,"\u002Fsummaries\u002F69029b1d4492097c-engineering-agentic-models-insights-from-minimax-summary","2026-07-31 03:00:14","2026-07-31 03:10:20",{"title":5,"description":69},{"loc":97},"69029b1d4492097c","AI Engineer","video","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=AVMr9PMINyo","summaries\u002F69029b1d4492097c-engineering-agentic-models-insights-from-minimax-summary",[108,109,110,111],"llm","agents","reinforcement-learning","inference","https:\u002F\u002Fi.ytimg.com\u002Fvi\u002FAVMr9PMINyo\u002Fhqdefault.jpg","Building production-ready AI agents requires co-designing the model architecture, training data, and inference stack—specifically optimizing for long-horizon tasks, multimodal inputs, and efficient KV cache management.","This is a technical panel discussion between the RL lead at MiniMax and the VP of kernels at Together AI, focusing on the practical engineering required to ship and serve open-weight models. They discuss the \"unglamorous\" work of writing custom GPU kernels, optimizing inference stacks for agentic workloads, and the specific training challenges involved in maintaining multimodal stability.",[110,111],"4j06jcUCptqv4USH3tlz9fAAYevZM_97anHGGptjJIg",[118,120,123,126,128,131,134,136,138,140,143,145,147,149,151,154,156,158,160,162,165,167,169,171,173,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,206,209,211,213,215,217,219,221,223,225,227,229,231,234,236,238,240,242,244,246,248,250,252,254,256,258,260,262,264,266,269,271,273,275,277,279,281,283,285,287,289,291,293,295,298,300,302,304,306,308,310,312,314,316,318,320,322,324,326,328,330,332,334,336,338,340,342,344,346,348,350,352,354,357,359,361,363,365,367,369,371,373,375,378,380,382,384,386,388,390,392,394,396,398,400,402,405,407,409,411,413,415,417,419,421,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,477,479,481,484,486,488,490,492,494,496,498,500,502,504,506,508,510,513,515,517,519,521,523,525,527,529,531,533,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752,754,756,758,760,762,764,766,768,770,772,774,776,778,780,782,784,787,789,791,793,795,798,800,802,804,806,808,810,812,814,816,818,821,823,825,827,829,831,833,835,837,839,841,843,845,847,849,851,853,855,857,859,861,863,865,867,869,871,873,875,877,879,881,883,885,887,889,891,893,895,897,899,901,903,905,907,909,911,913,915,917,919,921,923,925,927,929,931,933,935,937,939,941,943,945,947,949,951,953,955,957,959,961,963,965,967,969,971,973,975,977,979,981,983,985,987,989,991,993,995,997,999,1001,1003,1005,1007,1009,1011,1013,1015,1017,1019,1021,1023,1025,1027,1029,1031,1033,1035,1037,1039,1041,1043,1045,1047,1049,1051,1053,1055,1057,1059,1061,1063,1065,1067,1069,1071,1073,1075,1077,1079,1081,1083,1085,1087,1089,1091,1093,1095,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1194,1196,1198,1200,1202,1204,1206,1208,1210,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1271,1273,1275,1277,1279,1281,1283,1285,1287,1289,1291,1293,1295,1297,1299,1301,1303,1305,1307,1309,1311,1313,1315,1317,1319,1321,1323,1325,1327,1329,1331,1333,1335,1337,1339,1341,1343,1345,1347,1349,1351,1353,1355,1357,1359,1361,1363,1365,1367,1369,1371,1373,1375,1377,1379,1381,1383,1385,1387,1389,1391,1393,1395,1397,1399,1402,1404,1406,1408,1410,1412,1414,1416,1418,1420,1422,1424,1426,1428,1430,1432,1434,1436,1438,1440,1442,1444,1446,1448,1450,1452,1454,1456,1458,1460,1462,1464,1466,1468,1470,1472,1474,1476,1478,1480,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1532,1534,1537,1539,1541,1543,1545,1547,1549,1551,1553,1555,1557,1559,1561,1563,1565,1567,1569,1571,1573,1575,1577,1579,1581,1583,1585,1587,1589,1591,1594,1596,1598,1600,1602,1604,1606,1608,1610,1612,1614,1616,1618,1620,1622,1624,1626,1628,1630,1632,1634,1636,1638,1640,1642,1644,1646,1648,1650,1652,1654,1656,1658,1660,1662,1664,1666,1668,1670,1672,1674,1676,1678,1680,1682,1684,1686,1688,1690,1692,1694,1696,1698,1700,1702,1704,1706,1708,1710,1712,1714,1716,1718,1720,1722,1724,1726,1728,1730,1732,1734,1736,1738,1740,1742,1744,1746,1748,1750,1752,1754,1756,1758,1760,1762,1764,1766,1768,1770,1772,1774,1776,1778,1780,1782,1784,1786,1788,1790,1792,1794,1796,1798,1800,1802,1804,1806,1808,1810,1812,1814,1816,1818,1820,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842,1844,1846,1848,1850,1852,1854,1856,1858,1860,1862,1864,1866,1868,1870,1872,1874,1876,1878,1880,1882,1884,1886,1888,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1967,1969,1971,1973,1975,1977,1979,1981,1983,1985,1987,1989,1991,1993,1995,1997,1999,2001,2003,2005,2007,2009,2011,2013,2015,2017,2019,2021,2023,2025,2027,2029,2031,2033,2035,2037,2039,2041,2043,2046,2048,2050,2052,2054,2056,2058,2060,2062,2064,2066,2068,2070,2072,2074,2076,2078,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2116,2118,2120,2122,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142,2144,2146,2148,2150,2152,2155,2157,2159,2161,2163,2165,2167,2169,2171,2173,2175,2177,2179,2181,2183,2185,2187,2189,2191,2193,2196,2198,2200,2202,2204,2206,2208,2210,2212,2214,2216,2218,2220,2222,2224,2226,2228,2230,2232,2234,2236,2238,2240,2242,2244,2246,2248,2250,2252,2254,2256,2258,2260,2262,2264,2266,2268,2270,2272,2274,2276,2278,2280,2282,2284,2286,2288,2290,2292,2294,2296,2298,2300,2302,2304,2306,2308,2310,2312,2314,2316,2318,2320,2322,2324,2326,2328,2330,2332,2334,2336,2338,2340,2342,2344,2346,2348,2350,2352,2354,2356,2358,2360,2362,2364,2366,2368,2370,2372,2374,2376,2378,2380,2382,2384,2386,2388,2390,2392,2394,2396,2398,2400,2402,2404,2406,2408,2410,2412,2414,2416,2418,2420,2422,2424,2426,2428,2430,2432,2434,2436,2438,2440,2442,2444,2446,2448,2450,2452,2454,2456,2458,2460,2462,2464,2466,2468,2470,2472,2474,2476,2478,2480,2482,2484,2486,2488,2490,2492,2494,2496,2498,2500,2502,2504,2506,2508,2510,2512,2514,2516,2518,2520,2522,2524,2526,2528,2530,2532,2534,2536,2538,2540,2542,2544,2546,2548,2550,2552,2554,2556,2558,2560,2562,2564,2566,2568,2570,2572,2574,2576,2578,2580,2582,2584,2586,2588,2590,2592,2594,2596,2598,2600,2602,2604,2606,2608,2610,2612,2614,2616,2618,2620,2622,2624,2626,2628,2630,2632,2634,2636,2638,2640,2642,2644,2646,2648,2650,2652,2654,2656,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2757,2759,2761,2763,2765,2767,2769,2771,2773,2775,2777,2779,2781,2783,2785,2787,2789,2791,2793,2795,2797,2799,2801,2803,2805,2807,2809,2811,2813,2815,2817,2819,2821,2823,2825,2827,2829,2831,2833,2835,2837,2839,2841,2843,2845,2847,2849,2851,2853,2855,2857,2860,2862,2864,2866,2868,2870,2872,2874,2876,2878,2880,2882,2884,2886,2888,2890,2892,2894,2896,2898,2900,2902,2904,2906,2908,2910,2912,2914,2916,2918,2920,2922,2924,2926,2928,2930,2932,2934,2936,2938,2940,2942,2944,2946,2948,2950,2952,2954,2956,2958,2960,2962,2964,2966,2968,2970,2972,2974,2976,2978,2980,2982,2984,2986,2988,2990,2992,2994,2996,2998,3000,3002,3004,3006,3008,3010,3012,3014,3016,3018,3020,3022,3024,3026,3028,3030,3032,3034,3036,3038,3040,3042,3044,3046,3048,3050,3052,3054,3056,3058,3060,3062,3064,3066,3068,3070,3072,3074,3076,3078,3080,3082,3084,3086,3088,3090,3092,3094,3096,3098,3100,3102,3104,3106,3108,3110,3112,3114,3116,3118,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3164,3166,3168,3170,3172,3174,3176,3178,3180,3182,3184,3186,3188,3190,3192,3194,3196,3198,3200,3202,3204,3206,3208,3210,3212,3214,3216,3218,3220,3222,3224,3226,3228,3230,3232,3234,3236,3238,3240,3242,3244,3246,3248,3250,3252,3254,3256,3258,3260,3262,3264,3266,3268,3270,3272,3274,3276,3278,3280,3282,3284,3286,3288,3290,3292,3294,3296,3298,3300,3302,3304,3306,3308,3310,3312,3314,3316,3318,3320,3322,3324,3326,3328,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3376,3378,3380,3382,3384,3386,3388,3390,3392,3394,3396,3398,3400,3402,3404,3406,3408,3410,3412,3414,3416,3418,3420,3422,3424,3426,3428,3430,3432,3434,3436,3438,3440,3442,3444,3446,3448,3450,3452,3454,3456,3458,3460,3462,3464,3466,3468,3470,3472,3474,3476,3478,3480,3482,3484,3486,3488,3490,3492,3494,3496,3498,3500,3502,3504,3506,3508,3510,3512,3514,3516,3518,3520,3522,3524,3526,3528,3530,3532,3534,3536,3538,3540,3542,3544,3546,3548,3550,3552,3554,3556,3558,3560,3562,3564,3566,3568,3570,3572,3574,3576,3578,3580,3582,3584,3586,3588,3590,3592,3594,3596,3598,3600,3602,3604,3606,3608,3610,3612,3614,3616,3618,3620,3622,3624,3626,3628,3630,3632,3634,3636,3638,3640,3642,3644,3646,3648,3650,3652,3654,3656,3658,3660,3662,3664,3666,3668,3670,3672,3674,3676,3678,3680,3682,3684,3686,3688,3690,3692,3694,3696,3698,3700,3702,3704,3706,3708,3710,3712,3714,3716,3718,3720,3722,3724,3726,3728,3730,3732,3734,3736,3738,3740,3742,3744,3746,3748,3750,3752,3754,3756,3758,3760,3762,3764,3766,3768,3770,3772,3774,3776,3778,3780,3782,3784,3786,3788,3790,3792,3794,3796,3798,3800,3802,3804,3806,3808,3810,3812,3814,3816,3818,3820,3822,3824,3826,3828,3830,3832,3834,3836,3838,3840,3842,3844,3846,3848,3850,3852,3854,3856,3858,3860,3862,3864,3866,3868,3870,3872,3874,3876,3878,3880,3882,3884,3886,3888,3890,3892,3894,3896,3898,3900,3902,3904,3906,3908,3910,3912,3914,3916,3918,3920,3922,3924,3926,3928,3930,3932,3934,3936,3938,3940,3942,3944,3946,3948,3950,3952,3954,3956,3958,3960,3962,3964,3966,3968,3970,3972,3974,3976,3978,3980,3983,3985,3987,3989,3991,3993,3995,3997,3999,4001,4003,4005,4007,4009,4011,4013,4015,4017,4019,4021,4023,4025,4027,4029,4031,4033,4035,4037,4039,4041,4043,4045,4047,4049,4051,4053,4055,4057,4059,4061,4063,4065,4067,4069,4071,4073,4075,4077,4079,4081,4083,4085,4087,4089,4091,4093,4095,4097,4099,4101,4103,4105,4107,4109,4111,4113,4115,4117,4119,4121,4123,4125,4127,4129,4131,4133,4135,4137,4139,4141,4143,4145,4147,4149,4151,4153,4155,4157,4159,4161,4163,4165,4167,4169,4171,4173,4175,4177,4179,4181,4183,4185,4187,4189,4191,4193,4195,4197,4199,4201,4203,4205,4207,4209,4211,4213,4215,4217,4219,4221,4223,4225,4227,4229,4231,4233,4235,4237,4239,4241,4243,4245,4247,4249,4251,4253,4255,4257,4259,4261,4263,4265,4267,4269,4271,4273,4275,4277,4279,4281,4283,4285,4287,4289,4291,4293,4295,4297,4299,4301,4303,4305,4307,4309,4311,4313,4315,4317,4319,4321,4323,4325,4327,4329,4331,4333,4335,4337,4339,4341,4343,4345,4347,4349,4351,4353,4355,4357,4359,4361,4363,4365,4367,4369,4371,4373,4375,4377,4379,4381,4383,4385,4387,4389,4391,4393,4395,4397,4399,4401,4403,4405,4407,4409,4411,4413,4415,4417,4419,4421,4423,4425,4427,4429,4431,4433,4435,4437,4439,4441,4443,4445,4447,4449,4451,4453,4455,4457,4459,4461,4463,4465,4467,4469,4471,4473,4475,4477,4479,4481,4483,4485,4487,4489,4491,4493,4495,4497,4499,4501,4503,4505,4507,4509,4511,4513,4515,4517,4519,4521,4523,4525,4527,4529,4531,4533,4535,4537,4539,4541,4543,4545,4547,4549,4551,4553,4555,4557,4559,4561,4563,4565,4567,4569,4571,4573,4575,4577,4579,4581,4583,4585,4587,4589,4591,4593,4595,4597,4599,4601,4603,4605,4607,4609,4611,4613,4615,4617,4619,4621,4623,4625,4627,4629,4631,4633,4635,4637,4639,4641,4643,4645,4647,4649,4651,4653,4655,4657,4659,4661,4663,4665,4667,4669,4671,4673,4675,4677,4679,4681,4683,4685,4687,4689,4691,4693,4695,4697,4699,4701,4703,4705,4707,4709,4711,4713,4715,4717,4719,4721,4723,4725,4727,4729,4731,4733,4735,4737,4740,4742,4744,4746,4748,4750,4752,4754,4756,4758,4760,4762,4764,4766,4768,4770,4772,4774,4776,4778,4780,4782,4784,4786,4788,4790,4792,4794,4796,4798,4800,4802,4804,4806,4808,4810,4812,4814,4816,4818,4820,4822,4824,4826,4828,4830,4832,4834,4836,4838,4840,4842,4844,4846,4848,4850,4852,4854,4856,4858,4860,4862,4864,4866,4868,4870,4872,4874,4876,4878,4880,4882,4884,4886,4888,4890,4892,4894,4896,4898,4900,4902,4904,4906,4908,4910,4912,4915,4917,4919,4921,4923,4925,4927,4929,4931,4933,4935,4937,4939,4941,4943,4945,4947,4949,4951,4953,4955,4957,4959,4961,4963,4965,4967,4969,4971,4973,4975,4977,4979,4981,4983,4985,4987,4989,4991,4993,4995,4997,4999,5001,5003,5005,5007,5009,5011,5013,5015,5017,5019,5021,5023,5025,5027,5029,5031,5033,5035,5037,5039,5041,5043,5045,5047,5049,5051,5053,5055,5057,5059,5061,5063,5065,5067,5069,5071,5073,5075,5077,5079,5081,5083,5085,5087,5089,5091,5093,5095,5097,5099,5101,5103,5105,5107,5109,5111,5113,5115,5117,5119,5121,5123,5125,5127,5129,5131,5133,5135,5137,5139,5141,5143,5145,5147,5149,5151,5153,5155,5157,5159,5161,5163,5165,5167,5169,5171,5173,5175,5177,5179,5181,5183,5185,5187,5189,5191,5193,5195,5197,5199,5201,5203,5205,5207,5209,5211,5213,5215,5217,5219,5221,5223,5225,5227,5229,5231,5233,5235,5237,5239,5241,5243,5245,5247,5249,5251,5253,5255,5257,5259,5261,5263,5265,5267,5269,5271,5273,5275,5277,5279,5281,5283,5285,5287,5289,5291,5293,5295,5297,5299,5301,5303,5305,5307,5309,5311,5313,5315,5317,5319,5321,5323,5325,5327,5329,5331,5333,5335,5337,5339,5341,5343,5345,5347,5349,5351,5353,5355,5357,5359,5361,5363,5365,5367,5369,5371,5373,5375,5377,5379,5381,5383,5385,5387,5389,5391,5393,5395,5397,5399,5401,5403,5405,5407,5409,5411,5413,5415,5417,5419,5421,5423,5425,5427,5429,5431,5433,5435,5437,5439,5441,5443,5445,5447,5449,5451,5453,5455,5457,5459,5461,5463,5465,5467,5469,5471,5473,5475,5477,5479,5481,5483,5485,5487,5489,5491,5493,5495,5497,5499,5501,5503,5505,5507,5509,5511,5513,5515,5517,5519,5521,5523,5525,5527,5529,5531,5533,5535,5537,5539,5541,5543,5545,5547,5549,5551,5553,5555,5557,5559,5561,5563,5565,5567,5569,5571,5573,5575,5577,5579,5581,5583,5585,5587,5589,5591,5593,5595,5597,5599,5601,5603,5605,5607,5609,5611,5613,5615,5617,5619,5621,5623,5625,5627,5629,5631,5633,5635,5637,5639,5641,5643,5645,5647,5649,5651,5653,5655,5657,5659,5661,5663,5665,5667,5669,5671,5673,5675,5677,5679,5681,5683,5685,5687,5689,5691,5693,5695,5697,5699,5701,5703,5705,5707,5709,5711,5713,5715,5717,5719,5721,5723,5725,5727,5729,5731,5733,5735,5737,5739,5741,5743,5745,5747,5749,5751,5753,5755,5757,5759,5761,5763,5765,5767,5769,5771,5773,5775,5777,5779,5781,5783,5785,5787,5789,5791,5793,5795,5797,5799,5801,5803,5805,5807,5809,5811,5813,5815,5817,5819,5821,5823,5825,5827,5829,5831,5833,5835,5837,5839,5841,5843,5845,5847,5849,5851,5853,5855,5857,5859,5861,5863,5865,5867,5869,5871,5873,5875,5877,5879,5881,5883,5885,5887,5889,5891,5893,5895,5897,5899,5901,5903,5905,5907,5909,5911,5913,5915,5917,5919,5921,5923,5925,5927,5929,5931,5933,5935,5937,5939,5941,5943,5945,5947,5949,5951,5953,5955,5957,5959,5961,5963,5965,5967,5969,5971,5973,5975,5977,5979,5981,5983,5985,5987,5989,5991,5993,5995,5997,5999,6001,6003,6005,6007,6009,6011,6013,6015,6017,6019,6021,6023,6025,6027,6029,6031,6033,6035,6037,6039,6041,6043,6045,6047,6049,6051,6053,6055,6057,6059,6061,6063,6065,6067,6069,6071,6073,6075,6077,6079,6081,6083,6085,6087,6089,6091,6093,6095,6097,6099,6101,6103,6105,6107,6109,6111,6113,6115,6117,6119,6121,6123,6125,6127,6129,6131,6133,6135,6137,6139,6141,6143,6145,6147,6149],{"categories":119},[76],{"categories":121},[122],"Developer Productivity",{"categories":124},[125],"Business & SaaS",{"categories":127},[76],{"categories":129},[130],"AI Automation",{"categories":132},[133],"Product Strategy",{"categories":135},[76],{"categories":137},[122],{"categories":139},[130],{"categories":141},[142],"Software Engineering",{"categories":144},[76],{"categories":146},[125],{"categories":148},[],{"categories":150},[76],{"categories":152},[153],"Inference & Serving",{"categories":155},[76],{"categories":157},[76],{"categories":159},[130],{"categories":161},[],{"categories":163},[164],"AI News & Trends",{"categories":166},[130],{"categories":168},[76],{"categories":170},[125],{"categories":172},[122],{"categories":174},[76],{"categories":176},[130],{"categories":178},[164],{"categories":180},[130],{"categories":182},[130],{"categories":184},[76],{"categories":186},[130],{"categories":188},[76],{"categories":190},[76],{"categories":192},[76],{"categories":194},[164],{"categories":196},[76],{"categories":198},[76],{"categories":200},[76],{"categories":202},[],{"categories":204},[205],"Design & Frontend",{"categories":207},[208],"Data Science & Visualization",{"categories":210},[164],{"categories":212},[76],{"categories":214},[76],{"categories":216},[76],{"categories":218},[],{"categories":220},[76],{"categories":222},[130],{"categories":224},[142],{"categories":226},[76],{"categories":228},[130],{"categories":230},[76],{"categories":232},[233],"Marketing & Growth",{"categories":235},[205],{"categories":237},[76],{"categories":239},[130],{"categories":241},[76],{"categories":243},[142],{"categories":245},[],{"categories":247},[],{"categories":249},[205],{"categories":251},[76],{"categories":253},[130],{"categories":255},[122],{"categories":257},[142],{"categories":259},[205],{"categories":261},[133],{"categories":263},[76],{"categories":265},[142],{"categories":267},[268],"DevOps & Cloud",{"categories":270},[130],{"categories":272},[133],{"categories":274},[164],{"categories":276},[76],{"categories":278},[],{"categories":280},[76],{"categories":282},[76],{"categories":284},[],{"categories":286},[130],{"categories":288},[142],{"categories":290},[],{"categories":292},[142],{"categories":294},[76],{"categories":296},[297],"Governance & Standards",{"categories":299},[125],{"categories":301},[],{"categories":303},[],{"categories":305},[76],{"categories":307},[76],{"categories":309},[130],{"categories":311},[76],{"categories":313},[76],{"categories":315},[130],{"categories":317},[76],{"categories":319},[76],{"categories":321},[76],{"categories":323},[],{"categories":325},[142],{"categories":327},[],{"categories":329},[],{"categories":331},[142],{"categories":333},[],{"categories":335},[142],{"categories":337},[76],{"categories":339},[76],{"categories":341},[233],{"categories":343},[76],{"categories":345},[205],{"categories":347},[205],{"categories":349},[76],{"categories":351},[142],{"categories":353},[130],{"categories":355},[356],"GovTech & Public-Sector Adoption",{"categories":358},[142],{"categories":360},[76],{"categories":362},[76],{"categories":364},[130],{"categories":366},[130],{"categories":368},[208],{"categories":370},[76],{"categories":372},[164],{"categories":374},[130],{"categories":376},[377],"Legal AI Tools",{"categories":379},[130],{"categories":381},[233],{"categories":383},[130],{"categories":385},[133],{"categories":387},[142],{"categories":389},[356],{"categories":391},[],{"categories":393},[130],{"categories":395},[],{"categories":397},[125],{"categories":399},[130],{"categories":401},[130],{"categories":403},[404],"RAG & Retrieval",{"categories":406},[125],{"categories":408},[76],{"categories":410},[142],{"categories":412},[142],{"categories":414},[268],{"categories":416},[205],{"categories":418},[76],{"categories":420},[],{"categories":422},[423],"Agents & Orchestration",{"categories":425},[142],{"categories":427},[76],{"categories":429},[],{"categories":431},[130],{"categories":433},[125],{"categories":435},[],{"categories":437},[76],{"categories":439},[],{"categories":441},[122],{"categories":443},[142],{"categories":445},[125],{"categories":447},[76],{"categories":449},[130],{"categories":451},[76],{"categories":453},[164],{"categories":455},[76],{"categories":457},[],{"categories":459},[76],{"categories":461},[],{"categories":463},[142],{"categories":465},[76],{"categories":467},[208],{"categories":469},[],{"categories":471},[76],{"categories":473},[205],{"categories":475},[476],"Models & Frontier Labs",{"categories":478},[],{"categories":480},[205],{"categories":482},[483],"Regulation & Governance of AI",{"categories":485},[130],{"categories":487},[],{"categories":489},[76],{"categories":491},[76],{"categories":493},[130],{"categories":495},[164],{"categories":497},[125],{"categories":499},[76],{"categories":501},[],{"categories":503},[142],{"categories":505},[130],{"categories":507},[76],{"categories":509},[133],{"categories":511},[512],"AI Policy & Regulation",{"categories":514},[],{"categories":516},[76],{"categories":518},[133],{"categories":520},[130],{"categories":522},[76],{"categories":524},[76],{"categories":526},[76],{"categories":528},[130],{"categories":530},[],{"categories":532},[208],{"categories":534},[535],"Evals & Reliability",{"categories":537},[76],{"categories":539},[],{"categories":541},[122],{"categories":543},[356],{"categories":545},[512],{"categories":547},[76],{"categories":549},[125],{"categories":551},[76],{"categories":553},[130],{"categories":555},[76],{"categories":557},[130],{"categories":559},[423],{"categories":561},[76],{"categories":563},[142],{"categories":565},[76],{"categories":567},[],{"categories":569},[],{"categories":571},[76],{"categories":573},[356],{"categories":575},[76],{"categories":577},[76],{"categories":579},[76],{"categories":581},[],{"categories":583},[205],{"categories":585},[],{"categories":587},[76],{"categories":589},[],{"categories":591},[130],{"categories":593},[76],{"categories":595},[205],{"categories":597},[],{"categories":599},[76],{"categories":601},[130],{"categories":603},[76],{"categories":605},[125],{"categories":607},[130],{"categories":609},[76],{"categories":611},[76],{"categories":613},[142],{"categories":615},[205],{"categories":617},[130],{"categories":619},[],{"categories":621},[142],{"categories":623},[130],{"categories":625},[208],{"categories":627},[],{"categories":629},[164],{"categories":631},[],{"categories":633},[76],{"categories":635},[76],{"categories":637},[76],{"categories":639},[125,233],{"categories":641},[],{"categories":643},[76],{"categories":645},[76],{"categories":647},[130],{"categories":649},[],{"categories":651},[],{"categories":653},[76],{"categories":655},[205],{"categories":657},[76],{"categories":659},[],{"categories":661},[76],{"categories":663},[268],{"categories":665},[],{"categories":667},[130],{"categories":669},[164],{"categories":671},[76],{"categories":673},[76],{"categories":675},[205],{"categories":677},[],{"categories":679},[164],{"categories":681},[76],{"categories":683},[153],{"categories":685},[76],{"categories":687},[130],{"categories":689},[164],{"categories":691},[476],{"categories":693},[76],{"categories":695},[233],{"categories":697},[],{"categories":699},[130],{"categories":701},[125],{"categories":703},[142],{"categories":705},[76],{"categories":707},[130],{"categories":709},[],{"categories":711},[76,268],{"categories":713},[76],{"categories":715},[76],{"categories":717},[76],{"categories":719},[130],{"categories":721},[76,142],{"categories":723},[208],{"categories":725},[76],{"categories":727},[76],{"categories":729},[142],{"categories":731},[130],{"categories":733},[512],{"categories":735},[233],{"categories":737},[76],{"categories":739},[130],{"categories":741},[76],{"categories":743},[76],{"categories":745},[130],{"categories":747},[],{"categories":749},[130],{"categories":751},[76],{"categories":753},[76],{"categories":755},[130],{"categories":757},[76],{"categories":759},[76,125],{"categories":761},[125],{"categories":763},[],{"categories":765},[205],{"categories":767},[205],{"categories":769},[76],{"categories":771},[],{"categories":773},[],{"categories":775},[164],{"categories":777},[],{"categories":779},[122],{"categories":781},[76],{"categories":783},[142],{"categories":785},[786],"Generative UI & Design-to-Code",{"categories":788},[76],{"categories":790},[76],{"categories":792},[205],{"categories":794},[76],{"categories":796},[797],"Algorithmic Accountability",{"categories":799},[130],{"categories":801},[142],{"categories":803},[164],{"categories":805},[205],{"categories":807},[],{"categories":809},[133],{"categories":811},[76],{"categories":813},[76],{"categories":815},[76],{"categories":817},[130],{"categories":819},[820],"MLOps & Infrastructure",{"categories":822},[76],{"categories":824},[76],{"categories":826},[76],{"categories":828},[76],{"categories":830},[76],{"categories":832},[164],{"categories":834},[122],{"categories":836},[76],{"categories":838},[130],{"categories":840},[268],{"categories":842},[76],{"categories":844},[125],{"categories":846},[76],{"categories":848},[205],{"categories":850},[76],{"categories":852},[76],{"categories":854},[130],{"categories":856},[],{"categories":858},[],{"categories":860},[76],{"categories":862},[153],{"categories":864},[205],{"categories":866},[164],{"categories":868},[208],{"categories":870},[],{"categories":872},[76],{"categories":874},[76],{"categories":876},[125],{"categories":878},[130],{"categories":880},[76],{"categories":882},[76],{"categories":884},[76],{"categories":886},[164],{"categories":888},[153],{"categories":890},[76],{"categories":892},[205],{"categories":894},[76],{"categories":896},[],{"categories":898},[130],{"categories":900},[142],{"categories":902},[],{"categories":904},[76],{"categories":906},[76],{"categories":908},[130],{"categories":910},[142],{"categories":912},[76],{"categories":914},[208],{"categories":916},[],{"categories":918},[76],{"categories":920},[],{"categories":922},[76],{"categories":924},[],{"categories":926},[133],{"categories":928},[125],{"categories":930},[130],{"categories":932},[130],{"categories":934},[],{"categories":936},[122],{"categories":938},[76],{"categories":940},[76],{"categories":942},[125],{"categories":944},[164],{"categories":946},[122],{"categories":948},[],{"categories":950},[76],{"categories":952},[],{"categories":954},[],{"categories":956},[164],{"categories":958},[164],{"categories":960},[],{"categories":962},[423],{"categories":964},[76],{"categories":966},[205],{"categories":968},[142],{"categories":970},[],{"categories":972},[377],{"categories":974},[125],{"categories":976},[],{"categories":978},[],{"categories":980},[122],{"categories":982},[208],{"categories":984},[],{"categories":986},[233],{"categories":988},[130],{"categories":990},[125],{"categories":992},[130],{"categories":994},[125],{"categories":996},[142],{"categories":998},[],{"categories":1000},[153],{"categories":1002},[133],{"categories":1004},[76],{"categories":1006},[205],{"categories":1008},[142],{"categories":1010},[125],{"categories":1012},[76],{"categories":1014},[130],{"categories":1016},[125],{"categories":1018},[76],{"categories":1020},[76],{"categories":1022},[76],{"categories":1024},[76],{"categories":1026},[],{"categories":1028},[],{"categories":1030},[142],{"categories":1032},[208],{"categories":1034},[133],{"categories":1036},[76],{"categories":1038},[130],{"categories":1040},[142],{"categories":1042},[76],{"categories":1044},[],{"categories":1046},[164],{"categories":1048},[133],{"categories":1050},[76],{"categories":1052},[535],{"categories":1054},[268],{"categories":1056},[],{"categories":1058},[130],{"categories":1060},[],{"categories":1062},[122],{"categories":1064},[],{"categories":1066},[76],{"categories":1068},[76],{"categories":1070},[205],{"categories":1072},[233],{"categories":1074},[142],{"categories":1076},[130],{"categories":1078},[],{"categories":1080},[142],{"categories":1082},[76],{"categories":1084},[122],{"categories":1086},[],{"categories":1088},[125],{"categories":1090},[76],{"categories":1092},[164],{"categories":1094},[76,268],{"categories":1096},[1097],"Design Systems for AI",{"categories":1099},[76],{"categories":1101},[76],{"categories":1103},[164],{"categories":1105},[76],{"categories":1107},[76],{"categories":1109},[125],{"categories":1111},[76],{"categories":1113},[76],{"categories":1115},[],{"categories":1117},[76],{"categories":1119},[76],{"categories":1121},[125],{"categories":1123},[76],{"categories":1125},[],{"categories":1127},[130],{"categories":1129},[142],{"categories":1131},[164],{"categories":1133},[142],{"categories":1135},[205],{"categories":1137},[164],{"categories":1139},[208],{"categories":1141},[76],{"categories":1143},[122],{"categories":1145},[512],{"categories":1147},[76],{"categories":1149},[130],{"categories":1151},[76],{"categories":1153},[142],{"categories":1155},[142],{"categories":1157},[],{"categories":1159},[],{"categories":1161},[130],{"categories":1163},[133],{"categories":1165},[],{"categories":1167},[76],{"categories":1169},[],{"categories":1171},[205],{"categories":1173},[130],{"categories":1175},[142],{"categories":1177},[205],{"categories":1179},[76],{"categories":1181},[76],{"categories":1183},[205],{"categories":1185},[],{"categories":1187},[],{"categories":1189},[164],{"categories":1191},[130],{"categories":1193},[130],{"categories":1195},[76],{"categories":1197},[76],{"categories":1199},[76],{"categories":1201},[76],{"categories":1203},[125],{"categories":1205},[76],{"categories":1207},[76],{"categories":1209},[],{"categories":1211},[142],{"categories":1213},[142],{"categories":1215},[76],{"categories":1217},[142],{"categories":1219},[125],{"categories":1221},[],{"categories":1223},[76],{"categories":1225},[76],{"categories":1227},[76],{"categories":1229},[76],{"categories":1231},[130],{"categories":1233},[122],{"categories":1235},[125],{"categories":1237},[76],{"categories":1239},[164],{"categories":1241},[130],{"categories":1243},[153],{"categories":1245},[233],{"categories":1247},[76],{"categories":1249},[130],{"categories":1251},[76],{"categories":1253},[],{"categories":1255},[205],{"categories":1257},[],{"categories":1259},[76],{"categories":1261},[76],{"categories":1263},[],{"categories":1265},[142],{"categories":1267},[125],{"categories":1269},[1270],"Visual & Generative Media",{"categories":1272},[130],{"categories":1274},[],{"categories":1276},[76],{"categories":1278},[76],{"categories":1280},[142],{"categories":1282},[268],{"categories":1284},[208],{"categories":1286},[512],{"categories":1288},[142],{"categories":1290},[233],{"categories":1292},[76],{"categories":1294},[205],{"categories":1296},[76],{"categories":1298},[76],{"categories":1300},[142],{"categories":1302},[130],{"categories":1304},[76],{"categories":1306},[],{"categories":1308},[],{"categories":1310},[130],{"categories":1312},[142],{"categories":1314},[122],{"categories":1316},[130],{"categories":1318},[476],{"categories":1320},[76],{"categories":1322},[133],{"categories":1324},[76],{"categories":1326},[125],{"categories":1328},[],{"categories":1330},[76],{"categories":1332},[133],{"categories":1334},[76],{"categories":1336},[76],{"categories":1338},[76],{"categories":1340},[133],{"categories":1342},[76],{"categories":1344},[76],{"categories":1346},[233],{"categories":1348},[76],{"categories":1350},[423],{"categories":1352},[76],{"categories":1354},[130],{"categories":1356},[76],{"categories":1358},[76],{"categories":1360},[76],{"categories":1362},[76],{"categories":1364},[205],{"categories":1366},[130],{"categories":1368},[],{"categories":1370},[130],{"categories":1372},[],{"categories":1374},[268],{"categories":1376},[142],{"categories":1378},[],{"categories":1380},[476],{"categories":1382},[76],{"categories":1384},[130],{"categories":1386},[76],{"categories":1388},[205,76],{"categories":1390},[122],{"categories":1392},[76],{"categories":1394},[],{"categories":1396},[76],{"categories":1398},[122],{"categories":1400},[1401],"Medical Imaging & Radiology",{"categories":1403},[76],{"categories":1405},[205],{"categories":1407},[130],{"categories":1409},[142],{"categories":1411},[],{"categories":1413},[76],{"categories":1415},[76],{"categories":1417},[76],{"categories":1419},[],{"categories":1421},[],{"categories":1423},[76],{"categories":1425},[423],{"categories":1427},[76],{"categories":1429},[122],{"categories":1431},[76],{"categories":1433},[76],{"categories":1435},[],{"categories":1437},[130],{"categories":1439},[76],{"categories":1441},[133],{"categories":1443},[142],{"categories":1445},[76],{"categories":1447},[423],{"categories":1449},[76],{"categories":1451},[130],{"categories":1453},[76],{"categories":1455},[205],{"categories":1457},[130],{"categories":1459},[268],{"categories":1461},[205],{"categories":1463},[125],{"categories":1465},[130],{"categories":1467},[76],{"categories":1469},[76],{"categories":1471},[133],{"categories":1473},[76],{"categories":1475},[76],{"categories":1477},[76],{"categories":1479},[130],{"categories":1481},[142],{"categories":1483},[142],{"categories":1485},[76],{"categories":1487},[133],{"categories":1489},[],{"categories":1491},[164],{"categories":1493},[],{"categories":1495},[133],{"categories":1497},[130],{"categories":1499},[130],{"categories":1501},[1097],{"categories":1503},[1097],{"categories":1505},[205],{"categories":1507},[76],{"categories":1509},[76],{"categories":1511},[130],{"categories":1513},[142],{"categories":1515},[205],{"categories":1517},[130],{"categories":1519},[164],{"categories":1521},[],{"categories":1523},[76],{"categories":1525},[],{"categories":1527},[76],{"categories":1529},[76],{"categories":1531},[76],{"categories":1533},[130],{"categories":1535},[1536],"Contract Review & E-Discovery",{"categories":1538},[205],{"categories":1540},[76],{"categories":1542},[122],{"categories":1544},[164],{"categories":1546},[76],{"categories":1548},[76],{"categories":1550},[233],{"categories":1552},[142],{"categories":1554},[76],{"categories":1556},[76],{"categories":1558},[130],{"categories":1560},[130],{"categories":1562},[797],{"categories":1564},[76],{"categories":1566},[76],{"categories":1568},[130],{"categories":1570},[130],{"categories":1572},[76],{"categories":1574},[76],{"categories":1576},[130],{"categories":1578},[76],{"categories":1580},[76],{"categories":1582},[423],{"categories":1584},[404],{"categories":1586},[76],{"categories":1588},[130],{"categories":1590},[76],{"categories":1592},[1593],"Law-Firm Practice & Adoption",{"categories":1595},[76],{"categories":1597},[130],{"categories":1599},[205],{"categories":1601},[76],{"categories":1603},[76],{"categories":1605},[],{"categories":1607},[],{"categories":1609},[142],{"categories":1611},[],{"categories":1613},[130],{"categories":1615},[122],{"categories":1617},[268],{"categories":1619},[76],{"categories":1621},[],{"categories":1623},[122],{"categories":1625},[125],{"categories":1627},[76],{"categories":1629},[233],{"categories":1631},[],{"categories":1633},[125],{"categories":1635},[125],{"categories":1637},[],{"categories":1639},[76],{"categories":1641},[76],{"categories":1643},[142],{"categories":1645},[],{"categories":1647},[],{"categories":1649},[],{"categories":1651},[],{"categories":1653},[76],{"categories":1655},[130],{"categories":1657},[268],{"categories":1659},[76],{"categories":1661},[122],{"categories":1663},[142],{"categories":1665},[76],{"categories":1667},[76],{"categories":1669},[142],{"categories":1671},[133],{"categories":1673},[76],{"categories":1675},[76],{"categories":1677},[820],{"categories":1679},[76],{"categories":1681},[76],{"categories":1683},[233],{"categories":1685},[142],{"categories":1687},[125],{"categories":1689},[76],{"categories":1691},[76],{"categories":1693},[205],{"categories":1695},[76],{"categories":1697},[76],{"categories":1699},[76],{"categories":1701},[130],{"categories":1703},[76,122],{"categories":1705},[423],{"categories":1707},[76],{"categories":1709},[76],{"categories":1711},[142],{"categories":1713},[142],{"categories":1715},[205],{"categories":1717},[130],{"categories":1719},[142],{"categories":1721},[76],{"categories":1723},[76],{"categories":1725},[],{"categories":1727},[],{"categories":1729},[76],{"categories":1731},[],{"categories":1733},[76],{"categories":1735},[142],{"categories":1737},[208],{"categories":1739},[164],{"categories":1741},[205],{"categories":1743},[76],{"categories":1745},[76],{"categories":1747},[142],{"categories":1749},[],{"categories":1751},[130],{"categories":1753},[76],{"categories":1755},[76],{"categories":1757},[76],{"categories":1759},[76],{"categories":1761},[],{"categories":1763},[130],{"categories":1765},[76],{"categories":1767},[76],{"categories":1769},[],{"categories":1771},[130],{"categories":1773},[76],{"categories":1775},[76],{"categories":1777},[125],{"categories":1779},[76],{"categories":1781},[],{"categories":1783},[122],{"categories":1785},[76],{"categories":1787},[76],{"categories":1789},[205],{"categories":1791},[142],{"categories":1793},[76],{"categories":1795},[122],{"categories":1797},[76],{"categories":1799},[142],{"categories":1801},[233],{"categories":1803},[130],{"categories":1805},[130],{"categories":1807},[76],{"categories":1809},[76],{"categories":1811},[76,205],{"categories":1813},[76],{"categories":1815},[164],{"categories":1817},[76],{"categories":1819},[164],{"categories":1821},[130],{"categories":1823},[205],{"categories":1825},[],{"categories":1827},[142],{"categories":1829},[268],{"categories":1831},[205],{"categories":1833},[142],{"categories":1835},[76],{"categories":1837},[133],{"categories":1839},[76],{"categories":1841},[130],{"categories":1843},[],{"categories":1845},[],{"categories":1847},[76],{"categories":1849},[],{"categories":1851},[],{"categories":1853},[133],{"categories":1855},[142],{"categories":1857},[76],{"categories":1859},[130],{"categories":1861},[130],{"categories":1863},[125],{"categories":1865},[130],{"categories":1867},[268],{"categories":1869},[76],{"categories":1871},[76],{"categories":1873},[153],{"categories":1875},[76],{"categories":1877},[76],{"categories":1879},[130],{"categories":1881},[76],{"categories":1883},[76],{"categories":1885},[377],{"categories":1887},[797],{"categories":1889},[],{"categories":1891},[205],{"categories":1893},[1593],{"categories":1895},[142],{"categories":1897},[],{"categories":1899},[],{"categories":1901},[130],{"categories":1903},[],{"categories":1905},[],{"categories":1907},[233],{"categories":1909},[76],{"categories":1911},[233],{"categories":1913},[130],{"categories":1915},[76],{"categories":1917},[142],{"categories":1919},[133],{"categories":1921},[],{"categories":1923},[76],{"categories":1925},[76],{"categories":1927},[142],{"categories":1929},[1536],{"categories":1931},[205],{"categories":1933},[205],{"categories":1935},[76],{"categories":1937},[130],{"categories":1939},[122],{"categories":1941},[76],{"categories":1943},[76],{"categories":1945},[76],{"categories":1947},[205],{"categories":1949},[205],{"categories":1951},[130],{"categories":1953},[130],{"categories":1955},[76],{"categories":1957},[76],{"categories":1959},[],{"categories":1961},[76],{"categories":1963},[],{"categories":1965},[1966],"Interaction & Product Design",{"categories":1968},[76],{"categories":1970},[130],{"categories":1972},[297],{"categories":1974},[164],{"categories":1976},[142],{"categories":1978},[76],{"categories":1980},[76],{"categories":1982},[142],{"categories":1984},[122],{"categories":1986},[130],{"categories":1988},[76],{"categories":1990},[],{"categories":1992},[130],{"categories":1994},[130],{"categories":1996},[],{"categories":1998},[142],{"categories":2000},[76],{"categories":2002},[122],{"categories":2004},[1966],{"categories":2006},[76],{"categories":2008},[122],{"categories":2010},[122],{"categories":2012},[],{"categories":2014},[142],{"categories":2016},[],{"categories":2018},[130],{"categories":2020},[164],{"categories":2022},[76],{"categories":2024},[130],{"categories":2026},[76],{"categories":2028},[130],{"categories":2030},[76],{"categories":2032},[76],{"categories":2034},[164],{"categories":2036},[208],{"categories":2038},[76],{"categories":2040},[133],{"categories":2042},[142],{"categories":2044},[2045],"Coding Agents & Dev Productivity",{"categories":2047},[164],{"categories":2049},[205],{"categories":2051},[76],{"categories":2053},[],{"categories":2055},[76],{"categories":2057},[797],{"categories":2059},[],{"categories":2061},[76],{"categories":2063},[268],{"categories":2065},[76],{"categories":2067},[164],{"categories":2069},[],{"categories":2071},[],{"categories":2073},[76],{"categories":2075},[],{"categories":2077},[130],{"categories":2079},[76],{"categories":2081},[],{"categories":2083},[142],{"categories":2085},[142],{"categories":2087},[76],{"categories":2089},[208],{"categories":2091},[],{"categories":2093},[76],{"categories":2095},[76],{"categories":2097},[76],{"categories":2099},[208],{"categories":2101},[142],{"categories":2103},[],{"categories":2105},[],{"categories":2107},[76],{"categories":2109},[76],{"categories":2111},[130],{"categories":2113},[130],{"categories":2115},[356],{"categories":2117},[142],{"categories":2119},[142],{"categories":2121},[130],{"categories":2123},[164],{"categories":2125},[164],{"categories":2127},[130],{"categories":2129},[130],{"categories":2131},[76],{"categories":2133},[122],{"categories":2135},[1966],{"categories":2137},[76,268],{"categories":2139},[208],{"categories":2141},[],{"categories":2143},[205],{"categories":2145},[142],{"categories":2147},[122],{"categories":2149},[76],{"categories":2151},[130],{"categories":2153},[2154],"The Designer's Role & Craft",{"categories":2156},[205],{"categories":2158},[],{"categories":2160},[130],{"categories":2162},[76],{"categories":2164},[130],{"categories":2166},[130],{"categories":2168},[76],{"categories":2170},[233],{"categories":2172},[76],{"categories":2174},[142],{"categories":2176},[76],{"categories":2178},[205],{"categories":2180},[76],{"categories":2182},[],{"categories":2184},[130],{"categories":2186},[205],{"categories":2188},[76],{"categories":2190},[76],{"categories":2192},[76],{"categories":2194},[2195],"AI UX Patterns",{"categories":2197},[130],{"categories":2199},[130],{"categories":2201},[130],{"categories":2203},[130],{"categories":2205},[233],{"categories":2207},[208],{"categories":2209},[76],{"categories":2211},[130],{"categories":2213},[76],{"categories":2215},[1097],{"categories":2217},[],{"categories":2219},[233],{"categories":2221},[130],{"categories":2223},[164],{"categories":2225},[142],{"categories":2227},[76],{"categories":2229},[130],{"categories":2231},[],{"categories":2233},[],{"categories":2235},[76],{"categories":2237},[130],{"categories":2239},[76],{"categories":2241},[130],{"categories":2243},[356],{"categories":2245},[205],{"categories":2247},[164],{"categories":2249},[142],{"categories":2251},[76],{"categories":2253},[130],{"categories":2255},[130],{"categories":2257},[],{"categories":2259},[76],{"categories":2261},[],{"categories":2263},[],{"categories":2265},[76],{"categories":2267},[76],{"categories":2269},[76],{"categories":2271},[130],{"categories":2273},[142],{"categories":2275},[],{"categories":2277},[],{"categories":2279},[208],{"categories":2281},[153],{"categories":2283},[76],{"categories":2285},[208],{"categories":2287},[164],{"categories":2289},[76],{"categories":2291},[76],{"categories":2293},[130],{"categories":2295},[76],{"categories":2297},[130],{"categories":2299},[76],{"categories":2301},[76],{"categories":2303},[130],{"categories":2305},[],{"categories":2307},[],{"categories":2309},[76],{"categories":2311},[268],{"categories":2313},[76],{"categories":2315},[],{"categories":2317},[],{"categories":2319},[205],{"categories":2321},[820],{"categories":2323},[130],{"categories":2325},[122],{"categories":2327},[2154],{"categories":2329},[],{"categories":2331},[],{"categories":2333},[76],{"categories":2335},[],{"categories":2337},[],{"categories":2339},[142],{"categories":2341},[164],{"categories":2343},[233],{"categories":2345},[125],{"categories":2347},[76],{"categories":2349},[76],{"categories":2351},[125],{"categories":2353},[],{"categories":2355},[205],{"categories":2357},[133],{"categories":2359},[76],{"categories":2361},[76],{"categories":2363},[130],{"categories":2365},[125],{"categories":2367},[76],{"categories":2369},[76],{"categories":2371},[122],{"categories":2373},[76],{"categories":2375},[],{"categories":2377},[122],{"categories":2379},[76],{"categories":2381},[233],{"categories":2383},[130],{"categories":2385},[164],{"categories":2387},[76],{"categories":2389},[76],{"categories":2391},[76],{"categories":2393},[125],{"categories":2395},[76],{"categories":2397},[76],{"categories":2399},[76],{"categories":2401},[130],{"categories":2403},[],{"categories":2405},[76],{"categories":2407},[142],{"categories":2409},[122],{"categories":2411},[76],{"categories":2413},[76],{"categories":2415},[],{"categories":2417},[76],{"categories":2419},[423],{"categories":2421},[125],{"categories":2423},[164],{"categories":2425},[76],{"categories":2427},[76],{"categories":2429},[],{"categories":2431},[125],{"categories":2433},[125],{"categories":2435},[76],{"categories":2437},[76],{"categories":2439},[133],{"categories":2441},[76],{"categories":2443},[76],{"categories":2445},[76],{"categories":2447},[142],{"categories":2449},[142],{"categories":2451},[76],{"categories":2453},[],{"categories":2455},[142],{"categories":2457},[76],{"categories":2459},[142],{"categories":2461},[512],{"categories":2463},[],{"categories":2465},[],{"categories":2467},[76],{"categories":2469},[164],{"categories":2471},[],{"categories":2473},[268],{"categories":2475},[76],{"categories":2477},[76],{"categories":2479},[205],{"categories":2481},[786],{"categories":2483},[],{"categories":2485},[76],{"categories":2487},[76],{"categories":2489},[76],{"categories":2491},[142],{"categories":2493},[76],{"categories":2495},[76],{"categories":2497},[76,268],{"categories":2499},[76],{"categories":2501},[76],{"categories":2503},[205],{"categories":2505},[130],{"categories":2507},[],{"categories":2509},[130],{"categories":2511},[130],{"categories":2513},[76],{"categories":2515},[76],{"categories":2517},[76],{"categories":2519},[208],{"categories":2521},[76],{"categories":2523},[2195],{"categories":2525},[122],{"categories":2527},[208],{"categories":2529},[122],{"categories":2531},[142],{"categories":2533},[205],{"categories":2535},[130],{"categories":2537},[76],{"categories":2539},[],{"categories":2541},[125],{"categories":2543},[76],{"categories":2545},[76],{"categories":2547},[164],{"categories":2549},[76],{"categories":2551},[76],{"categories":2553},[130],{"categories":2555},[76],{"categories":2557},[76],{"categories":2559},[125],{"categories":2561},[],{"categories":2563},[268],{"categories":2565},[76],{"categories":2567},[356],{"categories":2569},[205],{"categories":2571},[205],{"categories":2573},[142],{"categories":2575},[130],{"categories":2577},[76],{"categories":2579},[125],{"categories":2581},[164],{"categories":2583},[76],{"categories":2585},[205],{"categories":2587},[130],{"categories":2589},[76],{"categories":2591},[76],{"categories":2593},[476],{"categories":2595},[],{"categories":2597},[76],{"categories":2599},[76],{"categories":2601},[76],{"categories":2603},[],{"categories":2605},[],{"categories":2607},[76],{"categories":2609},[76],{"categories":2611},[130],{"categories":2613},[76],{"categories":2615},[76],{"categories":2617},[76],{"categories":2619},[142],{"categories":2621},[76],{"categories":2623},[76],{"categories":2625},[130],{"categories":2627},[76],{"categories":2629},[76],{"categories":2631},[76],{"categories":2633},[76],{"categories":2635},[76],{"categories":2637},[],{"categories":2639},[142],{"categories":2641},[208],{"categories":2643},[76],{"categories":2645},[130],{"categories":2647},[76],{"categories":2649},[],{"categories":2651},[],{"categories":2653},[76],{"categories":2655},[76],{"categories":2657},[76],{"categories":2659},[164],{"categories":2661},[],{"categories":2663},[76],{"categories":2665},[205],{"categories":2667},[76],{"categories":2669},[268],{"categories":2671},[1593],{"categories":2673},[164],{"categories":2675},[142],{"categories":2677},[142],{"categories":2679},[142],{"categories":2681},[164],{"categories":2683},[164],{"categories":2685},[268],{"categories":2687},[],{"categories":2689},[164],{"categories":2691},[76],{"categories":2693},[122],{"categories":2695},[142],{"categories":2697},[76],{"categories":2699},[164],{"categories":2701},[],{"categories":2703},[76],{"categories":2705},[142],{"categories":2707},[142],{"categories":2709},[208],{"categories":2711},[76],{"categories":2713},[164],{"categories":2715},[76],{"categories":2717},[142],{"categories":2719},[130],{"categories":2721},[164],{"categories":2723},[130],{"categories":2725},[268],{"categories":2727},[130],{"categories":2729},[76],{"categories":2731},[76],{"categories":2733},[142],{"categories":2735},[76],{"categories":2737},[],{"categories":2739},[130],{"categories":2741},[125],{"categories":2743},[142],{"categories":2745},[],{"categories":2747},[],{"categories":2749},[76],{"categories":2751},[130],{"categories":2753},[76],{"categories":2755},[2756],"Frameworks & Tooling",{"categories":2758},[76],{"categories":2760},[76],{"categories":2762},[142],{"categories":2764},[76],{"categories":2766},[76],{"categories":2768},[],{"categories":2770},[208],{"categories":2772},[208],{"categories":2774},[122],{"categories":2776},[130],{"categories":2778},[205],{"categories":2780},[],{"categories":2782},[1593],{"categories":2784},[76],{"categories":2786},[142],{"categories":2788},[76],{"categories":2790},[268],{"categories":2792},[268],{"categories":2794},[],{"categories":2796},[130],{"categories":2798},[164],{"categories":2800},[164],{"categories":2802},[76],{"categories":2804},[130],{"categories":2806},[],{"categories":2808},[205],{"categories":2810},[76],{"categories":2812},[76],{"categories":2814},[],{"categories":2816},[76],{"categories":2818},[76],{"categories":2820},[],{"categories":2822},[142],{"categories":2824},[76],{"categories":2826},[142],{"categories":2828},[268],{"categories":2830},[76],{"categories":2832},[76],{"categories":2834},[142],{"categories":2836},[125],{"categories":2838},[76],{"categories":2840},[1593],{"categories":2842},[],{"categories":2844},[130],{"categories":2846},[122],{"categories":2848},[76],{"categories":2850},[122],{"categories":2852},[],{"categories":2854},[130],{"categories":2856},[76],{"categories":2858},[2859],"AI Design Tooling",{"categories":2861},[205],{"categories":2863},[76],{"categories":2865},[76],{"categories":2867},[142],{"categories":2869},[205],{"categories":2871},[76],{"categories":2873},[142],{"categories":2875},[164],{"categories":2877},[133],{"categories":2879},[142],{"categories":2881},[76],{"categories":2883},[130],{"categories":2885},[],{"categories":2887},[76],{"categories":2889},[76],{"categories":2891},[130],{"categories":2893},[76],{"categories":2895},[76],{"categories":2897},[76],{"categories":2899},[],{"categories":2901},[130],{"categories":2903},[2756],{"categories":2905},[76],{"categories":2907},[130],{"categories":2909},[130],{"categories":2911},[142],{"categories":2913},[142],{"categories":2915},[],{"categories":2917},[142],{"categories":2919},[76],{"categories":2921},[76],{"categories":2923},[130],{"categories":2925},[125],{"categories":2927},[76],{"categories":2929},[],{"categories":2931},[76],{"categories":2933},[76],{"categories":2935},[1966],{"categories":2937},[],{"categories":2939},[76],{"categories":2941},[76],{"categories":2943},[76],{"categories":2945},[76],{"categories":2947},[],{"categories":2949},[76],{"categories":2951},[76],{"categories":2953},[76],{"categories":2955},[233],{"categories":2957},[164],{"categories":2959},[76],{"categories":2961},[76],{"categories":2963},[1593],{"categories":2965},[122],{"categories":2967},[76],{"categories":2969},[76],{"categories":2971},[208],{"categories":2973},[76],{"categories":2975},[164],{"categories":2977},[130],{"categories":2979},[],{"categories":2981},[76],{"categories":2983},[76],{"categories":2985},[205],{"categories":2987},[76],{"categories":2989},[233],{"categories":2991},[76],{"categories":2993},[130],{"categories":2995},[],{"categories":2997},[],{"categories":2999},[],{"categories":3001},[122],{"categories":3003},[164],{"categories":3005},[130],{"categories":3007},[76],{"categories":3009},[76],{"categories":3011},[76],{"categories":3013},[377],{"categories":3015},[205],{"categories":3017},[130],{"categories":3019},[76],{"categories":3021},[],{"categories":3023},[130],{"categories":3025},[130],{"categories":3027},[],{"categories":3029},[76],{"categories":3031},[130],{"categories":3033},[76],{"categories":3035},[],{"categories":3037},[76],{"categories":3039},[76],{"categories":3041},[164],{"categories":3043},[205],{"categories":3045},[130],{"categories":3047},[205],{"categories":3049},[130],{"categories":3051},[76],{"categories":3053},[125],{"categories":3055},[],{"categories":3057},[],{"categories":3059},[76],{"categories":3061},[76],{"categories":3063},[122],{"categories":3065},[130],{"categories":3067},[164],{"categories":3069},[],{"categories":3071},[205],{"categories":3073},[],{"categories":3075},[142],{"categories":3077},[76],{"categories":3079},[142],{"categories":3081},[205],{"categories":3083},[142],{"categories":3085},[76],{"categories":3087},[],{"categories":3089},[76],{"categories":3091},[76],{"categories":3093},[],{"categories":3095},[76],{"categories":3097},[233],{"categories":3099},[76],{"categories":3101},[268],{"categories":3103},[142],{"categories":3105},[],{"categories":3107},[130],{"categories":3109},[76],{"categories":3111},[122],{"categories":3113},[476],{"categories":3115},[76],{"categories":3117},[130],{"categories":3119},[130],{"categories":3121},[76],{"categories":3123},[76],{"categories":3125},[],{"categories":3127},[76],{"categories":3129},[122],{"categories":3131},[76],{"categories":3133},[125],{"categories":3135},[142],{"categories":3137},[205],{"categories":3139},[],{"categories":3141},[],{"categories":3143},[],{"categories":3145},[130],{"categories":3147},[142],{"categories":3149},[205],{"categories":3151},[164],{"categories":3153},[76],{"categories":3155},[164],{"categories":3157},[130],{"categories":3159},[205],{"categories":3161},[76],{"categories":3163},[],{"categories":3165},[76],{"categories":3167},[153],{"categories":3169},[130],{"categories":3171},[205],{"categories":3173},[164],{"categories":3175},[125],{"categories":3177},[142],{"categories":3179},[76],{"categories":3181},[76],{"categories":3183},[164],{"categories":3185},[233],{"categories":3187},[],{"categories":3189},[],{"categories":3191},[208],{"categories":3193},[423],{"categories":3195},[76],{"categories":3197},[130],{"categories":3199},[76,142],{"categories":3201},[164],{"categories":3203},[76],{"categories":3205},[76],{"categories":3207},[76],{"categories":3209},[76],{"categories":3211},[130],{"categories":3213},[76],{"categories":3215},[130],{"categories":3217},[76],{"categories":3219},[76],{"categories":3221},[],{"categories":3223},[76],{"categories":3225},[1097],{"categories":3227},[142],{"categories":3229},[205],{"categories":3231},[76],{"categories":3233},[76],{"categories":3235},[76],{"categories":3237},[208],{"categories":3239},[130],{"categories":3241},[233],{"categories":3243},[268],{"categories":3245},[],{"categories":3247},[76],{"categories":3249},[125],{"categories":3251},[130],{"categories":3253},[122],{"categories":3255},[130],{"categories":3257},[76],{"categories":3259},[130],{"categories":3261},[133],{"categories":3263},[142],{"categories":3265},[76],{"categories":3267},[76],{"categories":3269},[],{"categories":3271},[],{"categories":3273},[],{"categories":3275},[268],{"categories":3277},[76],{"categories":3279},[164],{"categories":3281},[76],{"categories":3283},[76],{"categories":3285},[76],{"categories":3287},[76],{"categories":3289},[],{"categories":3291},[208],{"categories":3293},[125],{"categories":3295},[130],{"categories":3297},[76],{"categories":3299},[],{"categories":3301},[76],{"categories":3303},[130],{"categories":3305},[76],{"categories":3307},[268],{"categories":3309},[],{"categories":3311},[205],{"categories":3313},[205],{"categories":3315},[],{"categories":3317},[142],{"categories":3319},[76],{"categories":3321},[205],{"categories":3323},[76],{"categories":3325},[125],{"categories":3327},[130],{"categories":3329},[76],{"categories":3331},[],{"categories":3333},[164],{"categories":3335},[76],{"categories":3337},[76],{"categories":3339},[76],{"categories":3341},[205],{"categories":3343},[130],{"categories":3345},[164],{"categories":3347},[],{"categories":3349},[130],{"categories":3351},[125],{"categories":3353},[130],{"categories":3355},[205],{"categories":3357},[76],{"categories":3359},[76],{"categories":3361},[76],{"categories":3363},[423],{"categories":3365},[76],{"categories":3367},[],{"categories":3369},[76],{"categories":3371},[76],{"categories":3373},[268],{"categories":3375},[164],{"categories":3377},[208],{"categories":3379},[512],{"categories":3381},[208],{"categories":3383},[76],{"categories":3385},[],{"categories":3387},[],{"categories":3389},[],{"categories":3391},[130],{"categories":3393},[130],{"categories":3395},[142],{"categories":3397},[76],{"categories":3399},[404],{"categories":3401},[142],{"categories":3403},[76],{"categories":3405},[76],{"categories":3407},[76],{"categories":3409},[76],{"categories":3411},[130],{"categories":3413},[],{"categories":3415},[],{"categories":3417},[76],{"categories":3419},[],{"categories":3421},[76],{"categories":3423},[130],{"categories":3425},[205],{"categories":3427},[76],{"categories":3429},[76],{"categories":3431},[],{"categories":3433},[130],{"categories":3435},[133],{"categories":3437},[76],{"categories":3439},[205],{"categories":3441},[76],{"categories":3443},[130],{"categories":3445},[125],{"categories":3447},[76],{"categories":3449},[233],{"categories":3451},[130],{"categories":3453},[76],{"categories":3455},[76],{"categories":3457},[786],{"categories":3459},[76],{"categories":3461},[130],{"categories":3463},[76],{"categories":3465},[142],{"categories":3467},[76],{"categories":3469},[476],{"categories":3471},[205],{"categories":3473},[],{"categories":3475},[164],{"categories":3477},[423],{"categories":3479},[130],{"categories":3481},[76],{"categories":3483},[],{"categories":3485},[164],{"categories":3487},[356],{"categories":3489},[130],{"categories":3491},[130],{"categories":3493},[76],{"categories":3495},[76],{"categories":3497},[130],{"categories":3499},[],{"categories":3501},[125],{"categories":3503},[76],{"categories":3505},[125],{"categories":3507},[130],{"categories":3509},[],{"categories":3511},[142],{"categories":3513},[76],{"categories":3515},[76],{"categories":3517},[122],{"categories":3519},[164],{"categories":3521},[268],{"categories":3523},[153],{"categories":3525},[130],{"categories":3527},[130],{"categories":3529},[76],{"categories":3531},[130],{"categories":3533},[76],{"categories":3535},[122],{"categories":3537},[],{"categories":3539},[76],{"categories":3541},[76],{"categories":3543},[76],{"categories":3545},[76],{"categories":3547},[],{"categories":3549},[],{"categories":3551},[205],{"categories":3553},[130],{"categories":3555},[76,125],{"categories":3557},[130],{"categories":3559},[76],{"categories":3561},[],{"categories":3563},[122],{"categories":3565},[208],{"categories":3567},[125],{"categories":3569},[76],{"categories":3571},[142],{"categories":3573},[76],{"categories":3575},[76],{"categories":3577},[130],{"categories":3579},[76],{"categories":3581},[76],{"categories":3583},[76],{"categories":3585},[164],{"categories":3587},[1097],{"categories":3589},[130],{"categories":3591},[76],{"categories":3593},[],{"categories":3595},[],{"categories":3597},[76],{"categories":3599},[130],{"categories":3601},[76],{"categories":3603},[76],{"categories":3605},[268],{"categories":3607},[],{"categories":3609},[76],{"categories":3611},[130],{"categories":3613},[153],{"categories":3615},[130],{"categories":3617},[423],{"categories":3619},[],{"categories":3621},[377],{"categories":3623},[130],{"categories":3625},[76],{"categories":3627},[233],{"categories":3629},[76],{"categories":3631},[208],{"categories":3633},[130],{"categories":3635},[76],{"categories":3637},[423],{"categories":3639},[76],{"categories":3641},[268],{"categories":3643},[],{"categories":3645},[76],{"categories":3647},[233],{"categories":3649},[205],{"categories":3651},[76],{"categories":3653},[76],{"categories":3655},[76],{"categories":3657},[],{"categories":3659},[233],{"categories":3661},[164],{"categories":3663},[76],{"categories":3665},[76],{"categories":3667},[512],{"categories":3669},[122],{"categories":3671},[76],{"categories":3673},[],{"categories":3675},[],{"categories":3677},[205],{"categories":3679},[76],{"categories":3681},[208],{"categories":3683},[233],{"categories":3685},[130],{"categories":3687},[76],{"categories":3689},[233],{"categories":3691},[164],{"categories":3693},[],{"categories":3695},[76],{"categories":3697},[76],{"categories":3699},[],{"categories":3701},[76],{"categories":3703},[76],{"categories":3705},[535],{"categories":3707},[76],{"categories":3709},[76],{"categories":3711},[130],{"categories":3713},[142],{"categories":3715},[423],{"categories":3717},[76],{"categories":3719},[76],{"categories":3721},[76],{"categories":3723},[],{"categories":3725},[76,142],{"categories":3727},[164],{"categories":3729},[130],{"categories":3731},[142],{"categories":3733},[130],{"categories":3735},[820],{"categories":3737},[142],{"categories":3739},[76],{"categories":3741},[122],{"categories":3743},[],{"categories":3745},[],{"categories":3747},[130],{"categories":3749},[76],{"categories":3751},[142],{"categories":3753},[76],{"categories":3755},[122],{"categories":3757},[142],{"categories":3759},[142],{"categories":3761},[76],{"categories":3763},[233],{"categories":3765},[76],{"categories":3767},[142],{"categories":3769},[76],{"categories":3771},[],{"categories":3773},[76],{"categories":3775},[205,76],{"categories":3777},[268],{"categories":3779},[122],{"categories":3781},[],{"categories":3783},[76],{"categories":3785},[76],{"categories":3787},[125],{"categories":3789},[125],{"categories":3791},[76],{"categories":3793},[76],{"categories":3795},[356],{"categories":3797},[76],{"categories":3799},[125],{"categories":3801},[142],{"categories":3803},[208],{"categories":3805},[130],{"categories":3807},[142],{"categories":3809},[76],{"categories":3811},[76],{"categories":3813},[164],{"categories":3815},[233],{"categories":3817},[205],{"categories":3819},[76],{"categories":3821},[76],{"categories":3823},[76],{"categories":3825},[76],{"categories":3827},[122],{"categories":3829},[76],{"categories":3831},[130],{"categories":3833},[130],{"categories":3835},[142],{"categories":3837},[164],{"categories":3839},[142],{"categories":3841},[142],{"categories":3843},[76],{"categories":3845},[],{"categories":3847},[],{"categories":3849},[208],{"categories":3851},[76],{"categories":3853},[142],{"categories":3855},[76],{"categories":3857},[205],{"categories":3859},[423],{"categories":3861},[377],{"categories":3863},[356],{"categories":3865},[76],{"categories":3867},[76],{"categories":3869},[76],{"categories":3871},[208],{"categories":3873},[76],{"categories":3875},[76],{"categories":3877},[76],{"categories":3879},[76],{"categories":3881},[76],{"categories":3883},[76],{"categories":3885},[130],{"categories":3887},[122],{"categories":3889},[130],{"categories":3891},[76,125],{"categories":3893},[],{"categories":3895},[205],{"categories":3897},[],{"categories":3899},[133],{"categories":3901},[76],{"categories":3903},[164],{"categories":3905},[122],{"categories":3907},[122],{"categories":3909},[130],{"categories":3911},[130],{"categories":3913},[130],{"categories":3915},[76],{"categories":3917},[76],{"categories":3919},[125],{"categories":3921},[130],{"categories":3923},[142],{"categories":3925},[233],{"categories":3927},[76],{"categories":3929},[],{"categories":3931},[164],{"categories":3933},[76],{"categories":3935},[76],{"categories":3937},[76],{"categories":3939},[76],{"categories":3941},[76],{"categories":3943},[142],{"categories":3945},[164],{"categories":3947},[142],{"categories":3949},[142],{"categories":3951},[76],{"categories":3953},[76],{"categories":3955},[76],{"categories":3957},[377],{"categories":3959},[76],{"categories":3961},[130],{"categories":3963},[164],{"categories":3965},[76],{"categories":3967},[76],{"categories":3969},[76],{"categories":3971},[130],{"categories":3973},[76],{"categories":3975},[76],{"categories":3977},[76],{"categories":3979},[2756],{"categories":3981},[3982],"Clinical AI",{"categories":3984},[205],{"categories":3986},[76],{"categories":3988},[76],{"categories":3990},[76],{"categories":3992},[268],{"categories":3994},[2195],{"categories":3996},[76],{"categories":3998},[133],{"categories":4000},[76],{"categories":4002},[130],{"categories":4004},[76],{"categories":4006},[76],{"categories":4008},[164],{"categories":4010},[76],{"categories":4012},[130],{"categories":4014},[142],{"categories":4016},[233],{"categories":4018},[76],{"categories":4020},[76],{"categories":4022},[125],{"categories":4024},[76],{"categories":4026},[76],{"categories":4028},[476],{"categories":4030},[76],{"categories":4032},[],{"categories":4034},[76],{"categories":4036},[142],{"categories":4038},[122],{"categories":4040},[76],{"categories":4042},[],{"categories":4044},[],{"categories":4046},[76],{"categories":4048},[],{"categories":4050},[125],{"categories":4052},[76],{"categories":4054},[130],{"categories":4056},[164],{"categories":4058},[164],{"categories":4060},[164],{"categories":4062},[164],{"categories":4064},[],{"categories":4066},[122],{"categories":4068},[130],{"categories":4070},[164],{"categories":4072},[76],{"categories":4074},[535],{"categories":4076},[133],{"categories":4078},[76],{"categories":4080},[122],{"categories":4082},[76],{"categories":4084},[130],{"categories":4086},[76],{"categories":4088},[76],{"categories":4090},[76,130],{"categories":4092},[130],{"categories":4094},[268],{"categories":4096},[164],{"categories":4098},[130],{"categories":4100},[164],{"categories":4102},[130],{"categories":4104},[76],{"categories":4106},[],{"categories":4108},[164],{"categories":4110},[233],{"categories":4112},[122],{"categories":4114},[76],{"categories":4116},[76],{"categories":4118},[],{"categories":4120},[142],{"categories":4122},[],{"categories":4124},[122],{"categories":4126},[130],{"categories":4128},[164],{"categories":4130},[76],{"categories":4132},[164],{"categories":4134},[122],{"categories":4136},[164],{"categories":4138},[164],{"categories":4140},[],{"categories":4142},[125],{"categories":4144},[130],{"categories":4146},[164],{"categories":4148},[164],{"categories":4150},[164],{"categories":4152},[164],{"categories":4154},[164],{"categories":4156},[164],{"categories":4158},[164],{"categories":4160},[164],{"categories":4162},[164],{"categories":4164},[164],{"categories":4166},[208],{"categories":4168},[122],{"categories":4170},[76],{"categories":4172},[76],{"categories":4174},[130],{"categories":4176},[130],{"categories":4178},[],{"categories":4180},[76],{"categories":4182},[76,122],{"categories":4184},[],{"categories":4186},[130],{"categories":4188},[76],{"categories":4190},[164],{"categories":4192},[130],{"categories":4194},[820],{"categories":4196},[76],{"categories":4198},[76],{"categories":4200},[76],{"categories":4202},[76],{"categories":4204},[76],{"categories":4206},[356],{"categories":4208},[76],{"categories":4210},[130],{"categories":4212},[125],{"categories":4214},[130],{"categories":4216},[130],{"categories":4218},[],{"categories":4220},[130],{"categories":4222},[205],{"categories":4224},[164],{"categories":4226},[76],{"categories":4228},[],{"categories":4230},[133],{"categories":4232},[],{"categories":4234},[142],{"categories":4236},[130],{"categories":4238},[205],{"categories":4240},[76],{"categories":4242},[],{"categories":4244},[76],{"categories":4246},[],{"categories":4248},[233],{"categories":4250},[76],{"categories":4252},[],{"categories":4254},[],{"categories":4256},[164],{"categories":4258},[122],{"categories":4260},[76],{"categories":4262},[76],{"categories":4264},[125],{"categories":4266},[76],{"categories":4268},[76],{"categories":4270},[76],{"categories":4272},[125],{"categories":4274},[125],{"categories":4276},[205],{"categories":4278},[],{"categories":4280},[76],{"categories":4282},[164],{"categories":4284},[],{"categories":4286},[76],{"categories":4288},[76],{"categories":4290},[205],{"categories":4292},[76],{"categories":4294},[233],{"categories":4296},[76],{"categories":4298},[268],{"categories":4300},[],{"categories":4302},[130],{"categories":4304},[233],{"categories":4306},[142],{"categories":4308},[],{"categories":4310},[76],{"categories":4312},[],{"categories":4314},[130],{"categories":4316},[205],{"categories":4318},[142],{"categories":4320},[],{"categories":4322},[2756],{"categories":4324},[125],{"categories":4326},[122],{"categories":4328},[76],{"categories":4330},[208],{"categories":4332},[130],{"categories":4334},[205],{"categories":4336},[142],{"categories":4338},[],{"categories":4340},[],{"categories":4342},[76],{"categories":4344},[122],{"categories":4346},[76],{"categories":4348},[233],{"categories":4350},[],{"categories":4352},[130],{"categories":4354},[130],{"categories":4356},[76],{"categories":4358},[130],{"categories":4360},[76],{"categories":4362},[164],{"categories":4364},[142],{"categories":4366},[76],{"categories":4368},[130],{"categories":4370},[133],{"categories":4372},[76],{"categories":4374},[76],{"categories":4376},[130],{"categories":4378},[76],{"categories":4380},[133],{"categories":4382},[233],{"categories":4384},[164],{"categories":4386},[],{"categories":4388},[233],{"categories":4390},[76],{"categories":4392},[],{"categories":4394},[142],{"categories":4396},[130],{"categories":4398},[],{"categories":4400},[76],{"categories":4402},[76],{"categories":4404},[76],{"categories":4406},[76],{"categories":4408},[130],{"categories":4410},[125],{"categories":4412},[122],{"categories":4414},[76],{"categories":4416},[205],{"categories":4418},[142],{"categories":4420},[142],{"categories":4422},[76],{"categories":4424},[208],{"categories":4426},[130],{"categories":4428},[76],{"categories":4430},[76],{"categories":4432},[130],{"categories":4434},[76],{"categories":4436},[125],{"categories":4438},[205],{"categories":4440},[142],{"categories":4442},[130],{"categories":4444},[76],{"categories":4446},[133],{"categories":4448},[76],{"categories":4450},[130],{"categories":4452},[76],{"categories":4454},[164],{"categories":4456},[],{"categories":4458},[122],{"categories":4460},[76],{"categories":4462},[76],{"categories":4464},[76],{"categories":4466},[142],{"categories":4468},[142],{"categories":4470},[76],{"categories":4472},[142],{"categories":4474},[76],{"categories":4476},[130],{"categories":4478},[76],{"categories":4480},[76],{"categories":4482},[76],{"categories":4484},[76],{"categories":4486},[76],{"categories":4488},[],{"categories":4490},[76],{"categories":4492},[205],{"categories":4494},[125],{"categories":4496},[164],{"categories":4498},[76],{"categories":4500},[130],{"categories":4502},[76],{"categories":4504},[76],{"categories":4506},[205],{"categories":4508},[130],{"categories":4510},[76],{"categories":4512},[233],{"categories":4514},[76],{"categories":4516},[208],{"categories":4518},[76],{"categories":4520},[76],{"categories":4522},[164],{"categories":4524},[76],{"categories":4526},[76],{"categories":4528},[76],{"categories":4530},[130],{"categories":4532},[268],{"categories":4534},[76],{"categories":4536},[142],{"categories":4538},[130],{"categories":4540},[208],{"categories":4542},[],{"categories":4544},[130],{"categories":4546},[142],{"categories":4548},[76],{"categories":4550},[76],{"categories":4552},[2045],{"categories":4554},[205],{"categories":4556},[297],{"categories":4558},[76],{"categories":4560},[76],{"categories":4562},[122],{"categories":4564},[76],{"categories":4566},[142],{"categories":4568},[125],{"categories":4570},[142],{"categories":4572},[76],{"categories":4574},[],{"categories":4576},[130],{"categories":4578},[130],{"categories":4580},[76],{"categories":4582},[76],{"categories":4584},[208],{"categories":4586},[],{"categories":4588},[164],{"categories":4590},[],{"categories":4592},[164],{"categories":4594},[76],{"categories":4596},[76],{"categories":4598},[130],{"categories":4600},[76],{"categories":4602},[130],{"categories":4604},[130],{"categories":4606},[],{"categories":4608},[164],{"categories":4610},[76],{"categories":4612},[],{"categories":4614},[76],{"categories":4616},[76],{"categories":4618},[],{"categories":4620},[205],{"categories":4622},[142],{"categories":4624},[130],{"categories":4626},[76],{"categories":4628},[76],{"categories":4630},[233],{"categories":4632},[76],{"categories":4634},[76],{"categories":4636},[76],{"categories":4638},[122],{"categories":4640},[76],{"categories":4642},[],{"categories":4644},[76],{"categories":4646},[76],{"categories":4648},[],{"categories":4650},[122],{"categories":4652},[164],{"categories":4654},[142],{"categories":4656},[133],{"categories":4658},[423],{"categories":4660},[76],{"categories":4662},[76],{"categories":4664},[76],{"categories":4666},[142],{"categories":4668},[164],{"categories":4670},[205],{"categories":4672},[76],{"categories":4674},[76],{"categories":4676},[76],{"categories":4678},[164],{"categories":4680},[205],{"categories":4682},[76],{"categories":4684},[76],{"categories":4686},[164],{"categories":4688},[205],{"categories":4690},[76],{"categories":4692},[164],{"categories":4694},[130],{"categories":4696},[130],{"categories":4698},[130],{"categories":4700},[142],{"categories":4702},[164],{"categories":4704},[130],{"categories":4706},[130],{"categories":4708},[76],{"categories":4710},[142],{"categories":4712},[205],{"categories":4714},[76],{"categories":4716},[76],{"categories":4718},[],{"categories":4720},[130],{"categories":4722},[],{"categories":4724},[76],{"categories":4726},[76],{"categories":4728},[],{"categories":4730},[],{"categories":4732},[130],{"categories":4734},[125],{"categories":4736},[130],{"categories":4738},[4739],"Liability & Ethics",{"categories":4741},[76],{"categories":4743},[130],{"categories":4745},[122],{"categories":4747},[130],{"categories":4749},[125],{"categories":4751},[233],{"categories":4753},[130],{"categories":4755},[76],{"categories":4757},[],{"categories":4759},[512],{"categories":4761},[130],{"categories":4763},[],{"categories":4765},[122],{"categories":4767},[130],{"categories":4769},[],{"categories":4771},[130],{"categories":4773},[76],{"categories":4775},[76],{"categories":4777},[76],{"categories":4779},[164],{"categories":4781},[76],{"categories":4783},[76],{"categories":4785},[130],{"categories":4787},[76],{"categories":4789},[76],{"categories":4791},[76],{"categories":4793},[164],{"categories":4795},[130],{"categories":4797},[142],{"categories":4799},[205],{"categories":4801},[122],{"categories":4803},[76],{"categories":4805},[76],{"categories":4807},[],{"categories":4809},[130],{"categories":4811},[130],{"categories":4813},[130],{"categories":4815},[423],{"categories":4817},[205],{"categories":4819},[130],{"categories":4821},[268],{"categories":4823},[164],{"categories":4825},[76],{"categories":4827},[205],{"categories":4829},[76],{"categories":4831},[122],{"categories":4833},[],{"categories":4835},[130],{"categories":4837},[76],{"categories":4839},[76],{"categories":4841},[130],{"categories":4843},[76],{"categories":4845},[205],{"categories":4847},[],{"categories":4849},[130],{"categories":4851},[133],{"categories":4853},[164],{"categories":4855},[130],{"categories":4857},[125],{"categories":4859},[],{"categories":4861},[76],{"categories":4863},[133],{"categories":4865},[76],{"categories":4867},[130],{"categories":4869},[164],{"categories":4871},[122],{"categories":4873},[268],{"categories":4875},[76],{"categories":4877},[76],{"categories":4879},[76],{"categories":4881},[164],{"categories":4883},[125],{"categories":4885},[76],{"categories":4887},[205],{"categories":4889},[164],{"categories":4891},[268],{"categories":4893},[76],{"categories":4895},[130],{"categories":4897},[],{"categories":4899},[476],{"categories":4901},[],{"categories":4903},[76],{"categories":4905},[268],{"categories":4907},[208],{"categories":4909},[130],{"categories":4911},[130],{"categories":4913},[4914],"Design News & Tools",{"categories":4916},[76],{"categories":4918},[164],{"categories":4920},[76],{"categories":4922},[76],{"categories":4924},[122],{"categories":4926},[76],{"categories":4928},[205],{"categories":4930},[130],{"categories":4932},[130],{"categories":4934},[205],{"categories":4936},[76],{"categories":4938},[423],{"categories":4940},[130],{"categories":4942},[76],{"categories":4944},[76],{"categories":4946},[423],{"categories":4948},[76],{"categories":4950},[233],{"categories":4952},[76],{"categories":4954},[130],{"categories":4956},[],{"categories":4958},[76],{"categories":4960},[76],{"categories":4962},[76],{"categories":4964},[164],{"categories":4966},[122],{"categories":4968},[],{"categories":4970},[76],{"categories":4972},[76],{"categories":4974},[142],{"categories":4976},[535],{"categories":4978},[142],{"categories":4980},[205],{"categories":4982},[76],{"categories":4984},[76,130],{"categories":4986},[233,125],{"categories":4988},[76],{"categories":4990},[76],{"categories":4992},[76],{"categories":4994},[],{"categories":4996},[130],{"categories":4998},[],{"categories":5000},[142],{"categories":5002},[76],{"categories":5004},[142],{"categories":5006},[],{"categories":5008},[130],{"categories":5010},[76],{"categories":5012},[164],{"categories":5014},[76],{"categories":5016},[],{"categories":5018},[130],{"categories":5020},[76],{"categories":5022},[],{"categories":5024},[205],{"categories":5026},[76],{"categories":5028},[76],{"categories":5030},[130],{"categories":5032},[76],{"categories":5034},[76],{"categories":5036},[122],{"categories":5038},[130],{"categories":5040},[76],{"categories":5042},[],{"categories":5044},[268],{"categories":5046},[233],{"categories":5048},[125],{"categories":5050},[125],{"categories":5052},[76],{"categories":5054},[122],{"categories":5056},[122],{"categories":5058},[76],{"categories":5060},[130],{"categories":5062},[76],{"categories":5064},[76],{"categories":5066},[76],{"categories":5068},[142],{"categories":5070},[76],{"categories":5072},[122],{"categories":5074},[76],{"categories":5076},[130],{"categories":5078},[76],{"categories":5080},[233],{"categories":5082},[76],{"categories":5084},[164],{"categories":5086},[76],{"categories":5088},[76],{"categories":5090},[130],{"categories":5092},[76],{"categories":5094},[130],{"categories":5096},[],{"categories":5098},[142],{"categories":5100},[],{"categories":5102},[142],{"categories":5104},[130],{"categories":5106},[122],{"categories":5108},[],{"categories":5110},[208],{"categories":5112},[268],{"categories":5114},[76],{"categories":5116},[142],{"categories":5118},[76],{"categories":5120},[],{"categories":5122},[164],{"categories":5124},[130],{"categories":5126},[142],{"categories":5128},[205],{"categories":5130},[76],{"categories":5132},[76],{"categories":5134},[130],{"categories":5136},[142],{"categories":5138},[130],{"categories":5140},[164],{"categories":5142},[76],{"categories":5144},[133],{"categories":5146},[122],{"categories":5148},[133],{"categories":5150},[164],{"categories":5152},[142],{"categories":5154},[76],{"categories":5156},[205],{"categories":5158},[125],{"categories":5160},[76],{"categories":5162},[76],{"categories":5164},[76],{"categories":5166},[76],{"categories":5168},[76],{"categories":5170},[76],{"categories":5172},[130],{"categories":5174},[76],{"categories":5176},[130],{"categories":5178},[76],{"categories":5180},[76],{"categories":5182},[122],{"categories":5184},[76],{"categories":5186},[130],{"categories":5188},[130],{"categories":5190},[205],{"categories":5192},[130],{"categories":5194},[130],{"categories":5196},[122],{"categories":5198},[130],{"categories":5200},[205],{"categories":5202},[],{"categories":5204},[76],{"categories":5206},[208],{"categories":5208},[423],{"categories":5210},[76],{"categories":5212},[76],{"categories":5214},[76],{"categories":5216},[142],{"categories":5218},[76],{"categories":5220},[],{"categories":5222},[130],{"categories":5224},[233],{"categories":5226},[76],{"categories":5228},[164],{"categories":5230},[130],{"categories":5232},[76],{"categories":5234},[233],{"categories":5236},[130],{"categories":5238},[125],{"categories":5240},[125],{"categories":5242},[76],{"categories":5244},[76],{"categories":5246},[76],{"categories":5248},[122],{"categories":5250},[],{"categories":5252},[76],{"categories":5254},[76],{"categories":5256},[130],{"categories":5258},[130],{"categories":5260},[76],{"categories":5262},[76],{"categories":5264},[76],{"categories":5266},[142],{"categories":5268},[],{"categories":5270},[122],{"categories":5272},[76],{"categories":5274},[76],{"categories":5276},[130],{"categories":5278},[130],{"categories":5280},[],{"categories":5282},[142],{"categories":5284},[142],{"categories":5286},[76],{"categories":5288},[233],{"categories":5290},[125],{"categories":5292},[205],{"categories":5294},[],{"categories":5296},[76],{"categories":5298},[130],{"categories":5300},[122],{"categories":5302},[76],{"categories":5304},[76],{"categories":5306},[142],{"categories":5308},[122],{"categories":5310},[164],{"categories":5312},[208],{"categories":5314},[164],{"categories":5316},[130],{"categories":5318},[],{"categories":5320},[164],{"categories":5322},[130],{"categories":5324},[205],{"categories":5326},[208],{"categories":5328},[76],{"categories":5330},[],{"categories":5332},[130],{"categories":5334},[130],{"categories":5336},[2756],{"categories":5338},[164],{"categories":5340},[142],{"categories":5342},[76],{"categories":5344},[76],{"categories":5346},[76],{"categories":5348},[76],{"categories":5350},[125],{"categories":5352},[76],{"categories":5354},[122],{"categories":5356},[1593],{"categories":5358},[268],{"categories":5360},[122],{"categories":5362},[],{"categories":5364},[],{"categories":5366},[164],{"categories":5368},[130],{"categories":5370},[205],{"categories":5372},[76],{"categories":5374},[164],{"categories":5376},[],{"categories":5378},[130],{"categories":5380},[130],{"categories":5382},[130],{"categories":5384},[],{"categories":5386},[76],{"categories":5388},[],{"categories":5390},[164],{"categories":5392},[122],{"categories":5394},[205],{"categories":5396},[76],{"categories":5398},[130],{"categories":5400},[164],{"categories":5402},[76],{"categories":5404},[164],{"categories":5406},[],{"categories":5408},[164],{"categories":5410},[122],{"categories":5412},[423],{"categories":5414},[130],{"categories":5416},[76],{"categories":5418},[],{"categories":5420},[142],{"categories":5422},[130],{"categories":5424},[133],{"categories":5426},[130],{"categories":5428},[122],{"categories":5430},[],{"categories":5432},[],{"categories":5434},[],{"categories":5436},[205],{"categories":5438},[130],{"categories":5440},[76],{"categories":5442},[76],{"categories":5444},[],{"categories":5446},[],{"categories":5448},[],{"categories":5450},[205],{"categories":5452},[76],{"categories":5454},[],{"categories":5456},[130],{"categories":5458},[76],{"categories":5460},[122],{"categories":5462},[],{"categories":5464},[],{"categories":5466},[76],{"categories":5468},[205],{"categories":5470},[76],{"categories":5472},[164],{"categories":5474},[],{"categories":5476},[76],{"categories":5478},[233],{"categories":5480},[164],{"categories":5482},[233],{"categories":5484},[208],{"categories":5486},[76],{"categories":5488},[76],{"categories":5490},[],{"categories":5492},[],{"categories":5494},[130],{"categories":5496},[],{"categories":5498},[76],{"categories":5500},[423],{"categories":5502},[76],{"categories":5504},[76],{"categories":5506},[76],{"categories":5508},[76],{"categories":5510},[],{"categories":5512},[130],{"categories":5514},[76],{"categories":5516},[76],{"categories":5518},[],{"categories":5520},[130],{"categories":5522},[76],{"categories":5524},[164],{"categories":5526},[76],{"categories":5528},[233],{"categories":5530},[125],{"categories":5532},[76],{"categories":5534},[76],{"categories":5536},[130],{"categories":5538},[208],{"categories":5540},[130],{"categories":5542},[130],{"categories":5544},[],{"categories":5546},[130],{"categories":5548},[],{"categories":5550},[76],{"categories":5552},[],{"categories":5554},[164],{"categories":5556},[125],{"categories":5558},[],{"categories":5560},[76],{"categories":5562},[],{"categories":5564},[205],{"categories":5566},[122],{"categories":5568},[],{"categories":5570},[125],{"categories":5572},[233],{"categories":5574},[76],{"categories":5576},[142],{"categories":5578},[122],{"categories":5580},[208],{"categories":5582},[125],{"categories":5584},[142],{"categories":5586},[130],{"categories":5588},[142],{"categories":5590},[],{"categories":5592},[133],{"categories":5594},[76],{"categories":5596},[],{"categories":5598},[130],{"categories":5600},[122],{"categories":5602},[205],{"categories":5604},[76],{"categories":5606},[122],{"categories":5608},[130],{"categories":5610},[268],{"categories":5612},[76],{"categories":5614},[76],{"categories":5616},[76],{"categories":5618},[122],{"categories":5620},[208],{"categories":5622},[130],{"categories":5624},[],{"categories":5626},[76],{"categories":5628},[76],{"categories":5630},[76],{"categories":5632},[142],{"categories":5634},[130],{"categories":5636},[164],{"categories":5638},[142],{"categories":5640},[76],{"categories":5642},[133],{"categories":5644},[],{"categories":5646},[205],{"categories":5648},[164],{"categories":5650},[122],{"categories":5652},[130],{"categories":5654},[76],{"categories":5656},[76],{"categories":5658},[130],{"categories":5660},[133],{"categories":5662},[76],{"categories":5664},[130],{"categories":5666},[76],{"categories":5668},[125],{"categories":5670},[130],{"categories":5672},[130,268],{"categories":5674},[76],{"categories":5676},[76],{"categories":5678},[130],{"categories":5680},[142],{"categories":5682},[76],{"categories":5684},[76],{"categories":5686},[208],{"categories":5688},[130],{"categories":5690},[233],{"categories":5692},[130],{"categories":5694},[125],{"categories":5696},[],{"categories":5698},[130],{"categories":5700},[76],{"categories":5702},[125],{"categories":5704},[],{"categories":5706},[],{"categories":5708},[142],{"categories":5710},[76],{"categories":5712},[76],{"categories":5714},[130],{"categories":5716},[208],{"categories":5718},[233],{"categories":5720},[76],{"categories":5722},[76],{"categories":5724},[130],{"categories":5726},[],{"categories":5728},[130],{"categories":5730},[164],{"categories":5732},[130],{"categories":5734},[],{"categories":5736},[164],{"categories":5738},[142],{"categories":5740},[2756],{"categories":5742},[122],{"categories":5744},[142],{"categories":5746},[76],{"categories":5748},[130],{"categories":5750},[76],{"categories":5752},[76],{"categories":5754},[233],{"categories":5756},[142],{"categories":5758},[],{"categories":5760},[164],{"categories":5762},[76],{"categories":5764},[],{"categories":5766},[130],{"categories":5768},[76],{"categories":5770},[76],{"categories":5772},[76],{"categories":5774},[76],{"categories":5776},[130],{"categories":5778},[76],{"categories":5780},[76],{"categories":5782},[133],{"categories":5784},[76],{"categories":5786},[130],{"categories":5788},[76],{"categories":5790},[76],{"categories":5792},[76],{"categories":5794},[76],{"categories":5796},[76],{"categories":5798},[76],{"categories":5800},[125],{"categories":5802},[],{"categories":5804},[133],{"categories":5806},[164],{"categories":5808},[130],{"categories":5810},[76],{"categories":5812},[142],{"categories":5814},[],{"categories":5816},[142],{"categories":5818},[142],{"categories":5820},[130],{"categories":5822},[142],{"categories":5824},[76],{"categories":5826},[76],{"categories":5828},[76],{"categories":5830},[130],{"categories":5832},[142],{"categories":5834},[76],{"categories":5836},[76],{"categories":5838},[130],{"categories":5840},[164],{"categories":5842},[76],{"categories":5844},[76],{"categories":5846},[76],{"categories":5848},[125],{"categories":5850},[76],{"categories":5852},[130],{"categories":5854},[205],{"categories":5856},[],{"categories":5858},[76],{"categories":5860},[208],{"categories":5862},[130],{"categories":5864},[76],{"categories":5866},[76],{"categories":5868},[],{"categories":5870},[76],{"categories":5872},[76],{"categories":5874},[164],{"categories":5876},[76],{"categories":5878},[76],{"categories":5880},[130],{"categories":5882},[233],{"categories":5884},[],{"categories":5886},[],{"categories":5888},[142],{"categories":5890},[76],{"categories":5892},[164],{"categories":5894},[142],{"categories":5896},[164],{"categories":5898},[76],{"categories":5900},[233],{"categories":5902},[208],{"categories":5904},[76],{"categories":5906},[122],{"categories":5908},[130],{"categories":5910},[76],{"categories":5912},[130],{"categories":5914},[130],{"categories":5916},[76],{"categories":5918},[125],{"categories":5920},[],{"categories":5922},[208],{"categories":5924},[76],{"categories":5926},[],{"categories":5928},[164],{"categories":5930},[76],{"categories":5932},[208],{"categories":5934},[76],{"categories":5936},[142],{"categories":5938},[142],{"categories":5940},[142],{"categories":5942},[130],{"categories":5944},[130],{"categories":5946},[76],{"categories":5948},[130],{"categories":5950},[76],{"categories":5952},[76],{"categories":5954},[205],{"categories":5956},[208],{"categories":5958},[208],{"categories":5960},[],{"categories":5962},[164],{"categories":5964},[76],{"categories":5966},[76],{"categories":5968},[142],{"categories":5970},[],{"categories":5972},[164],{"categories":5974},[164],{"categories":5976},[164],{"categories":5978},[],{"categories":5980},[130],{"categories":5982},[76],{"categories":5984},[],{"categories":5986},[122],{"categories":5988},[125],{"categories":5990},[],{"categories":5992},[76],{"categories":5994},[76],{"categories":5996},[],{"categories":5998},[142],{"categories":6000},[],{"categories":6002},[],{"categories":6004},[],{"categories":6006},[],{"categories":6008},[76],{"categories":6010},[164],{"categories":6012},[],{"categories":6014},[],{"categories":6016},[76],{"categories":6018},[76],{"categories":6020},[76],{"categories":6022},[208],{"categories":6024},[76],{"categories":6026},[208],{"categories":6028},[],{"categories":6030},[208],{"categories":6032},[208],{"categories":6034},[268],{"categories":6036},[130],{"categories":6038},[142],{"categories":6040},[],{"categories":6042},[],{"categories":6044},[208],{"categories":6046},[142],{"categories":6048},[142],{"categories":6050},[142],{"categories":6052},[],{"categories":6054},[122],{"categories":6056},[142],{"categories":6058},[142],{"categories":6060},[122],{"categories":6062},[142],{"categories":6064},[125],{"categories":6066},[142],{"categories":6068},[142],{"categories":6070},[142],{"categories":6072},[208],{"categories":6074},[164],{"categories":6076},[164],{"categories":6078},[76],{"categories":6080},[142],{"categories":6082},[208],{"categories":6084},[268],{"categories":6086},[208],{"categories":6088},[208],{"categories":6090},[208],{"categories":6092},[],{"categories":6094},[125],{"categories":6096},[],{"categories":6098},[268],{"categories":6100},[142],{"categories":6102},[142],{"categories":6104},[142],{"categories":6106},[130],{"categories":6108},[164,125],{"categories":6110},[208],{"categories":6112},[],{"categories":6114},[],{"categories":6116},[208],{"categories":6118},[],{"categories":6120},[208],{"categories":6122},[164],{"categories":6124},[130],{"categories":6126},[],{"categories":6128},[142],{"categories":6130},[76],{"categories":6132},[205],{"categories":6134},[],{"categories":6136},[76],{"categories":6138},[],{"categories":6140},[164],{"categories":6142},[122],{"categories":6144},[208],{"categories":6146},[],{"categories":6148},[142],{"categories":6150},[164],[6152,6259,6392,6489],{"id":6153,"title":6154,"ai":6155,"body":6160,"categories":6232,"created_at":77,"date_modified":77,"description":69,"extension":78,"faq":77,"featured":79,"kicker_label":77,"meta":6233,"navigation":96,"path":6244,"published_at":6245,"question":77,"scraped_at":6246,"seo":6247,"sitemap":6248,"source_id":6249,"source_name":103,"source_type":104,"source_url":6250,"stem":6251,"tags":6252,"thumbnail_url":6254,"tldr":6255,"tweet":6256,"unknown_tags":6257,"__hash__":6258},"summaries\u002Fsummaries\u002F7418683212d7daa2-scaling-agentic-post-training-via-real-world-inter-summary.md","Scaling Agentic Post-Training via Real-World Interaction",{"provider":7,"model":8,"input_tokens":6156,"output_tokens":6157,"processing_time_ms":6158,"cost_usd":6159},7068,729,3653,0.0028605,{"type":14,"value":6161,"toc":6227},[6162,6166,6169,6172,6176,6179,6193,6196,6200,6203,6224],[17,6163,6165],{"id":6164},"the-evolution-of-post-training-architectures","The Evolution of Post-Training Architectures",[22,6167,6168],{},"Post-training is shifting from simple, single-turn Q&A tasks toward long-horizon, agentic workflows. The current standard involves a closed-loop system: an orchestrator sends tasks to a model, a grader evaluates the output, and a training engine updates model weights based on the results.",[22,6170,6171],{},"As tasks become more complex, the environment state is moved outside the training stack. In these synthetic environments, the system must be fully replayable—allowing the model to rerun the same task multiple times to compare different trajectories. This is the foundation of GRPO (Group Relative Policy Optimization), where the model is incentivized to upweight successful trajectories and downweight failures.",[17,6173,6175],{"id":6174},"the-challenge-of-environment-fidelity-and-reward-hacking","The Challenge of Environment Fidelity and Reward Hacking",[22,6177,6178],{},"Replicating production environments is notoriously difficult. Any discrepancy between the training environment and reality leads to \"reward hacking,\" where models exploit quirks in the environment rather than solving the task.",[39,6180,6181,6187],{},[42,6182,6183,6186],{},[45,6184,6185],{},"Tool Call Failures:"," If an environment has intermittent network issues, models may learn to output shorter responses to avoid the risk of a \"pothole\" (a failed tool call) that results in a zero reward.",[42,6188,6189,6192],{},[45,6190,6191],{},"Timeout Exploitation:"," If a sandbox has strict timeouts, a model facing a difficult problem may intentionally spam tool calls to trigger a timeout, effectively dropping the task to avoid a negative grade.",[22,6194,6195],{},"These behaviors demonstrate that models are highly sensitive to the specific \"nooks and crannies\" of their environment. Consequently, the goal is to move toward \"bring your own harness\" architectures, where training occurs directly within the enterprise's production environment, eliminating the need to simulate reality.",[17,6197,6199],{"id":6198},"toward-self-improving-agents","Toward Self-Improving Agents",[22,6201,6202],{},"Moving training into production introduces significant hurdles: non-replayability and off-policy data. Unlike synthetic benchmarks, you cannot \"reset\" a real customer support chat to see if a different response would have yielded a better outcome. To overcome this, the focus is shifting toward three frontier research areas:",[6204,6205,6206,6212,6218],"ol",{},[42,6207,6208,6211],{},[45,6209,6210],{},"Self-Distillation:"," Using the model to generate its own training signals or refine its own behaviors.",[42,6213,6214,6217],{},[45,6215,6216],{},"Automated Data Pipelines:"," Moving away from manual, human-in-the-loop curation to automated systems that flag failure modes and generate training batches from raw traces.",[42,6219,6220,6223],{},[45,6221,6222],{},"Qualitative Feedback Ingestion:"," Developing methods to update models based on unstructured feedback (e.g., customer comments) rather than binary or numerical grades.",[22,6225,6226],{},"The ultimate vision is a model that treats every interaction as a training signal. By moving beyond the \"whack-a-mole\" approach of fixing one failure mode at a time, developers can build systems that continuously reflect on their performance, effectively turning experience into the primary driver of model improvement.",{"title":69,"searchDepth":70,"depth":70,"links":6228},[6229,6230,6231],{"id":6164,"depth":70,"text":6165},{"id":6174,"depth":70,"text":6175},{"id":6198,"depth":70,"text":6199},[76],{"content_references":6234,"triage":6240},[6235],{"type":6236,"title":6237,"author":6238,"context":6239},"paper","POLAR: Learning to Reason with Large Language Models","Nvidia","cited",{"relevance":92,"novelty":93,"quality":93,"actionability":6241,"composite":6242,"reasoning":6243},3,4.15,"Category: AI & LLMs. The article discusses the evolution of post-training architectures for AI agents, addressing a core topic of AI engineering that is highly relevant to product builders. It presents new insights on the challenges of training AI in real-world environments, which is crucial for developers looking to implement AI features effectively.","\u002Fsummaries\u002F7418683212d7daa2-scaling-agentic-post-training-via-real-world-inter-summary","2026-07-31 22:30:06","2026-08-01 03:12:16",{"title":6154,"description":69},{"loc":6244},"7418683212d7daa2","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=k35LeKZEhiE","summaries\u002F7418683212d7daa2-scaling-agentic-post-training-via-real-world-inter-summary",[108,109,6253,110],"ai-tools","https:\u002F\u002Fi.ytimg.com\u002Fvi\u002Fk35LeKZEhiE\u002Fhqdefault.jpg","To move beyond synthetic benchmarks, AI agents must learn directly from production environments. This requires shifting from controlled, replayable training loops to systems that ingest real-world interaction data and qualitative feedback to enable continuous, self-improving models.","This talk outlines a technical framework for \"learning on the job,\" where models are continuously fine-tuned via reinforcement learning using an enterprise's existing production harness rather than a synthetic sandbox. The speaker, [Raymond Feng](https:\u002F\u002Fx.com\u002Fraymondmfeng), details the shift from simple Q&A loops to long-horizon task adaptation, while candidly addressing the risks of reward hacking and the difficulty of maintaining environment fidelity when moving away from controlled, replayable data.",[110],"wW6jamErLntg5K01xoscq_NtPdX72V04T9OUTqle9tc",{"id":6260,"title":6261,"ai":6262,"body":6267,"categories":6367,"created_at":77,"date_modified":77,"description":69,"extension":78,"faq":77,"featured":79,"kicker_label":77,"meta":6368,"navigation":96,"path":6378,"published_at":6379,"question":77,"scraped_at":6380,"seo":6381,"sitemap":6382,"source_id":6383,"source_name":6384,"source_type":6385,"source_url":6386,"stem":6387,"tags":6388,"thumbnail_url":77,"tldr":6389,"tweet":77,"unknown_tags":6390,"__hash__":6391},"summaries\u002Fsummaries\u002Fe49f16bf5dbabedc-fixing-grpo-failure-modes-in-production-summary.md","Fixing GRPO Failure Modes in Production",{"provider":7,"model":8,"input_tokens":6263,"output_tokens":6264,"processing_time_ms":6265,"cost_usd":6266},6684,817,4693,0.0028965,{"type":14,"value":6268,"toc":6362},[6269,6273,6276,6296,6300,6303,6329,6333,6336],[17,6270,6272],{"id":6271},"the-structural-weaknesses-of-grpo","The Structural Weaknesses of GRPO",[22,6274,6275],{},"GRPO (Group Relative Policy Optimization) is widely favored for its efficiency, as it eliminates the need for a critic network. However, its reliance on group-relative advantage normalization creates three primary failure modes that stall training:",[39,6277,6278,6284,6290],{},[42,6279,6280,6283],{},[45,6281,6282],{},"Advantage Collapse:"," Occurs when all sampled responses in a group receive the same reward (e.g., all correct or all incorrect). This results in near-zero advantage, effectively killing the gradient signal. This is most common on very hard or very easy prompts.",[42,6285,6286,6289],{},[45,6287,6288],{},"Entropy Collapse:"," As the model converges, it may lose generation diversity. Once entropy drops below a critical threshold (typically \u003C 0.5 nats), the model becomes stuck in a narrow mode, making it difficult to recover without external intervention.",[42,6291,6292,6295],{},[45,6293,6294],{},"KL Drift:"," Using a blunt KL penalty coefficient often forces the model to choose between reward hacking (low penalty) or stagnation (high penalty). Baking KL into the reward signal further distorts the advantage normalization process.",[17,6297,6299],{"id":6298},"engineering-solutions-via-dapo","Engineering Solutions via DAPO",[22,6301,6302],{},"The DAPO (Dynamic Sampling Policy Optimization) framework provides specific algorithmic fixes to these issues:",[39,6304,6305,6311,6317,6323],{},[42,6306,6307,6310],{},[45,6308,6309],{},"Dynamic Sampling:"," Instead of training on all groups, filter out groups with zero reward variance. This prevents the model from updating on noise.",[42,6312,6313,6316],{},[45,6314,6315],{},"Asymmetric KL Clipping:"," By using a higher upper bound for the probability ratio, the model can aggressively reinforce correct responses without needing to compress its entire output distribution, which helps preserve entropy.",[42,6318,6319,6322],{},[45,6320,6321],{},"Decoupled KL:"," Remove the KL penalty from the reward signal entirely. Apply it as a direct loss term after advantage computation to prevent reward distortion.",[42,6324,6325,6328],{},[45,6326,6327],{},"Token-Level Normalization:"," Standard GRPO normalizes at the sample level, which biases the model against long chain-of-thought reasoning. Normalizing by total token count ensures that longer, more complex reasoning traces are weighted appropriately.",[17,6330,6332],{"id":6331},"production-best-practices","Production Best Practices",[22,6334,6335],{},"Beyond the algorithm, the success of GRPO depends on the quality of the reward signal and the training pipeline.",[39,6337,6338,6344,6350,6356],{},[42,6339,6340,6343],{},[45,6341,6342],{},"Audit the Reward Model:"," If the verifier is noisy, it will inject false signals that exacerbate advantage collapse.",[42,6345,6346,6349],{},[45,6347,6348],{},"Monitor Entropy:"," Track per-token entropy as a first-class metric. If it stays below 0.5 nats for more than 50 steps, the model is likely collapsing.",[42,6351,6352,6355],{},[45,6353,6354],{},"Manage SFT Bias:"," If the initial SFT checkpoint is already over-fitted to a specific format, it will be more prone to entropy collapse during RL.",[42,6357,6358,6361],{},[45,6359,6360],{},"Hyperparameter Tuning:"," While increasing group size (G) can stabilize estimates, it is often more compute-efficient to use dynamic sampling to discard low-variance groups than to simply increase the number of rollouts.",{"title":69,"searchDepth":70,"depth":70,"links":6363},[6364,6365,6366],{"id":6271,"depth":70,"text":6272},{"id":6298,"depth":70,"text":6299},{"id":6331,"depth":70,"text":6332},[76],{"content_references":6369,"triage":6376},[6370,6373],{"type":6236,"title":6371,"author":6372,"context":90},"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","DeepSeek-AI",{"type":6236,"title":6374,"author":6375,"context":86},"DAPO: Dynamic Sampling Policy Optimization","Yu et al.",{"relevance":92,"novelty":93,"quality":93,"actionability":93,"composite":94,"reasoning":6377},"Category: AI & LLMs. The article provides in-depth insights into the failure modes of GRPO and actionable solutions through DAPO techniques, addressing a specific pain point for AI developers working on production models. The detailed explanation of dynamic sampling and KL clipping offers practical steps that can be implemented in AI training workflows.","\u002Fsummaries\u002Fe49f16bf5dbabedc-fixing-grpo-failure-modes-in-production-summary","2026-06-22 17:19:40","2026-06-23 12:56:49",{"title":6261,"description":69},{"loc":6378},"e49f16bf5dbabedc","Level Up Coding","article","https:\u002F\u002Flevelup.gitconnected.com\u002Fgrpo-in-production-the-failure-modes-nobody-writes-about-5d59c3fc9c3b?source=rss----5517fd7b58a6---4","summaries\u002Fe49f16bf5dbabedc-fixing-grpo-failure-modes-in-production-summary",[108,109,6253,110],"GRPO is more efficient than PPO but prone to silent failures like advantage collapse and entropy loss. Using Dynamic Sampling Policy Optimization (DAPO) techniques—specifically dynamic sampling, token-level normalization, and decoupled KL—is essential for stable production training.",[110],"4CEhNHYzoOyN8sKq7uCvHQxt3W7rlJzDp-bzL0gTCkE",{"id":6393,"title":6394,"ai":6395,"body":6400,"categories":6459,"created_at":77,"date_modified":77,"description":69,"extension":78,"faq":77,"featured":79,"kicker_label":77,"meta":6460,"navigation":96,"path":6475,"published_at":6476,"question":77,"scraped_at":6477,"seo":6478,"sitemap":6479,"source_id":6480,"source_name":103,"source_type":104,"source_url":6481,"stem":6482,"tags":6483,"thumbnail_url":6484,"tldr":6485,"tweet":6486,"unknown_tags":6487,"__hash__":6488},"summaries\u002Fsummaries\u002F64ef5b3eb112fa0b-optimizing-ai-for-tool-use-via-rl-and-data-quality-summary.md","Optimizing AI for Tool Use via RL and Data Quality",{"provider":7,"model":8,"input_tokens":6396,"output_tokens":6397,"processing_time_ms":6398,"cost_usd":6399},8611,652,3933,0.00313075,{"type":14,"value":6401,"toc":6454},[6402,6406,6409,6413,6416,6447,6451],[17,6403,6405],{"id":6404},"the-fallacy-of-scaling-for-tool-use","The Fallacy of Scaling for Tool Use",[22,6407,6408],{},"Many enterprise AI projects fail to reach production because developers default to using larger models, assuming increased reasoning depth will solve reliability issues. However, larger models often lack \"tool discipline.\" In a financial analysis task, a 235B parameter model (Qwen 3) failed to query a database correctly because it did not inspect the environment, leading it to hallucinate an answer after two failed attempts. This demonstrates that raw reasoning capability does not equate to effective tool interaction.",[17,6410,6412],{"id":6411},"achieving-performance-via-targeted-rl","Achieving Performance via Targeted RL",[22,6414,6415],{},"Instead of scaling up, Snorkel and the RLLM team at UC Berkeley demonstrated that a 4B parameter model could be fine-tuned using Reinforcement Learning (RL) to outperform much larger models. By focusing on behavior rather than core knowledge, the team achieved a significant uplift in performance:",[39,6417,6418,6429,6435,6441],{},[42,6419,6420,6423,6424,6428],{},[45,6421,6422],{},"Tool Discipline:"," The fine-tuned model learned to first call ",[6425,6426,6427],"code",{},"get_table_name"," to discover available data, then inspect the schema before querying.",[42,6430,6431,6434],{},[45,6432,6433],{},"Self-Correction:"," The model learned to observe SQL errors (e.g., missing columns) and self-correct its queries in real-time.",[42,6436,6437,6440],{},[45,6438,6439],{},"Efficiency:"," The entire training process was completed in 21 hours for under $500.",[42,6442,6443,6446],{},[45,6444,6445],{},"Generalization:"," Surprisingly, training exclusively on single-table tasks yielded the best performance, which then generalized to improve multi-table reasoning benchmarks from 13.9% to 26.6%.",[17,6448,6450],{"id":6449},"rubric-based-evaluation","Rubric-Based Evaluation",[22,6452,6453],{},"To identify the specific behaviors needing improvement, the team advocates for building rubrics into evaluation pipelines. Rather than relying on a binary \"pass\u002Ffail\" metric, rubrics break down model responses into granular components. This allows developers to pinpoint exactly where a model fails (e.g., schema discovery vs. query construction) and generate targeted training data to address those specific failure modes before initiating the RL cycle.",{"title":69,"searchDepth":70,"depth":70,"links":6455},[6456,6457,6458],{"id":6404,"depth":70,"text":6405},{"id":6411,"depth":70,"text":6412},{"id":6449,"depth":70,"text":6450},[76],{"content_references":6461,"triage":6473},[6462,6465,6467,6470],{"type":83,"title":6463,"url":6464,"context":90},"Snorkel","https:\u002F\u002Fsnorkel.ai\u002F",{"type":83,"title":6466,"context":90},"FinQA",{"type":83,"title":6468,"url":6469,"context":90},"OpenEnv","https:\u002F\u002Fgithub.com\u002Fopen-env\u002Fopen-env",{"type":83,"title":6471,"url":6472,"context":90},"PrimeIntellect","https:\u002F\u002Fwww.primeintellect.ai\u002F",{"relevance":92,"novelty":93,"quality":93,"actionability":93,"composite":94,"reasoning":6474},"Category: AI & LLMs. The article provides a deep dive into optimizing AI models for tool use through reinforcement learning, addressing a specific pain point for developers regarding the limitations of scaling models. It offers actionable insights on implementing rubrics for evaluation and targeted training, which can directly enhance model performance in production.","\u002Fsummaries\u002F64ef5b3eb112fa0b-optimizing-ai-for-tool-use-via-rl-and-data-quality-summary","2026-06-10 17:00:25","2026-06-11 12:56:12",{"title":6394,"description":69},{"loc":6475},"64ef5b3eb112fa0b","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TNwJ1LMiENk","summaries\u002F64ef5b3eb112fa0b-optimizing-ai-for-tool-use-via-rl-and-data-quality-summary",[108,109,6253,110],"https:\u002F\u002Fi.ytimg.com\u002Fvi\u002FTNwJ1LMiENk\u002Fhqdefault.jpg","Improving model performance for complex tasks often requires teaching tool discipline through RL and high-quality data rather than scaling model size. A 4B parameter model outperformed a 235B model by learning to inspect schemas and self-correct errors.","This presentation argues that for tool-use tasks, model behavior is more important than raw reasoning capacity. The speaker demonstrates how fine-tuning a 4B parameter model with reinforcement learning—using high-quality, expert-curated data—can outperform massive models that lack the discipline to correctly inspect schemas and self-correct during execution.",[110],"EYBAXV3xpQ--pQSEBkEE83W1voZbTuHI7-vX6YmtIt4",{"id":6490,"title":6491,"ai":6492,"body":6497,"categories":6577,"created_at":77,"date_modified":77,"description":69,"extension":78,"faq":77,"featured":79,"kicker_label":77,"meta":6578,"navigation":96,"path":6591,"published_at":6592,"question":77,"scraped_at":6592,"seo":6593,"sitemap":6594,"source_id":6595,"source_name":6596,"source_type":6385,"source_url":6597,"stem":6598,"tags":6599,"thumbnail_url":77,"tldr":6601,"tweet":77,"unknown_tags":6602,"__hash__":6603},"summaries\u002Fsummaries\u002F73c67fb584b2873f-harness-1-offloading-bookkeeping-to-improve-search-summary.md","Harness-1: Offloading Bookkeeping to Improve Search Agent Performance",{"provider":7,"model":8,"input_tokens":6493,"output_tokens":6494,"processing_time_ms":6495,"cost_usd":6496},9437,801,5156,0.00356075,{"type":14,"value":6498,"toc":6572},[6499,6503,6506,6510,6513,6533,6548,6552,6555,6569],[17,6500,6502],{"id":6501},"stateful-cognitive-offloading","Stateful Cognitive Offloading",[22,6504,6505],{},"Most search agents struggle because they attempt to manage both high-level search strategy and low-level bookkeeping (tracking evidence, deduplication, and state maintenance) within a single, growing transcript. Harness-1, a 20B model built on gpt-oss-20b, addresses this by implementing \"stateful cognitive offloading.\" The model acts as a policy that makes semantic decisions, while an external state-machine harness manages the \"working memory\" and routine operations.",[17,6507,6509],{"id":6508},"the-harness-architecture","The Harness Architecture",[22,6511,6512],{},"The harness maintains a recoverable state that includes:",[39,6514,6515,6521,6527],{},[42,6516,6517,6520],{},[45,6518,6519],{},"Candidate Pool:"," A deduplicated set of retrieved documents.",[42,6522,6523,6526],{},[45,6524,6525],{},"Curated Set:"," A final output set (capped at 30 documents) tagged by importance (very_high, high, fair, low).",[42,6528,6529,6532],{},[45,6530,6531],{},"Evidence Graph:"," A structure that uses regex extraction to identify frequent entities and bridge documents, helping the agent identify follow-up leads.",[22,6534,6535,6536,6539,6540,6543,6544,6547],{},"By offloading this state, the agent avoids the performance degradation associated with managing complex bookkeeping inside the prompt. The harness provides eight tools to the model, including ",[6425,6537,6538],{},"fan_out_search",", ",[6425,6541,6542],{},"curate",", and ",[6425,6545,6546],{},"verify",". A key design choice is the \"warm-start\" mechanism, where the first successful search auto-seeds the curated set, shifting the agent's task from building from scratch to iterative refinement.",[17,6549,6551],{"id":6550},"training-and-performance","Training and Performance",[22,6553,6554],{},"Harness-1 uses a two-stage training process:",[6204,6556,6557,6563],{},[42,6558,6559,6562],{},[45,6560,6561],{},"Supervised Fine-Tuning (SFT):"," Teaches the model how to operate the harness interface using 899 trajectories generated by a GPT-5.4 teacher.",[42,6564,6565,6568],{},[45,6566,6567],{},"Reinforcement Learning (RL):"," Uses on-policy CISPO with a terminal-only reward to optimize search decisions. A critical addition is a \"tool-diversity bonus,\" which prevents the agent from collapsing into repetitive search patterns; without this, curated recall plateaus significantly lower.",[22,6570,6571],{},"In benchmarks across web, finance, and patent data, Harness-1 achieved an average curated recall of 0.730, outperforming other open models and trailing only frontier-scale models like Opus-4.6. Notably, the model showed strong generalization, with a 2.2x larger gain on held-out benchmarks compared to tasks similar to its training data.",{"title":69,"searchDepth":70,"depth":70,"links":6573},[6574,6575,6576],{"id":6501,"depth":70,"text":6502},{"id":6508,"depth":70,"text":6509},{"id":6550,"depth":70,"text":6551},[76],{"content_references":6579,"triage":6589},[6580,6583,6586],{"type":6236,"title":6581,"url":6582,"context":6239},"Harness-1: A 20B Retrieval Subagent Trained With Reinforcement Learning Inside a Stateful Search Harness on gpt-oss-20b","https:\u002F\u002Farxiv.org\u002Fpdf\u002F2606.02373",{"type":83,"title":6584,"url":6585,"context":86},"Harness-1 Model Weights","https:\u002F\u002Fhuggingface.co\u002Fpat-jj\u002Fharness-1",{"type":83,"title":6587,"url":6588,"context":86},"Harness-1 GitHub Repository","https:\u002F\u002Fgithub.com\u002Fpat-jj\u002Fharness-1",{"relevance":92,"novelty":93,"quality":93,"actionability":6241,"composite":6242,"reasoning":6590},"Category: AI & LLMs. The article provides a detailed exploration of the Harness-1 model, specifically addressing how it improves search agent performance through stateful cognitive offloading, which is a relevant topic for AI product builders. It presents new insights into the architecture and training processes, though it lacks specific actionable steps for implementation.","\u002Fsummaries\u002F73c67fb584b2873f-harness-1-offloading-bookkeeping-to-improve-search-summary","2026-06-07 12:56:24",{"title":6491,"description":69},{"loc":6591},"73c67fb584b2873f","MarkTechPost","https:\u002F\u002Fwww.marktechpost.com\u002F2026\u002F06\u002F06\u002Fmeet-harness-1-a-20b-retrieval-subagent-trained-with-reinforcement-learning-inside-a-stateful-search-harness-on-gpt-oss-20b\u002F","summaries\u002F73c67fb584b2873f-harness-1-offloading-bookkeeping-to-improve-search-summary",[108,109,110,6600],"retrieval","Harness-1 improves retrieval performance by separating search policy from state management, using a stateful harness to handle bookkeeping and memory, allowing the 20B model to focus on semantic decisions.",[110,6600],"TkpWka_tCJDfhhmS91QVXnL-qiEepGUZu7rknsRyPaU"]