[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"summary-788e0faff32168e3-programming-stacks-map-to-llm-agents-for-smarter-b-summary":3,"summaries-facets-categories":71,"summary-related-788e0faff32168e3-programming-stacks-map-to-llm-agents-for-smarter-b-summary":3640},{"id":4,"title":5,"ai":6,"body":13,"categories":41,"created_at":43,"date_modified":43,"description":36,"extension":44,"faq":43,"featured":45,"kicker_label":43,"meta":46,"navigation":53,"path":54,"published_at":55,"question":43,"scraped_at":56,"seo":57,"sitemap":58,"source_id":59,"source_name":60,"source_type":61,"source_url":62,"stem":63,"tags":64,"thumbnail_url":43,"tldr":68,"tweet":43,"unknown_tags":69,"__hash__":70},"summaries\u002Fsummaries\u002F788e0faff32168e3-programming-stacks-map-to-llm-agents-for-smarter-b-summary.md","Programming Stacks Map to LLM Agents for Smarter Builds",{"provider":7,"model":8,"input_tokens":9,"output_tokens":10,"processing_time_ms":11,"cost_usd":12},"openrouter","x-ai\u002Fgrok-4.1-fast",3863,1003,11090,0.0012516,{"type":14,"value":15,"toc":35},"minimark",[16,21,25,28,32],[17,18,20],"h2",{"id":19},"analogy-equips-you-to-build-maintainable-agentic-systems","Analogy Equips You to Build Maintainable Agentic Systems",[22,23,24],"p",{},"Traditional software engineering maps closely to LLM-based agentic systems, revealing why current stacks often fail at scale. Treat the LLM itself (e.g., Qwen, Llama, Claude) as your core programming language—it handles execution of instructions. MCP servers (like libraries such as NumPy or Textual) provide reusable capabilities without bloating the base model. Individual skills act as discrete programs, composed atop these for specific tasks. Context windows function like RAM: fast but volatile and size-limited, forcing careful state management. RAG serves as disk\u002Fdatabase: persistent, slower retrieval for grounding without overwhelming short-term memory.",[22,26,27],{},"This mapping isn't perfect—LLMs introduce non-determinism and hallucination risks absent in deterministic languages—but it holds enough to guide architecture. It breaks where LLMs lack compile-time checks or true modularity, yet applying software principles (e.g., minimize context bloat like RAM overuse, version MCPs like library deps) yields more reliable agents.",[17,29,31],{"id":30},"practical-implications-shift-your-agent-stack","Practical Implications Shift Your Agent Stack",[22,33,34],{},"Adopt this lens to escape ad-hoc prompting: design agents as layered software stacks. Start with a capable LLM 'language,' plug in specialized MCP 'libraries' for domain logic, author focused 'skills' as composable units, manage context like volatile memory (evict aggressively), and offload facts to RAG for persistence. Result: systems that scale like apps, not brittle prompt chains—easier to debug, version, and extend. Hands-on builders gain a mental model for production agents, prioritizing composition over raw model power.",{"title":36,"searchDepth":37,"depth":37,"links":38},"",2,[39,40],{"id":19,"depth":37,"text":20},{"id":30,"depth":37,"text":31},[42],"AI & LLMs",null,"md",false,{"content_references":47,"triage":48},[],{"relevance":49,"novelty":50,"quality":50,"actionability":50,"composite":51,"reasoning":52},5,4,4.35,"Category: AI & LLMs. The article provides a detailed analogy between traditional software engineering and LLM-based systems, addressing the audience's need for practical applications in building AI-powered products. It offers actionable insights on structuring agentic systems, which is directly relevant to developers and founders looking to implement AI effectively.",true,"\u002Fsummaries\u002F788e0faff32168e3-programming-stacks-map-to-llm-agents-for-smarter-b-summary","2026-04-29 01:52:13","2026-05-03 17:00:53",{"title":5,"description":36},{"loc":54},"788e0faff32168e3","Generative AI","article","https:\u002F\u002Fgenerativeai.pub\u002Fthe-hidden-analogy-between-programming-languages-and-llms-that-will-change-how-you-build-agentic-a344fa26dc09?source=rss----440100e76000---4","summaries\u002F788e0faff32168e3-programming-stacks-map-to-llm-agents-for-smarter-b-summary",[65,66,67],"llm","agents","software-engineering","Map LLMs to programming languages, MCP servers to libraries, skills to programs, context windows to RAM, and RAG to disk—use this analogy to compose and maintain agentic systems like traditional software.",[67],"_g6isC4Txgg9eOHjkCG4cbpzGLv4o7EVwKaZv6zkg2o",[72,75,78,80,83,86,88,90,92,94,96,98,101,103,105,107,109,111,113,115,117,119,122,125,127,129,132,134,136,139,141,143,145,147,149,151,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223,225,227,229,231,233,235,237,239,241,243,245,247,249,251,253,255,257,259,261,263,265,267,269,271,273,275,277,279,281,283,285,287,289,291,293,295,297,299,301,303,305,307,309,311,313,315,317,319,321,323,325,327,329,331,333,335,337,339,341,343,345,347,349,351,353,355,357,359,361,363,365,367,369,371,373,375,377,379,381,383,385,387,389,391,394,396,398,400,402,404,406,408,410,412,414,416,418,420,422,424,426,428,430,432,434,436,438,440,442,444,446,448,450,452,454,456,458,460,462,464,466,468,470,472,474,476,478,480,482,484,486,488,490,492,494,496,498,500,502,504,506,508,510,512,514,516,518,520,522,524,526,528,530,532,534,536,538,540,542,544,546,548,550,552,554,556,558,560,562,564,566,568,570,572,574,576,578,580,582,584,586,588,590,592,594,596,598,600,602,604,606,608,610,612,614,616,618,620,622,624,626,628,630,632,634,636,638,640,642,644,646,648,650,652,654,656,658,660,662,664,666,668,670,672,674,676,678,680,682,684,686,688,690,692,694,696,698,700,702,704,706,708,710,712,714,716,718,720,722,724,726,728,730,732,734,736,738,740,742,744,746,748,750,752,754,756,758,760,762,764,766,768,770,772,774,776,778,780,782,784,786,788,790,792,794,796,798,800,802,804,806,808,810,812,814,816,818,820,822,824,826,828,830,832,834,836,838,840,842,844,846,848,850,852,854,856,858,860,862,864,866,868,870,872,874,876,878,880,882,884,886,888,890,892,894,896,898,900,902,904,906,908,910,912,914,916,918,920,922,924,926,928,930,932,934,936,938,940,942,944,946,948,950,952,954,956,958,960,962,964,966,968,970,972,974,976,978,980,982,984,986,988,990,992,994,996,998,1000,1002,1004,1006,1008,1010,1012,1014,1016,1018,1020,1022,1024,1026,1028,1030,1032,1034,1036,1038,1040,1042,1044,1046,1048,1050,1052,1054,1056,1058,1060,1062,1064,1066,1068,1070,1072,1074,1076,1078,1080,1082,1084,1086,1088,1090,1092,1094,1096,1098,1100,1102,1104,1106,1108,1110,1112,1114,1116,1118,1120,1122,1124,1126,1128,1130,1132,1134,1136,1138,1140,1142,1144,1146,1148,1150,1152,1154,1156,1158,1160,1162,1164,1166,1168,1170,1172,1174,1176,1178,1180,1182,1184,1186,1188,1190,1192,1194,1196,1198,1200,1202,1204,1206,1208,1210,1212,1214,1216,1218,1220,1222,1224,1226,1228,1230,1232,1234,1236,1238,1240,1242,1244,1246,1248,1250,1252,1254,1256,1258,1260,1262,1264,1266,1268,1270,1272,1274,1276,1278,1280,1282,1284,1286,1288,1290,1292,1294,1296,1298,1300,1302,1304,1306,1308,1310,1312,1314,1316,1318,1320,1322,1324,1326,1328,1330,1332,1334,1336,1338,1340,1342,1344,1346,1348,1350,1352,1354,1356,1358,1360,1362,1364,1366,1368,1370,1372,1374,1376,1378,1380,1382,1384,1386,1388,1390,1392,1394,1396,1398,1400,1402,1404,1406,1408,1410,1412,1414,1416,1418,1420,1422,1424,1426,1428,1430,1432,1434,1436,1438,1440,1442,1444,1446,1448,1450,1452,1454,1456,1458,1460,1462,1464,1466,1468,1470,1472,1474,1476,1478,1480,1482,1484,1486,1488,1490,1492,1494,1496,1498,1500,1502,1504,1506,1508,1510,1512,1514,1516,1518,1520,1522,1524,1526,1528,1530,1532,1534,1536,1538,1540,1542,1544,1546,1548,1550,1552,1554,1556,1558,1560,1562,1564,1566,1568,1570,1572,1574,1576,1578,1580,1582,1584,1586,1588,1590,1592,1594,1596,1598,1600,1602,1604,1606,1608,1610,1612,1614,1616,1618,1620,1622,1624,1626,1628,1630,1632,1634,1636,1638,1640,1642,1644,1646,1648,1650,1652,1654,1656,1658,1660,1662,1664,1666,1668,1670,1672,1674,1676,1678,1680,1682,1684,1686,1688,1690,1692,1694,1696,1698,1700,1702,1704,1706,1708,1710,1712,1714,1716,1718,1720,1722,1724,1726,1728,1730,1732,1734,1736,1738,1740,1742,1744,1746,1748,1750,1752,1754,1756,1758,1760,1762,1764,1766,1768,1770,1772,1774,1776,1778,1780,1782,1784,1786,1788,1790,1792,1794,1796,1798,1800,1802,1804,1806,1808,1810,1812,1814,1816,1818,1820,1822,1824,1826,1828,1830,1832,1834,1836,1838,1840,1842,1844,1846,1848,1850,1852,1854,1856,1858,1860,1862,1864,1866,1868,1870,1872,1874,1876,1878,1880,1882,1884,1886,1888,1890,1892,1894,1896,1898,1900,1902,1904,1906,1908,1910,1912,1914,1916,1918,1920,1922,1924,1926,1928,1930,1932,1934,1936,1938,1940,1942,1944,1946,1948,1950,1952,1954,1956,1958,1960,1962,1964,1966,1968,1970,1972,1974,1976,1978,1980,1982,1984,1986,1988,1990,1992,1994,1996,1998,2000,2002,2004,2006,2008,2010,2012,2014,2016,2018,2020,2022,2024,2026,2028,2030,2032,2034,2036,2038,2040,2042,2044,2046,2048,2050,2052,2054,2056,2058,2060,2062,2064,2066,2068,2070,2072,2074,2076,2078,2080,2082,2084,2086,2088,2090,2092,2094,2096,2098,2100,2102,2104,2106,2108,2110,2112,2114,2116,2118,2120,2122,2124,2126,2128,2130,2132,2134,2136,2138,2140,2142,2144,2146,2148,2150,2152,2154,2156,2158,2160,2162,2164,2166,2168,2170,2172,2174,2176,2178,2180,2182,2184,2186,2188,2190,2192,2194,2196,2198,2200,2202,2204,2206,2208,2210,2212,2214,2216,2218,2220,2222,2224,2226,2228,2230,2232,2234,2236,2238,2240,2242,2244,2246,2248,2250,2252,2254,2256,2258,2260,2262,2264,2266,2268,2270,2272,2274,2276,2278,2280,2282,2284,2286,2288,2290,2292,2294,2296,2298,2300,2302,2304,2306,2308,2310,2312,2314,2316,2318,2320,2322,2324,2326,2328,2330,2332,2334,2336,2338,2340,2342,2344,2346,2348,2350,2352,2354,2356,2358,2360,2362,2364,2366,2368,2370,2372,2374,2376,2378,2380,2382,2384,2386,2388,2390,2392,2394,2396,2398,2400,2402,2404,2406,2408,2410,2412,2414,2416,2418,2420,2422,2424,2426,2428,2430,2432,2434,2436,2438,2440,2442,2444,2446,2448,2450,2452,2454,2456,2458,2460,2462,2464,2466,2468,2470,2472,2474,2476,2478,2480,2482,2484,2486,2488,2490,2492,2494,2496,2498,2500,2502,2504,2506,2508,2510,2512,2514,2516,2518,2520,2522,2524,2526,2528,2530,2532,2534,2536,2538,2540,2542,2544,2546,2548,2550,2552,2554,2556,2558,2560,2562,2564,2566,2568,2570,2572,2574,2576,2578,2580,2582,2584,2586,2588,2590,2592,2594,2596,2598,2600,2602,2604,2606,2608,2610,2612,2614,2616,2618,2620,2622,2624,2626,2628,2630,2632,2634,2636,2638,2640,2642,2644,2646,2648,2650,2652,2654,2656,2658,2660,2662,2664,2666,2668,2670,2672,2674,2676,2678,2680,2682,2684,2686,2688,2690,2692,2694,2696,2698,2700,2702,2704,2706,2708,2710,2712,2714,2716,2718,2720,2722,2724,2726,2728,2730,2732,2734,2736,2738,2740,2742,2744,2746,2748,2750,2752,2754,2756,2758,2760,2762,2764,2766,2768,2770,2772,2774,2776,2778,2780,2782,2784,2786,2788,2790,2792,2794,2796,2798,2800,2802,2804,2806,2808,2810,2812,2814,2816,2818,2820,2822,2824,2826,2828,2830,2832,2834,2836,2838,2840,2842,2844,2846,2848,2850,2852,2854,2856,2858,2860,2862,2864,2866,2868,2870,2872,2874,2876,2878,2880,2882,2884,2886,2888,2890,2892,2894,2896,2898,2900,2902,2904,2906,2908,2910,2912,2914,2916,2918,2920,2922,2924,2926,2928,2930,2932,2934,2936,2938,2940,2942,2944,2946,2948,2950,2952,2954,2956,2958,2960,2962,2964,2966,2968,2970,2972,2974,2976,2978,2980,2982,2984,2986,2988,2990,2992,2994,2996,2998,3000,3002,3004,3006,3008,3010,3012,3014,3016,3018,3020,3022,3024,3026,3028,3030,3032,3034,3036,3038,3040,3042,3044,3046,3048,3050,3052,3054,3056,3058,3060,3062,3064,3066,3068,3070,3072,3074,3076,3078,3080,3082,3084,3086,3088,3090,3092,3094,3096,3098,3100,3102,3104,3106,3108,3110,3112,3114,3116,3118,3120,3122,3124,3126,3128,3130,3132,3134,3136,3138,3140,3142,3144,3146,3148,3150,3152,3154,3156,3158,3160,3162,3164,3166,3168,3170,3172,3174,3176,3178,3180,3182,3184,3186,3188,3190,3192,3194,3196,3198,3200,3202,3204,3206,3208,3210,3212,3214,3216,3218,3220,3222,3224,3226,3228,3230,3232,3234,3236,3238,3240,3242,3244,3246,3248,3250,3252,3254,3256,3258,3260,3262,3264,3266,3268,3270,3272,3274,3276,3278,3280,3282,3284,3286,3288,3290,3292,3294,3296,3298,3300,3302,3304,3306,3308,3310,3312,3314,3316,3318,3320,3322,3324,3326,3328,3330,3332,3334,3336,3338,3340,3342,3344,3346,3348,3350,3352,3354,3356,3358,3360,3362,3364,3366,3368,3370,3372,3374,3376,3378,3380,3382,3384,3386,3388,3390,3392,3394,3396,3398,3400,3402,3404,3406,3408,3410,3412,3414,3416,3418,3420,3422,3424,3426,3428,3430,3432,3434,3436,3438,3440,3442,3444,3446,3448,3450,3452,3454,3456,3458,3460,3462,3464,3466,3468,3470,3472,3474,3476,3478,3480,3482,3484,3486,3488,3490,3492,3494,3496,3498,3500,3502,3504,3506,3508,3510,3512,3514,3516,3518,3520,3522,3524,3526,3528,3530,3532,3534,3536,3538,3540,3542,3544,3546,3548,3550,3552,3554,3556,3558,3560,3562,3564,3566,3568,3570,3572,3574,3576,3578,3580,3582,3584,3586,3588,3590,3592,3594,3596,3598,3600,3602,3604,3606,3608,3610,3612,3614,3616,3618,3620,3622,3624,3626,3628,3630,3632,3634,3636,3638],{"categories":73},[74],"Developer Productivity",{"categories":76},[77],"Business & SaaS",{"categories":79},[42],{"categories":81},[82],"AI Automation",{"categories":84},[85],"Product Strategy",{"categories":87},[42],{"categories":89},[74],{"categories":91},[77],{"categories":93},[],{"categories":95},[42],{"categories":97},[],{"categories":99},[100],"AI News & Trends",{"categories":102},[82],{"categories":104},[100],{"categories":106},[82],{"categories":108},[82],{"categories":110},[42],{"categories":112},[42],{"categories":114},[100],{"categories":116},[42],{"categories":118},[],{"categories":120},[121],"Design & Frontend",{"categories":123},[124],"Data Science & Visualization",{"categories":126},[100],{"categories":128},[],{"categories":130},[131],"Software Engineering",{"categories":133},[42],{"categories":135},[82],{"categories":137},[138],"Marketing & Growth",{"categories":140},[42],{"categories":142},[82],{"categories":144},[],{"categories":146},[],{"categories":148},[121],{"categories":150},[82],{"categories":152},[74],{"categories":154},[121],{"categories":156},[42],{"categories":158},[82],{"categories":160},[100],{"categories":162},[],{"categories":164},[],{"categories":166},[82],{"categories":168},[131],{"categories":170},[],{"categories":172},[77],{"categories":174},[],{"categories":176},[],{"categories":178},[82],{"categories":180},[82],{"categories":182},[42],{"categories":184},[],{"categories":186},[131],{"categories":188},[],{"categories":190},[],{"categories":192},[],{"categories":194},[42],{"categories":196},[138],{"categories":198},[121],{"categories":200},[121],{"categories":202},[42],{"categories":204},[82],{"categories":206},[42],{"categories":208},[42],{"categories":210},[82],{"categories":212},[82],{"categories":214},[124],{"categories":216},[100],{"categories":218},[82],{"categories":220},[138],{"categories":222},[82],{"categories":224},[85],{"categories":226},[],{"categories":228},[82],{"categories":230},[],{"categories":232},[82],{"categories":234},[131],{"categories":236},[121],{"categories":238},[42],{"categories":240},[],{"categories":242},[],{"categories":244},[82],{"categories":246},[],{"categories":248},[42],{"categories":250},[],{"categories":252},[74],{"categories":254},[131],{"categories":256},[77],{"categories":258},[100],{"categories":260},[42],{"categories":262},[],{"categories":264},[42],{"categories":266},[],{"categories":268},[131],{"categories":270},[124],{"categories":272},[],{"categories":274},[42],{"categories":276},[121],{"categories":278},[],{"categories":280},[121],{"categories":282},[82],{"categories":284},[],{"categories":286},[82],{"categories":288},[100],{"categories":290},[42],{"categories":292},[],{"categories":294},[82],{"categories":296},[42],{"categories":298},[85],{"categories":300},[],{"categories":302},[42],{"categories":304},[82],{"categories":306},[82],{"categories":308},[],{"categories":310},[124],{"categories":312},[42],{"categories":314},[],{"categories":316},[74],{"categories":318},[77],{"categories":320},[42],{"categories":322},[82],{"categories":324},[131],{"categories":326},[42],{"categories":328},[],{"categories":330},[],{"categories":332},[42],{"categories":334},[],{"categories":336},[121],{"categories":338},[],{"categories":340},[42],{"categories":342},[],{"categories":344},[82],{"categories":346},[42],{"categories":348},[121],{"categories":350},[],{"categories":352},[42],{"categories":354},[42],{"categories":356},[77],{"categories":358},[82],{"categories":360},[42],{"categories":362},[121],{"categories":364},[82],{"categories":366},[],{"categories":368},[],{"categories":370},[100],{"categories":372},[],{"categories":374},[42],{"categories":376},[77,138],{"categories":378},[],{"categories":380},[42],{"categories":382},[],{"categories":384},[],{"categories":386},[42],{"categories":388},[],{"categories":390},[42],{"categories":392},[393],"DevOps & Cloud",{"categories":395},[],{"categories":397},[100],{"categories":399},[121],{"categories":401},[],{"categories":403},[100],{"categories":405},[100],{"categories":407},[42],{"categories":409},[138],{"categories":411},[],{"categories":413},[77],{"categories":415},[],{"categories":417},[42,393],{"categories":419},[42],{"categories":421},[42],{"categories":423},[82],{"categories":425},[42,131],{"categories":427},[124],{"categories":429},[42],{"categories":431},[138],{"categories":433},[82],{"categories":435},[82],{"categories":437},[],{"categories":439},[82],{"categories":441},[42,77],{"categories":443},[],{"categories":445},[121],{"categories":447},[121],{"categories":449},[],{"categories":451},[],{"categories":453},[100],{"categories":455},[],{"categories":457},[74],{"categories":459},[131],{"categories":461},[42],{"categories":463},[121],{"categories":465},[82],{"categories":467},[131],{"categories":469},[100],{"categories":471},[121],{"categories":473},[],{"categories":475},[42],{"categories":477},[42],{"categories":479},[42],{"categories":481},[100],{"categories":483},[74],{"categories":485},[42],{"categories":487},[82],{"categories":489},[393],{"categories":491},[121],{"categories":493},[82],{"categories":495},[],{"categories":497},[],{"categories":499},[121],{"categories":501},[100],{"categories":503},[124],{"categories":505},[],{"categories":507},[42],{"categories":509},[42],{"categories":511},[77],{"categories":513},[42],{"categories":515},[42],{"categories":517},[100],{"categories":519},[],{"categories":521},[82],{"categories":523},[131],{"categories":525},[],{"categories":527},[42],{"categories":529},[42],{"categories":531},[82],{"categories":533},[],{"categories":535},[],{"categories":537},[42],{"categories":539},[],{"categories":541},[77],{"categories":543},[82],{"categories":545},[],{"categories":547},[74],{"categories":549},[42],{"categories":551},[77],{"categories":553},[100],{"categories":555},[],{"categories":557},[],{"categories":559},[],{"categories":561},[100],{"categories":563},[100],{"categories":565},[],{"categories":567},[],{"categories":569},[77],{"categories":571},[],{"categories":573},[],{"categories":575},[74],{"categories":577},[],{"categories":579},[138],{"categories":581},[82],{"categories":583},[77],{"categories":585},[82],{"categories":587},[],{"categories":589},[85],{"categories":591},[121],{"categories":593},[131],{"categories":595},[42],{"categories":597},[82],{"categories":599},[77],{"categories":601},[42],{"categories":603},[],{"categories":605},[],{"categories":607},[131],{"categories":609},[124],{"categories":611},[85],{"categories":613},[82],{"categories":615},[42],{"categories":617},[],{"categories":619},[393],{"categories":621},[],{"categories":623},[82],{"categories":625},[],{"categories":627},[],{"categories":629},[42],{"categories":631},[121],{"categories":633},[138],{"categories":635},[82],{"categories":637},[],{"categories":639},[74],{"categories":641},[],{"categories":643},[100],{"categories":645},[42,393],{"categories":647},[100],{"categories":649},[42],{"categories":651},[77],{"categories":653},[42],{"categories":655},[],{"categories":657},[77],{"categories":659},[],{"categories":661},[131],{"categories":663},[121],{"categories":665},[100],{"categories":667},[124],{"categories":669},[74],{"categories":671},[42],{"categories":673},[131],{"categories":675},[],{"categories":677},[],{"categories":679},[85],{"categories":681},[],{"categories":683},[42],{"categories":685},[],{"categories":687},[121],{"categories":689},[121],{"categories":691},[121],{"categories":693},[],{"categories":695},[],{"categories":697},[100],{"categories":699},[82],{"categories":701},[42],{"categories":703},[42],{"categories":705},[42],{"categories":707},[77],{"categories":709},[42],{"categories":711},[],{"categories":713},[131],{"categories":715},[131],{"categories":717},[77],{"categories":719},[],{"categories":721},[42],{"categories":723},[42],{"categories":725},[77],{"categories":727},[100],{"categories":729},[138],{"categories":731},[82],{"categories":733},[],{"categories":735},[121],{"categories":737},[],{"categories":739},[42],{"categories":741},[],{"categories":743},[77],{"categories":745},[82],{"categories":747},[],{"categories":749},[393],{"categories":751},[124],{"categories":753},[131],{"categories":755},[138],{"categories":757},[131],{"categories":759},[82],{"categories":761},[],{"categories":763},[],{"categories":765},[82],{"categories":767},[74],{"categories":769},[82],{"categories":771},[85],{"categories":773},[77],{"categories":775},[],{"categories":777},[42],{"categories":779},[85],{"categories":781},[42],{"categories":783},[42],{"categories":785},[138],{"categories":787},[121],{"categories":789},[82],{"categories":791},[],{"categories":793},[],{"categories":795},[393],{"categories":797},[131],{"categories":799},[],{"categories":801},[82],{"categories":803},[42],{"categories":805},[121,42],{"categories":807},[74],{"categories":809},[],{"categories":811},[42],{"categories":813},[74],{"categories":815},[121],{"categories":817},[82],{"categories":819},[131],{"categories":821},[],{"categories":823},[42],{"categories":825},[],{"categories":827},[74],{"categories":829},[],{"categories":831},[82],{"categories":833},[85],{"categories":835},[42],{"categories":837},[42],{"categories":839},[121],{"categories":841},[82],{"categories":843},[393],{"categories":845},[121],{"categories":847},[82],{"categories":849},[42],{"categories":851},[42],{"categories":853},[42],{"categories":855},[100],{"categories":857},[],{"categories":859},[85],{"categories":861},[82],{"categories":863},[121],{"categories":865},[82],{"categories":867},[131],{"categories":869},[121],{"categories":871},[82],{"categories":873},[100],{"categories":875},[],{"categories":877},[42],{"categories":879},[121],{"categories":881},[42],{"categories":883},[74],{"categories":885},[100],{"categories":887},[42],{"categories":889},[138],{"categories":891},[42],{"categories":893},[42],{"categories":895},[82],{"categories":897},[82],{"categories":899},[42],{"categories":901},[82],{"categories":903},[121],{"categories":905},[42],{"categories":907},[],{"categories":909},[],{"categories":911},[131],{"categories":913},[],{"categories":915},[74],{"categories":917},[393],{"categories":919},[],{"categories":921},[74],{"categories":923},[77],{"categories":925},[138],{"categories":927},[],{"categories":929},[77],{"categories":931},[],{"categories":933},[],{"categories":935},[],{"categories":937},[],{"categories":939},[],{"categories":941},[42],{"categories":943},[82],{"categories":945},[393],{"categories":947},[74],{"categories":949},[42],{"categories":951},[131],{"categories":953},[85],{"categories":955},[42],{"categories":957},[138],{"categories":959},[42],{"categories":961},[42],{"categories":963},[42],{"categories":965},[42,74],{"categories":967},[131],{"categories":969},[131],{"categories":971},[121],{"categories":973},[42],{"categories":975},[],{"categories":977},[],{"categories":979},[],{"categories":981},[131],{"categories":983},[124],{"categories":985},[100],{"categories":987},[121],{"categories":989},[],{"categories":991},[42],{"categories":993},[42],{"categories":995},[],{"categories":997},[],{"categories":999},[82],{"categories":1001},[42],{"categories":1003},[77],{"categories":1005},[],{"categories":1007},[74],{"categories":1009},[42],{"categories":1011},[74],{"categories":1013},[42],{"categories":1015},[131],{"categories":1017},[138],{"categories":1019},[42,121],{"categories":1021},[100],{"categories":1023},[121],{"categories":1025},[],{"categories":1027},[393],{"categories":1029},[121],{"categories":1031},[82],{"categories":1033},[],{"categories":1035},[],{"categories":1037},[],{"categories":1039},[],{"categories":1041},[131],{"categories":1043},[82],{"categories":1045},[82],{"categories":1047},[42],{"categories":1049},[42],{"categories":1051},[],{"categories":1053},[121],{"categories":1055},[],{"categories":1057},[],{"categories":1059},[82],{"categories":1061},[],{"categories":1063},[],{"categories":1065},[138],{"categories":1067},[138],{"categories":1069},[82],{"categories":1071},[],{"categories":1073},[42],{"categories":1075},[42],{"categories":1077},[131],{"categories":1079},[121],{"categories":1081},[121],{"categories":1083},[82],{"categories":1085},[74],{"categories":1087},[42],{"categories":1089},[121],{"categories":1091},[121],{"categories":1093},[82],{"categories":1095},[82],{"categories":1097},[42],{"categories":1099},[],{"categories":1101},[],{"categories":1103},[42],{"categories":1105},[82],{"categories":1107},[100],{"categories":1109},[131],{"categories":1111},[74],{"categories":1113},[42],{"categories":1115},[],{"categories":1117},[82],{"categories":1119},[82],{"categories":1121},[],{"categories":1123},[74],{"categories":1125},[42],{"categories":1127},[74],{"categories":1129},[74],{"categories":1131},[],{"categories":1133},[],{"categories":1135},[82],{"categories":1137},[82],{"categories":1139},[42],{"categories":1141},[42],{"categories":1143},[100],{"categories":1145},[124],{"categories":1147},[85],{"categories":1149},[100],{"categories":1151},[121],{"categories":1153},[],{"categories":1155},[100],{"categories":1157},[],{"categories":1159},[],{"categories":1161},[],{"categories":1163},[],{"categories":1165},[131],{"categories":1167},[124],{"categories":1169},[],{"categories":1171},[42],{"categories":1173},[42],{"categories":1175},[124],{"categories":1177},[131],{"categories":1179},[],{"categories":1181},[],{"categories":1183},[82],{"categories":1185},[100],{"categories":1187},[100],{"categories":1189},[82],{"categories":1191},[74],{"categories":1193},[42,393],{"categories":1195},[],{"categories":1197},[121],{"categories":1199},[74],{"categories":1201},[82],{"categories":1203},[121],{"categories":1205},[],{"categories":1207},[82],{"categories":1209},[82],{"categories":1211},[42],{"categories":1213},[138],{"categories":1215},[131],{"categories":1217},[121],{"categories":1219},[],{"categories":1221},[82],{"categories":1223},[42],{"categories":1225},[82],{"categories":1227},[82],{"categories":1229},[82],{"categories":1231},[138],{"categories":1233},[82],{"categories":1235},[42],{"categories":1237},[],{"categories":1239},[138],{"categories":1241},[100],{"categories":1243},[82],{"categories":1245},[],{"categories":1247},[],{"categories":1249},[42],{"categories":1251},[82],{"categories":1253},[100],{"categories":1255},[82],{"categories":1257},[],{"categories":1259},[],{"categories":1261},[],{"categories":1263},[82],{"categories":1265},[],{"categories":1267},[],{"categories":1269},[124],{"categories":1271},[42],{"categories":1273},[124],{"categories":1275},[100],{"categories":1277},[42],{"categories":1279},[42],{"categories":1281},[82],{"categories":1283},[42],{"categories":1285},[],{"categories":1287},[],{"categories":1289},[393],{"categories":1291},[],{"categories":1293},[],{"categories":1295},[74],{"categories":1297},[],{"categories":1299},[],{"categories":1301},[],{"categories":1303},[],{"categories":1305},[131],{"categories":1307},[100],{"categories":1309},[138],{"categories":1311},[77],{"categories":1313},[42],{"categories":1315},[42],{"categories":1317},[77],{"categories":1319},[],{"categories":1321},[121],{"categories":1323},[82],{"categories":1325},[77],{"categories":1327},[42],{"categories":1329},[42],{"categories":1331},[74],{"categories":1333},[],{"categories":1335},[74],{"categories":1337},[42],{"categories":1339},[138],{"categories":1341},[82],{"categories":1343},[100],{"categories":1345},[77],{"categories":1347},[42],{"categories":1349},[82],{"categories":1351},[],{"categories":1353},[42],{"categories":1355},[74],{"categories":1357},[42],{"categories":1359},[],{"categories":1361},[100],{"categories":1363},[42],{"categories":1365},[],{"categories":1367},[77],{"categories":1369},[42],{"categories":1371},[],{"categories":1373},[],{"categories":1375},[],{"categories":1377},[42],{"categories":1379},[],{"categories":1381},[393],{"categories":1383},[42],{"categories":1385},[],{"categories":1387},[42],{"categories":1389},[42],{"categories":1391},[42],{"categories":1393},[42,393],{"categories":1395},[42],{"categories":1397},[42],{"categories":1399},[121],{"categories":1401},[82],{"categories":1403},[],{"categories":1405},[82],{"categories":1407},[42],{"categories":1409},[42],{"categories":1411},[42],{"categories":1413},[74],{"categories":1415},[74],{"categories":1417},[131],{"categories":1419},[121],{"categories":1421},[82],{"categories":1423},[],{"categories":1425},[42],{"categories":1427},[100],{"categories":1429},[42],{"categories":1431},[77],{"categories":1433},[],{"categories":1435},[393],{"categories":1437},[121],{"categories":1439},[121],{"categories":1441},[82],{"categories":1443},[100],{"categories":1445},[82],{"categories":1447},[42],{"categories":1449},[],{"categories":1451},[42],{"categories":1453},[],{"categories":1455},[],{"categories":1457},[42],{"categories":1459},[42],{"categories":1461},[42],{"categories":1463},[82],{"categories":1465},[42],{"categories":1467},[],{"categories":1469},[124],{"categories":1471},[82],{"categories":1473},[],{"categories":1475},[42],{"categories":1477},[100],{"categories":1479},[],{"categories":1481},[121],{"categories":1483},[393],{"categories":1485},[100],{"categories":1487},[131],{"categories":1489},[131],{"categories":1491},[100],{"categories":1493},[100],{"categories":1495},[393],{"categories":1497},[],{"categories":1499},[100],{"categories":1501},[42],{"categories":1503},[74],{"categories":1505},[100],{"categories":1507},[],{"categories":1509},[124],{"categories":1511},[100],{"categories":1513},[131],{"categories":1515},[100],{"categories":1517},[393],{"categories":1519},[42],{"categories":1521},[42],{"categories":1523},[],{"categories":1525},[77],{"categories":1527},[],{"categories":1529},[],{"categories":1531},[42],{"categories":1533},[42],{"categories":1535},[42],{"categories":1537},[42],{"categories":1539},[],{"categories":1541},[124],{"categories":1543},[74],{"categories":1545},[],{"categories":1547},[42],{"categories":1549},[42],{"categories":1551},[393],{"categories":1553},[393],{"categories":1555},[],{"categories":1557},[82],{"categories":1559},[100],{"categories":1561},[100],{"categories":1563},[42],{"categories":1565},[82],{"categories":1567},[],{"categories":1569},[121],{"categories":1571},[42],{"categories":1573},[42],{"categories":1575},[],{"categories":1577},[],{"categories":1579},[393],{"categories":1581},[42],{"categories":1583},[131],{"categories":1585},[77],{"categories":1587},[42],{"categories":1589},[],{"categories":1591},[82],{"categories":1593},[74],{"categories":1595},[74],{"categories":1597},[],{"categories":1599},[42],{"categories":1601},[121],{"categories":1603},[82],{"categories":1605},[],{"categories":1607},[42],{"categories":1609},[42],{"categories":1611},[82],{"categories":1613},[],{"categories":1615},[82],{"categories":1617},[131],{"categories":1619},[],{"categories":1621},[42],{"categories":1623},[],{"categories":1625},[42],{"categories":1627},[],{"categories":1629},[42],{"categories":1631},[42],{"categories":1633},[],{"categories":1635},[42],{"categories":1637},[100],{"categories":1639},[42],{"categories":1641},[42],{"categories":1643},[74],{"categories":1645},[42],{"categories":1647},[100],{"categories":1649},[82],{"categories":1651},[],{"categories":1653},[42],{"categories":1655},[138],{"categories":1657},[],{"categories":1659},[],{"categories":1661},[],{"categories":1663},[74],{"categories":1665},[100],{"categories":1667},[82],{"categories":1669},[42],{"categories":1671},[121],{"categories":1673},[82],{"categories":1675},[],{"categories":1677},[82],{"categories":1679},[],{"categories":1681},[42],{"categories":1683},[82],{"categories":1685},[42],{"categories":1687},[],{"categories":1689},[42],{"categories":1691},[42],{"categories":1693},[100],{"categories":1695},[121],{"categories":1697},[82],{"categories":1699},[121],{"categories":1701},[77],{"categories":1703},[],{"categories":1705},[],{"categories":1707},[42],{"categories":1709},[74],{"categories":1711},[100],{"categories":1713},[],{"categories":1715},[],{"categories":1717},[131],{"categories":1719},[121],{"categories":1721},[],{"categories":1723},[42],{"categories":1725},[],{"categories":1727},[138],{"categories":1729},[42],{"categories":1731},[393],{"categories":1733},[131],{"categories":1735},[],{"categories":1737},[82],{"categories":1739},[42],{"categories":1741},[82],{"categories":1743},[82],{"categories":1745},[42],{"categories":1747},[],{"categories":1749},[74],{"categories":1751},[42],{"categories":1753},[77],{"categories":1755},[131],{"categories":1757},[121],{"categories":1759},[],{"categories":1761},[],{"categories":1763},[],{"categories":1765},[82],{"categories":1767},[121],{"categories":1769},[100],{"categories":1771},[42],{"categories":1773},[100],{"categories":1775},[121],{"categories":1777},[],{"categories":1779},[121],{"categories":1781},[100],{"categories":1783},[77],{"categories":1785},[42],{"categories":1787},[100],{"categories":1789},[138],{"categories":1791},[],{"categories":1793},[],{"categories":1795},[124],{"categories":1797},[42,131],{"categories":1799},[100],{"categories":1801},[42],{"categories":1803},[82],{"categories":1805},[82],{"categories":1807},[42],{"categories":1809},[],{"categories":1811},[131],{"categories":1813},[42],{"categories":1815},[124],{"categories":1817},[82],{"categories":1819},[138],{"categories":1821},[393],{"categories":1823},[],{"categories":1825},[74],{"categories":1827},[82],{"categories":1829},[82],{"categories":1831},[131],{"categories":1833},[42],{"categories":1835},[42],{"categories":1837},[],{"categories":1839},[],{"categories":1841},[],{"categories":1843},[393],{"categories":1845},[100],{"categories":1847},[42],{"categories":1849},[42],{"categories":1851},[42],{"categories":1853},[],{"categories":1855},[124],{"categories":1857},[77],{"categories":1859},[],{"categories":1861},[82],{"categories":1863},[393],{"categories":1865},[],{"categories":1867},[121],{"categories":1869},[121],{"categories":1871},[],{"categories":1873},[131],{"categories":1875},[121],{"categories":1877},[42],{"categories":1879},[],{"categories":1881},[100],{"categories":1883},[42],{"categories":1885},[121],{"categories":1887},[82],{"categories":1889},[100],{"categories":1891},[],{"categories":1893},[82],{"categories":1895},[121],{"categories":1897},[42],{"categories":1899},[],{"categories":1901},[42],{"categories":1903},[42],{"categories":1905},[393],{"categories":1907},[100],{"categories":1909},[124],{"categories":1911},[124],{"categories":1913},[],{"categories":1915},[],{"categories":1917},[],{"categories":1919},[82],{"categories":1921},[131],{"categories":1923},[131],{"categories":1925},[],{"categories":1927},[],{"categories":1929},[42],{"categories":1931},[],{"categories":1933},[82],{"categories":1935},[42],{"categories":1937},[],{"categories":1939},[42],{"categories":1941},[77],{"categories":1943},[42],{"categories":1945},[138],{"categories":1947},[82],{"categories":1949},[42],{"categories":1951},[131],{"categories":1953},[100],{"categories":1955},[82],{"categories":1957},[],{"categories":1959},[100],{"categories":1961},[82],{"categories":1963},[82],{"categories":1965},[],{"categories":1967},[77],{"categories":1969},[82],{"categories":1971},[],{"categories":1973},[42],{"categories":1975},[74],{"categories":1977},[100],{"categories":1979},[393],{"categories":1981},[82],{"categories":1983},[82],{"categories":1985},[74],{"categories":1987},[42],{"categories":1989},[],{"categories":1991},[],{"categories":1993},[121],{"categories":1995},[42,77],{"categories":1997},[],{"categories":1999},[74],{"categories":2001},[124],{"categories":2003},[42],{"categories":2005},[131],{"categories":2007},[42],{"categories":2009},[82],{"categories":2011},[42],{"categories":2013},[42],{"categories":2015},[100],{"categories":2017},[82],{"categories":2019},[],{"categories":2021},[],{"categories":2023},[82],{"categories":2025},[42],{"categories":2027},[393],{"categories":2029},[],{"categories":2031},[42],{"categories":2033},[82],{"categories":2035},[],{"categories":2037},[42],{"categories":2039},[138],{"categories":2041},[124],{"categories":2043},[82],{"categories":2045},[42],{"categories":2047},[393],{"categories":2049},[],{"categories":2051},[42],{"categories":2053},[138],{"categories":2055},[121],{"categories":2057},[42],{"categories":2059},[],{"categories":2061},[138],{"categories":2063},[100],{"categories":2065},[42],{"categories":2067},[42],{"categories":2069},[74],{"categories":2071},[],{"categories":2073},[],{"categories":2075},[121],{"categories":2077},[42],{"categories":2079},[124],{"categories":2081},[138],{"categories":2083},[138],{"categories":2085},[100],{"categories":2087},[],{"categories":2089},[],{"categories":2091},[42],{"categories":2093},[],{"categories":2095},[42,131],{"categories":2097},[100],{"categories":2099},[82],{"categories":2101},[131],{"categories":2103},[42],{"categories":2105},[74],{"categories":2107},[],{"categories":2109},[],{"categories":2111},[74],{"categories":2113},[138],{"categories":2115},[42],{"categories":2117},[],{"categories":2119},[121,42],{"categories":2121},[393],{"categories":2123},[74],{"categories":2125},[],{"categories":2127},[77],{"categories":2129},[77],{"categories":2131},[42],{"categories":2133},[131],{"categories":2135},[82],{"categories":2137},[100],{"categories":2139},[138],{"categories":2141},[121],{"categories":2143},[42],{"categories":2145},[42],{"categories":2147},[42],{"categories":2149},[74],{"categories":2151},[42],{"categories":2153},[82],{"categories":2155},[100],{"categories":2157},[],{"categories":2159},[],{"categories":2161},[124],{"categories":2163},[131],{"categories":2165},[42],{"categories":2167},[121],{"categories":2169},[124],{"categories":2171},[42],{"categories":2173},[42],{"categories":2175},[82],{"categories":2177},[82],{"categories":2179},[42,77],{"categories":2181},[],{"categories":2183},[121],{"categories":2185},[],{"categories":2187},[42],{"categories":2189},[100],{"categories":2191},[74],{"categories":2193},[74],{"categories":2195},[82],{"categories":2197},[42],{"categories":2199},[77],{"categories":2201},[131],{"categories":2203},[138],{"categories":2205},[],{"categories":2207},[100],{"categories":2209},[42],{"categories":2211},[42],{"categories":2213},[100],{"categories":2215},[131],{"categories":2217},[42],{"categories":2219},[82],{"categories":2221},[100],{"categories":2223},[42],{"categories":2225},[121],{"categories":2227},[42],{"categories":2229},[42],{"categories":2231},[393],{"categories":2233},[85],{"categories":2235},[82],{"categories":2237},[42],{"categories":2239},[100],{"categories":2241},[82],{"categories":2243},[138],{"categories":2245},[42],{"categories":2247},[],{"categories":2249},[42],{"categories":2251},[],{"categories":2253},[],{"categories":2255},[],{"categories":2257},[77],{"categories":2259},[42],{"categories":2261},[82],{"categories":2263},[100],{"categories":2265},[100],{"categories":2267},[100],{"categories":2269},[100],{"categories":2271},[],{"categories":2273},[74],{"categories":2275},[82],{"categories":2277},[100],{"categories":2279},[74],{"categories":2281},[82],{"categories":2283},[42],{"categories":2285},[42,82],{"categories":2287},[82],{"categories":2289},[393],{"categories":2291},[100],{"categories":2293},[100],{"categories":2295},[82],{"categories":2297},[42],{"categories":2299},[],{"categories":2301},[100],{"categories":2303},[138],{"categories":2305},[74],{"categories":2307},[42],{"categories":2309},[42],{"categories":2311},[],{"categories":2313},[131],{"categories":2315},[],{"categories":2317},[74],{"categories":2319},[82],{"categories":2321},[100],{"categories":2323},[42],{"categories":2325},[100],{"categories":2327},[74],{"categories":2329},[100],{"categories":2331},[100],{"categories":2333},[],{"categories":2335},[77],{"categories":2337},[82],{"categories":2339},[100],{"categories":2341},[100],{"categories":2343},[100],{"categories":2345},[100],{"categories":2347},[100],{"categories":2349},[100],{"categories":2351},[100],{"categories":2353},[100],{"categories":2355},[100],{"categories":2357},[100],{"categories":2359},[124],{"categories":2361},[74],{"categories":2363},[42],{"categories":2365},[42],{"categories":2367},[],{"categories":2369},[42,74],{"categories":2371},[],{"categories":2373},[82],{"categories":2375},[100],{"categories":2377},[82],{"categories":2379},[42],{"categories":2381},[42],{"categories":2383},[42],{"categories":2385},[42],{"categories":2387},[42],{"categories":2389},[82],{"categories":2391},[77],{"categories":2393},[121],{"categories":2395},[100],{"categories":2397},[42],{"categories":2399},[],{"categories":2401},[],{"categories":2403},[82],{"categories":2405},[121],{"categories":2407},[42],{"categories":2409},[],{"categories":2411},[],{"categories":2413},[138],{"categories":2415},[42],{"categories":2417},[],{"categories":2419},[],{"categories":2421},[74],{"categories":2423},[77],{"categories":2425},[42],{"categories":2427},[77],{"categories":2429},[121],{"categories":2431},[],{"categories":2433},[100],{"categories":2435},[],{"categories":2437},[121],{"categories":2439},[42],{"categories":2441},[138],{"categories":2443},[],{"categories":2445},[138],{"categories":2447},[],{"categories":2449},[],{"categories":2451},[82],{"categories":2453},[],{"categories":2455},[77],{"categories":2457},[74],{"categories":2459},[121],{"categories":2461},[131],{"categories":2463},[],{"categories":2465},[],{"categories":2467},[42],{"categories":2469},[74],{"categories":2471},[138],{"categories":2473},[],{"categories":2475},[82],{"categories":2477},[82],{"categories":2479},[100],{"categories":2481},[42],{"categories":2483},[82],{"categories":2485},[42],{"categories":2487},[82],{"categories":2489},[42],{"categories":2491},[85],{"categories":2493},[100],{"categories":2495},[],{"categories":2497},[138],{"categories":2499},[131],{"categories":2501},[82],{"categories":2503},[],{"categories":2505},[42],{"categories":2507},[82],{"categories":2509},[77],{"categories":2511},[74],{"categories":2513},[42],{"categories":2515},[121],{"categories":2517},[131],{"categories":2519},[131],{"categories":2521},[42],{"categories":2523},[124],{"categories":2525},[42],{"categories":2527},[82],{"categories":2529},[77],{"categories":2531},[82],{"categories":2533},[42],{"categories":2535},[42],{"categories":2537},[82],{"categories":2539},[100],{"categories":2541},[],{"categories":2543},[74],{"categories":2545},[42],{"categories":2547},[82],{"categories":2549},[42],{"categories":2551},[42],{"categories":2553},[],{"categories":2555},[121],{"categories":2557},[77],{"categories":2559},[100],{"categories":2561},[42],{"categories":2563},[42],{"categories":2565},[121],{"categories":2567},[138],{"categories":2569},[124],{"categories":2571},[42],{"categories":2573},[100],{"categories":2575},[42],{"categories":2577},[82],{"categories":2579},[393],{"categories":2581},[42],{"categories":2583},[82],{"categories":2585},[124],{"categories":2587},[],{"categories":2589},[82],{"categories":2591},[131],{"categories":2593},[121],{"categories":2595},[42],{"categories":2597},[74],{"categories":2599},[77],{"categories":2601},[131],{"categories":2603},[],{"categories":2605},[82],{"categories":2607},[42],{"categories":2609},[],{"categories":2611},[100],{"categories":2613},[],{"categories":2615},[100],{"categories":2617},[42],{"categories":2619},[82],{"categories":2621},[82],{"categories":2623},[82],{"categories":2625},[],{"categories":2627},[],{"categories":2629},[42],{"categories":2631},[42],{"categories":2633},[],{"categories":2635},[121],{"categories":2637},[82],{"categories":2639},[138],{"categories":2641},[74],{"categories":2643},[],{"categories":2645},[],{"categories":2647},[100],{"categories":2649},[131],{"categories":2651},[42],{"categories":2653},[42],{"categories":2655},[42],{"categories":2657},[131],{"categories":2659},[100],{"categories":2661},[121],{"categories":2663},[42],{"categories":2665},[42],{"categories":2667},[42],{"categories":2669},[100],{"categories":2671},[42],{"categories":2673},[100],{"categories":2675},[82],{"categories":2677},[82],{"categories":2679},[131],{"categories":2681},[82],{"categories":2683},[42],{"categories":2685},[131],{"categories":2687},[121],{"categories":2689},[],{"categories":2691},[82],{"categories":2693},[],{"categories":2695},[],{"categories":2697},[77],{"categories":2699},[42],{"categories":2701},[82],{"categories":2703},[74],{"categories":2705},[82],{"categories":2707},[138],{"categories":2709},[],{"categories":2711},[82],{"categories":2713},[],{"categories":2715},[74],{"categories":2717},[82],{"categories":2719},[],{"categories":2721},[82],{"categories":2723},[42],{"categories":2725},[100],{"categories":2727},[42],{"categories":2729},[82],{"categories":2731},[100],{"categories":2733},[82],{"categories":2735},[131],{"categories":2737},[121],{"categories":2739},[74],{"categories":2741},[],{"categories":2743},[82],{"categories":2745},[121],{"categories":2747},[100],{"categories":2749},[42],{"categories":2751},[121],{"categories":2753},[74],{"categories":2755},[],{"categories":2757},[82],{"categories":2759},[82],{"categories":2761},[42],{"categories":2763},[],{"categories":2765},[82],{"categories":2767},[85],{"categories":2769},[100],{"categories":2771},[82],{"categories":2773},[77],{"categories":2775},[],{"categories":2777},[42],{"categories":2779},[85],{"categories":2781},[42],{"categories":2783},[82],{"categories":2785},[100],{"categories":2787},[74],{"categories":2789},[393],{"categories":2791},[42],{"categories":2793},[42],{"categories":2795},[42],{"categories":2797},[100],{"categories":2799},[77],{"categories":2801},[42],{"categories":2803},[121],{"categories":2805},[100],{"categories":2807},[393],{"categories":2809},[42],{"categories":2811},[],{"categories":2813},[],{"categories":2815},[393],{"categories":2817},[124],{"categories":2819},[82],{"categories":2821},[82],{"categories":2823},[100],{"categories":2825},[42],{"categories":2827},[74],{"categories":2829},[121],{"categories":2831},[82],{"categories":2833},[42],{"categories":2835},[138],{"categories":2837},[42],{"categories":2839},[82],{"categories":2841},[],{"categories":2843},[42],{"categories":2845},[42],{"categories":2847},[100],{"categories":2849},[74],{"categories":2851},[],{"categories":2853},[42],{"categories":2855},[42],{"categories":2857},[131],{"categories":2859},[121],{"categories":2861},[42,82],{"categories":2863},[138,77],{"categories":2865},[42],{"categories":2867},[],{"categories":2869},[82],{"categories":2871},[],{"categories":2873},[131],{"categories":2875},[42],{"categories":2877},[100],{"categories":2879},[],{"categories":2881},[82],{"categories":2883},[],{"categories":2885},[82],{"categories":2887},[74],{"categories":2889},[82],{"categories":2891},[42],{"categories":2893},[393],{"categories":2895},[138],{"categories":2897},[77],{"categories":2899},[77],{"categories":2901},[74],{"categories":2903},[74],{"categories":2905},[42],{"categories":2907},[82],{"categories":2909},[42],{"categories":2911},[42],{"categories":2913},[74],{"categories":2915},[42],{"categories":2917},[138],{"categories":2919},[100],{"categories":2921},[42],{"categories":2923},[82],{"categories":2925},[42],{"categories":2927},[],{"categories":2929},[131],{"categories":2931},[],{"categories":2933},[82],{"categories":2935},[74],{"categories":2937},[],{"categories":2939},[393],{"categories":2941},[42],{"categories":2943},[],{"categories":2945},[100],{"categories":2947},[82],{"categories":2949},[131],{"categories":2951},[42],{"categories":2953},[82],{"categories":2955},[131],{"categories":2957},[82],{"categories":2959},[100],{"categories":2961},[74],{"categories":2963},[100],{"categories":2965},[131],{"categories":2967},[42],{"categories":2969},[121],{"categories":2971},[42],{"categories":2973},[42],{"categories":2975},[42],{"categories":2977},[42],{"categories":2979},[82],{"categories":2981},[42],{"categories":2983},[82],{"categories":2985},[42],{"categories":2987},[74],{"categories":2989},[42],{"categories":2991},[82],{"categories":2993},[121],{"categories":2995},[74],{"categories":2997},[82],{"categories":2999},[121],{"categories":3001},[],{"categories":3003},[42],{"categories":3005},[42],{"categories":3007},[131],{"categories":3009},[],{"categories":3011},[82],{"categories":3013},[138],{"categories":3015},[42],{"categories":3017},[100],{"categories":3019},[138],{"categories":3021},[82],{"categories":3023},[77],{"categories":3025},[77],{"categories":3027},[42],{"categories":3029},[74],{"categories":3031},[],{"categories":3033},[42],{"categories":3035},[],{"categories":3037},[74],{"categories":3039},[42],{"categories":3041},[82],{"categories":3043},[82],{"categories":3045},[],{"categories":3047},[131],{"categories":3049},[131],{"categories":3051},[138],{"categories":3053},[121],{"categories":3055},[],{"categories":3057},[42],{"categories":3059},[74],{"categories":3061},[42],{"categories":3063},[131],{"categories":3065},[74],{"categories":3067},[100],{"categories":3069},[100],{"categories":3071},[],{"categories":3073},[100],{"categories":3075},[82],{"categories":3077},[121],{"categories":3079},[124],{"categories":3081},[42],{"categories":3083},[],{"categories":3085},[100],{"categories":3087},[131],{"categories":3089},[77],{"categories":3091},[42],{"categories":3093},[74],{"categories":3095},[393],{"categories":3097},[74],{"categories":3099},[],{"categories":3101},[],{"categories":3103},[100],{"categories":3105},[],{"categories":3107},[82],{"categories":3109},[82],{"categories":3111},[82],{"categories":3113},[],{"categories":3115},[42],{"categories":3117},[],{"categories":3119},[100],{"categories":3121},[74],{"categories":3123},[121],{"categories":3125},[42],{"categories":3127},[100],{"categories":3129},[100],{"categories":3131},[],{"categories":3133},[100],{"categories":3135},[74],{"categories":3137},[42],{"categories":3139},[],{"categories":3141},[82],{"categories":3143},[82],{"categories":3145},[74],{"categories":3147},[],{"categories":3149},[],{"categories":3151},[],{"categories":3153},[121],{"categories":3155},[82],{"categories":3157},[42],{"categories":3159},[],{"categories":3161},[],{"categories":3163},[],{"categories":3165},[121],{"categories":3167},[],{"categories":3169},[74],{"categories":3171},[],{"categories":3173},[],{"categories":3175},[121],{"categories":3177},[42],{"categories":3179},[100],{"categories":3181},[],{"categories":3183},[138],{"categories":3185},[100],{"categories":3187},[138],{"categories":3189},[42],{"categories":3191},[],{"categories":3193},[],{"categories":3195},[82],{"categories":3197},[],{"categories":3199},[],{"categories":3201},[82],{"categories":3203},[42],{"categories":3205},[],{"categories":3207},[82],{"categories":3209},[100],{"categories":3211},[138],{"categories":3213},[124],{"categories":3215},[82],{"categories":3217},[82],{"categories":3219},[],{"categories":3221},[],{"categories":3223},[],{"categories":3225},[100],{"categories":3227},[],{"categories":3229},[],{"categories":3231},[121],{"categories":3233},[74],{"categories":3235},[],{"categories":3237},[77],{"categories":3239},[138],{"categories":3241},[42],{"categories":3243},[131],{"categories":3245},[74],{"categories":3247},[124],{"categories":3249},[77],{"categories":3251},[131],{"categories":3253},[],{"categories":3255},[],{"categories":3257},[82],{"categories":3259},[74],{"categories":3261},[121],{"categories":3263},[74],{"categories":3265},[82],{"categories":3267},[393],{"categories":3269},[82],{"categories":3271},[],{"categories":3273},[42],{"categories":3275},[100],{"categories":3277},[131],{"categories":3279},[],{"categories":3281},[121],{"categories":3283},[100],{"categories":3285},[74],{"categories":3287},[82],{"categories":3289},[42],{"categories":3291},[77],{"categories":3293},[82,393],{"categories":3295},[82],{"categories":3297},[131],{"categories":3299},[42],{"categories":3301},[124],{"categories":3303},[138],{"categories":3305},[82],{"categories":3307},[],{"categories":3309},[82],{"categories":3311},[42],{"categories":3313},[77],{"categories":3315},[],{"categories":3317},[],{"categories":3319},[42],{"categories":3321},[124],{"categories":3323},[42],{"categories":3325},[],{"categories":3327},[100],{"categories":3329},[],{"categories":3331},[100],{"categories":3333},[131],{"categories":3335},[82],{"categories":3337},[42],{"categories":3339},[138],{"categories":3341},[131],{"categories":3343},[],{"categories":3345},[100],{"categories":3347},[42],{"categories":3349},[],{"categories":3351},[42],{"categories":3353},[82],{"categories":3355},[42],{"categories":3357},[82],{"categories":3359},[42],{"categories":3361},[42],{"categories":3363},[42],{"categories":3365},[42],{"categories":3367},[77],{"categories":3369},[],{"categories":3371},[85],{"categories":3373},[100],{"categories":3375},[42],{"categories":3377},[],{"categories":3379},[131],{"categories":3381},[42],{"categories":3383},[42],{"categories":3385},[82],{"categories":3387},[100],{"categories":3389},[42],{"categories":3391},[42],{"categories":3393},[77],{"categories":3395},[82],{"categories":3397},[121],{"categories":3399},[],{"categories":3401},[124],{"categories":3403},[42],{"categories":3405},[],{"categories":3407},[100],{"categories":3409},[138],{"categories":3411},[],{"categories":3413},[],{"categories":3415},[100],{"categories":3417},[100],{"categories":3419},[138],{"categories":3421},[74],{"categories":3423},[82],{"categories":3425},[82],{"categories":3427},[42],{"categories":3429},[77],{"categories":3431},[],{"categories":3433},[],{"categories":3435},[100],{"categories":3437},[124],{"categories":3439},[131],{"categories":3441},[82],{"categories":3443},[121],{"categories":3445},[124],{"categories":3447},[124],{"categories":3449},[],{"categories":3451},[100],{"categories":3453},[42],{"categories":3455},[42],{"categories":3457},[131],{"categories":3459},[],{"categories":3461},[100],{"categories":3463},[100],{"categories":3465},[100],{"categories":3467},[],{"categories":3469},[82],{"categories":3471},[42],{"categories":3473},[],{"categories":3475},[74],{"categories":3477},[77],{"categories":3479},[],{"categories":3481},[42],{"categories":3483},[42],{"categories":3485},[],{"categories":3487},[131],{"categories":3489},[],{"categories":3491},[],{"categories":3493},[],{"categories":3495},[],{"categories":3497},[42],{"categories":3499},[100],{"categories":3501},[],{"categories":3503},[],{"categories":3505},[42],{"categories":3507},[42],{"categories":3509},[42],{"categories":3511},[124],{"categories":3513},[42],{"categories":3515},[124],{"categories":3517},[],{"categories":3519},[124],{"categories":3521},[124],{"categories":3523},[393],{"categories":3525},[82],{"categories":3527},[131],{"categories":3529},[],{"categories":3531},[],{"categories":3533},[124],{"categories":3535},[131],{"categories":3537},[131],{"categories":3539},[131],{"categories":3541},[],{"categories":3543},[74],{"categories":3545},[131],{"categories":3547},[131],{"categories":3549},[74],{"categories":3551},[131],{"categories":3553},[77],{"categories":3555},[131],{"categories":3557},[131],{"categories":3559},[131],{"categories":3561},[124],{"categories":3563},[100],{"categories":3565},[100],{"categories":3567},[42],{"categories":3569},[131],{"categories":3571},[124],{"categories":3573},[393],{"categories":3575},[124],{"categories":3577},[124],{"categories":3579},[124],{"categories":3581},[],{"categories":3583},[77],{"categories":3585},[],{"categories":3587},[393],{"categories":3589},[131],{"categories":3591},[131],{"categories":3593},[131],{"categories":3595},[82],{"categories":3597},[100,77],{"categories":3599},[124],{"categories":3601},[],{"categories":3603},[],{"categories":3605},[124],{"categories":3607},[],{"categories":3609},[124],{"categories":3611},[100],{"categories":3613},[82],{"categories":3615},[],{"categories":3617},[131],{"categories":3619},[42],{"categories":3621},[121],{"categories":3623},[],{"categories":3625},[42],{"categories":3627},[],{"categories":3629},[100],{"categories":3631},[74],{"categories":3633},[124],{"categories":3635},[],{"categories":3637},[131],{"categories":3639},[100],[3641,3731,3898,3996],{"id":3642,"title":3643,"ai":3644,"body":3649,"categories":3707,"created_at":43,"date_modified":43,"description":36,"extension":44,"faq":43,"featured":45,"kicker_label":43,"meta":3708,"navigation":53,"path":3717,"published_at":3718,"question":43,"scraped_at":3719,"seo":3720,"sitemap":3721,"source_id":3722,"source_name":3723,"source_type":61,"source_url":3724,"stem":3725,"tags":3726,"thumbnail_url":43,"tldr":3728,"tweet":43,"unknown_tags":3729,"__hash__":3730},"summaries\u002Fsummaries\u002F274d310f289e54db-yin-yang-llm-pipeline-cuts-noise-in-code-scanning-summary.md","Yin-Yang LLM Pipeline Cuts Noise in Code Scanning",{"provider":7,"model":8,"input_tokens":3645,"output_tokens":3646,"processing_time_ms":3647,"cost_usd":3648},5484,1270,11737,0.00122495,{"type":14,"value":3650,"toc":3701},[3651,3655,3667,3671,3679,3683,3694,3698],[17,3652,3654],{"id":3653},"designed-distrust-yin-yang-agents-balance-recall-and-precision","Designed Distrust: Yin-Yang Agents Balance Recall and Precision",[22,3656,3657,3658,3662,3663,3666],{},"Treat LLMs as stochastic machines with expected errors, not infallible oracles. Veritas pipeline uses two opposing agents: the ",[3659,3660,3661],"strong",{},"hypothesis agent (Yang)"," maximizes recall by scanning architecture entry points, trust boundaries, and threat models to flag every plausible vulnerability candidate cheaply—prioritizing low cost of refuted hypotheses over missing real issues. The ",[3659,3664,3665],{},"evidence agent (Yin)"," maximizes precision as a skeptical auditor, refuting claims unless backed by cited source-code evidence like sanitizers or validation logic. This tug-of-war decouples generation from judgment, letting hypothesis over-generate (reducing Type 2 false negatives) while evidence strictly verifies (reducing Type 1 false positives), avoiding single-stage scanners' internal conflicts on the precision-recall curve.",[17,3668,3670],{"id":3669},"information-bottleneck-defeats-anchoring-bias","Information Bottleneck Defeats Anchoring Bias",[22,3672,3673,3674,3678],{},"Strip reasoning from hypotheses via ",[3675,3676,3677],"code",{},"slim_hypotheses_for_evidence()"," before evidence review, forcing independent verification against raw code context. Deleting the \"why\" prevents anchoring bias, where prior explanations cause overfitting and hallucinated confirmations. Evidence agent must rediscover exploit paths or discard findings, making the system smarter by intentionally \"dumbing down\" the second stage—trading tokens for quality.",[17,3680,3682],{"id":3681},"deterministic-policy-gate-overrides-ai-verdicts","Deterministic Policy Gate Overrides AI Verdicts",[22,3684,3685,3686,3689,3690,3693],{},"AI never decides alone: a mechanical ",[3659,3687,3688],{},"policy gate"," applies checklists post-pipeline. Findings below 0.3 confidence score marked \"Inconclusive\"; critical\u002Fhigh-severity inconclusive ones flagged ",[3675,3691,3692],{},"NEEDS_HUMAN"," instead of dropped. Every pre-scan finding gets confirmed, disproven, or escalated with full audit trail. This handles variation like assembly-line quality control, producing reviewable outputs for developers during manual reviews—not replacing SAST tools like CodeQL, but assisting Security Champions.",[17,3695,3697],{"id":3696},"pipeline-outcomes-process-over-prompting","Pipeline Outcomes: Process Over Prompting",[22,3699,3700],{},"Statistical process control trumps prompt engineering: accuracy emerges from architectural tension (expansion then contraction), not model size or perfect prompts. Hypothesis runs high-recall\u002Flow-precision; evidence shifts to high-precision. Extra compute yields hallucination-free reports tied to evidence, with next steps in empirical calibration against known vuln\u002Fnon-vuln cases. Veritas (GitHub POC) proves treating LLM outputs as intermediates—with inspection, disposition, escalation—yields trustworthy code review aids.",{"title":36,"searchDepth":37,"depth":37,"links":3702},[3703,3704,3705,3706],{"id":3653,"depth":37,"text":3654},{"id":3669,"depth":37,"text":3670},{"id":3681,"depth":37,"text":3682},{"id":3696,"depth":37,"text":3697},[42],{"content_references":3709,"triage":3715},[3710],{"type":3711,"title":3712,"url":3713,"context":3714},"tool","Veritas","https:\u002F\u002Fgithub.com\u002Fjoshconkel\u002FVeritas-POC","mentioned",{"relevance":49,"novelty":50,"quality":50,"actionability":50,"composite":51,"reasoning":3716},"Category: AI Automation. The article presents a novel approach to AI code scanning by introducing a dual-agent system that balances recall and precision, addressing a specific pain point for developers looking to improve code reliability. It offers actionable insights on implementing a deterministic policy gate and emphasizes the importance of independent verification, making it relevant and practical for the target audience.","\u002Fsummaries\u002F274d310f289e54db-yin-yang-llm-pipeline-cuts-noise-in-code-scanning-summary","2026-05-03 16:01:01","2026-05-03 17:00:57",{"title":3643,"description":36},{"loc":3717},"274d310f289e54db","Towards AI","https:\u002F\u002Fpub.towardsai.net\u002Fyin-yang-and-the-llm-engineering-reliability-into-ai-code-scanning-35f4f6c222fa?source=rss----98111c9905da---4","summaries\u002F274d310f289e54db-yin-yang-llm-pipeline-cuts-noise-in-code-scanning-summary",[65,66,3727,67],"ai-automation","Build reliable AI code scanners by pitting a recall-focused hypothesis agent against a precision-focused evidence agent, stripping reasoning to avoid bias, and enforcing a deterministic policy gate—treating LLMs as stochastic machines, not oracles.",[3727,67],"JWz6oOrzw6FIoiG_JJucEu0m9Nr-uNWnazNK1OjyM-I",{"id":3732,"title":3733,"ai":3734,"body":3739,"categories":3876,"created_at":43,"date_modified":43,"description":36,"extension":44,"faq":43,"featured":45,"kicker_label":43,"meta":3877,"navigation":53,"path":3885,"published_at":3886,"question":43,"scraped_at":3887,"seo":3888,"sitemap":3889,"source_id":3890,"source_name":3891,"source_type":61,"source_url":3892,"stem":3893,"tags":3894,"thumbnail_url":43,"tldr":3895,"tweet":43,"unknown_tags":3896,"__hash__":3897},"summaries\u002Fsummaries\u002Ffe837463ae43e90d-context-engines-fix-agent-context-to-cut-tokens-50-summary.md","Context Engines: Fix Agent Context to Cut Tokens 50%",{"provider":7,"model":8,"input_tokens":3735,"output_tokens":3736,"processing_time_ms":3737,"cost_usd":3738},8656,2106,27045,0.00276155,{"type":14,"value":3740,"toc":3869},[3741,3745,3748,3751,3754,3757,3761,3764,3767,3770,3773,3777,3780,3783,3811,3814,3817,3821,3824,3827,3830,3833,3836,3839,3843],[17,3742,3744],{"id":3743},"agents-need-org-context-to-avoid-doom-loops","Agents Need Org Context to Avoid Doom Loops",[22,3746,3747],{},"Peter Werry from Unblocked explains that AI agents start at \"ground zero\" with no knowledge of your codebase, conventions, or decisions. Without targeted context, they rip through repos inefficiently, leading to wrong code, long reviews, and \"doom loops\"—endless iterations fixing misguided outputs. Humans used to be the context engine, manually feeding tickets and correcting agents, but scaling to background agents demands automation.",[22,3749,3750],{},"The goal mirrors human onboarding: accumulate \"battle scars\" from incidents, mentors, and history to know \"why\" things are built a certain way. Werry references an adoption curve (lifted from Vimath) showing progression from autocomplete (2022, 8k tokens) to parallel agents with MCP servers, toward cloud-based YOLO agents. Humans become the bottleneck in context-switching; context engines enable agentic freedom by supplying \"all the context you need and most importantly none you don't\" in optimized form.",[22,3752,3753],{},"\"Context engineering is kind of the art of supplying uh all the context that you need and most importantly none of the context that you don't need in a highly optimized way so that when the agent starts to run it executes the task uh in a streamlined way that's in line with your organization's best practices.\" (Peter Werry defining context engines—core to avoiding waste.)",[22,3755,3756],{},"A demo contrasts MCP-only vs. context engine: without it, an agent missed legacy Anthropic token budget deps, deleting code; with it, the agent preserved backwards compatibility after reasoning over history.",[17,3758,3760],{"id":3759},"myths-rag-mcp-and-big-windows-fall-short","Myths: RAG, MCP, and Big Windows Fall Short",[22,3762,3763],{},"Naive RAG over docs causes \"satisfaction of search\"—agents grab the first plausible match (e.g., from Notion) and stop, missing golden nuggets in Slack incidents or deleted PRs. In large orgs, it pulls irrelevant code, creates conflicts, wastes tokens on compaction, and ignores tasks\u002Fpersonalization.",[22,3765,3766],{},"Connecting MCP servers gives access but no relationships or \"why.\" Bigger windows (e.g., Gemini's 1M tokens) excel at needle-in-haystack but fail reasoning across sources or truth selection. Most orgs exceed 1M tokens anyway; even 50M won't resolve conflicts or focus retrieval.",[22,3768,3769],{},"\"Access doesn't equal understanding.\" (Werry on why MCP\u002FRAG alone leads to doom loops—emphasizes need for reasoning layer.)",[22,3771,3772],{},"The iceberg below compiling code: user intent, past rejections, failures, deletions. Agents need history to infer absences.",[17,3774,3776],{"id":3775},"building-blocks-graphs-resolution-personalization","Building Blocks: Graphs, Resolution, Personalization",[22,3778,3779],{},"Inputs: planning tools, docs, Slack\u002FTeams, code, PRs. Outputs: agents, CLI, code review in SCM, messaging.",[22,3781,3782],{},"Key requirements:",[3784,3785,3786,3793,3799,3805],"ul",{},[3787,3788,3789,3792],"li",{},[3659,3790,3791],{},"Unified relationships via social engineering graph",": Link data deeply—e.g., distill repeated PR comments into \"memories\" of best practices. Easy: PR-Slack links. Hard: infer decisions from patterns\u002Fincidents. (Workshop builds this graph.)",[3787,3794,3795,3798],{},[3659,3796,3797],{},"Conflict resolution",": Reject naive recency (docs\u002Fchats lag code). Evolved to: main branch as truth + expert convos (forward-looking) + history (what not to repeat). Surface unresolvable conflicts for human input.",[3787,3800,3801,3804],{},[3659,3802,3803],{},"Permissions",": Flow access controls—e.g., Slack private channels only for authorized users; answers stay private.",[3787,3806,3807,3810],{},[3659,3808,3809],{},"Targeted retrieval",": Bias to user's repos (via PR counts): deep vector search there, shallow elsewhere. Task-focused to save tokens.",[22,3812,3813],{},"High-level flow: Data sources → graph\u002Freasoning → personalized context → agents.",[22,3815,3816],{},"\"Satisfaction of search is a term that actually comes out of uh the medical field in radiology... they might find something... and then they stop.\" (Werry borrowing radiology concept—explains why agents halt prematurely, missing key org history.)",[17,3818,3820],{"id":3819},"production-lessons-what-unblocked-got-wrong","Production Lessons: What Unblocked Got Wrong",[22,3822,3823],{},"Initially optimized for access: knowledge graph + retrieval tools. Failed—agents couldn't traverse meaningfully.",[22,3825,3826],{},"Hid conflicts by forcing naive resolution (recency\u002Fcode bias). Better: surface them to learn from feedback.",[22,3828,3829],{},"Don't cache answers—code\u002Fdocs change constantly; prior answers regress to mean, polluting context.",[22,3831,3832],{},"Experiment: Larger task without engine repeated past failures (missed implementation details); with it, nailed it. Time: 2.5 hours → 25 minutes. Tokens: 21M → 10M. (Claude-estimated; vibe is dramatic efficiency.)",[22,3834,3835],{},"Use in planning (biggest wins via MCP skill) and review (understands motivations beyond code).",[22,3837,3838],{},"\"Initially we optimized for access not understanding... that does not work.\" (Werry on first failure—shift to reasoning was key pivot.)",[17,3840,3842],{"id":3841},"key-takeaways","Key Takeaways",[3784,3844,3845,3848,3851,3854,3857,3860,3863,3866],{},[3787,3846,3847],{},"Build social graphs to link code\u002FPRs\u002FSlack into memories of decisions\u002Fbest practices, not just surface links.",[3787,3849,3850],{},"Resolve conflicts with multi-signal scoring (recency + code truth + expert forward-look); surface irresolvables.",[3787,3852,3853],{},"Personalize via user PR history: deep retrieval on their repos, shallow elsewhere.",[3787,3855,3856],{},"Enforce permissions end-to-end—e.g., private Slack only for access holders.",[3787,3858,3859],{},"Integrate early in agent flows (planning\u002Freview) via MCP skills for 50%+ token\u002Ftime savings.",[3787,3861,3862],{},"Avoid caching answers or feeding prior outputs—dynamic orgs demand fresh retrieval.",[3787,3864,3865],{},"Target 'why' via history\u002Fincidents, beating RAG's 'what' for production code.",[3787,3867,3868],{},"Prototype with graphs before full engine; workshop-style builds reveal gaps fast.",{"title":36,"searchDepth":37,"depth":37,"links":3870},[3871,3872,3873,3874,3875],{"id":3743,"depth":37,"text":3744},{"id":3759,"depth":37,"text":3760},{"id":3775,"depth":37,"text":3776},{"id":3819,"depth":37,"text":3820},{"id":3841,"depth":37,"text":3842},[42],{"content_references":3878,"triage":3883},[3879],{"type":3880,"title":3881,"author":3882,"context":3714},"other","Adoption curve","Vimath",{"relevance":49,"novelty":50,"quality":50,"actionability":50,"composite":51,"reasoning":3884},"Category: AI & LLMs. The article discusses the importance of context in AI agents, addressing a specific pain point for developers integrating AI into their workflows. It provides actionable insights on building a reasoning layer to optimize agent performance, which is directly applicable to product builders.","\u002Fsummaries\u002Ffe837463ae43e90d-context-engines-fix-agent-context-to-cut-tokens-50-summary","2026-05-03 16:00:06","2026-05-04 16:07:41",{"title":3733,"description":36},{"loc":3885},"b0a932deb93b0851","AI Engineer","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=5ID22ACI7IM","summaries\u002Ffe837463ae43e90d-context-engines-fix-agent-context-to-cut-tokens-50-summary",[66,65,3727,67],"Agents fail without org-specific context; build a reasoning layer that personalizes retrieval, resolves conflicts, and respects permissions to deliver task-focused info, reducing task time from 2.5hrs\u002F21M tokens to 25min\u002F10M.",[3727,67],"LZtC3JN5Z5WtQmxN4NyOtG03I0YxgtekncwOC8lwGuY",{"id":3899,"title":3900,"ai":3901,"body":3906,"categories":3946,"created_at":43,"date_modified":43,"description":36,"extension":44,"faq":43,"featured":45,"kicker_label":43,"meta":3947,"navigation":53,"path":3982,"published_at":3983,"question":43,"scraped_at":3984,"seo":3985,"sitemap":3986,"source_id":3987,"source_name":3988,"source_type":61,"source_url":3989,"stem":3990,"tags":3991,"thumbnail_url":43,"tldr":3993,"tweet":43,"unknown_tags":3994,"__hash__":3995},"summaries\u002Fsummaries\u002Fc2092be3dd970841-harness-engineering-delivers-6x-agent-performance--summary.md","Harness Engineering Delivers 6x Agent Performance Over Models",{"provider":7,"model":8,"input_tokens":3902,"output_tokens":3903,"processing_time_ms":3904,"cost_usd":3905},6473,2111,16741,0.0023276,{"type":14,"value":3907,"toc":3941},[3908,3912,3915,3918,3922,3925,3928,3931,3935,3938],[17,3909,3911],{"id":3910},"harness-beats-model-proven-6x-gains-and-transferability","Harness Beats Model: Proven 6x Gains and Transferability",[22,3913,3914],{},"Same model and benchmark yield 6x performance differences purely from harness changes—everything outside model weights like system prompts, tool definitions, orchestration logic, memory management, verification, and safety guardrails. LangChain improved from outside TerminalBench 2.0 top 30 to rank 5 by tweaking only harness infrastructure. Stanford's Meta-Harness ranked Haiku #1 despite smaller size, outpacing larger models via optimized harness. Key: harnesses transfer across models, boosting five others when optimized on one, making them the reusable asset over volatile models.",[22,3916,3917],{},"Full harnesses hit ~75% SWE-bench pass@4 rate but burn 14x compute (16.3M tokens, 642 calls, 32min vs. 1.2M tokens, 51 calls, 7min stripped). Anthropic's patterns—prompt chaining, routing, parallelization, orchestrator-workers, evaluator-optimizer loops—combine into production agents, but ad-hoc Python scatters logic, blocking ablations.",[17,3919,3921],{"id":3920},"natural-language-harnesses-enable-ablation-and-efficiency","Natural Language Harnesses Enable Ablation and Efficiency",[22,3923,3924],{},"Tsinghua's NLAH represents control logic (contracts, roles, state, failures) in structured natural language over brittle code, separating runtime charter (state persistence, child agents) for clean swaps. Execution contracts bound calls (inputs, budgets, permissions, conditions, outputs); file-backed state survives truncation.",[22,3926,3927],{},"Migrating OS Symphony code harness to NLAH jumped OSWorld accuracy 30.4% to 47.2%, cut runtime 361min to 141min, LLM calls 1200 to 34 by replacing GUI loops with durable state. Ablations show self-evolution (+4.8 SWE-bench, +2.7 OSWorld) helps via narrow attempt loops; verifiers hurt (-8.4 OSWorld), multi-candidate search (-5.6). 90% compute delegates to child agents—harness orchestrates, doesn't reason.",[22,3929,3930],{},"Disciplined narrowing outperforms broadening; prune over add, as models evolve (e.g., drop context resets when Opus 4.6 no longer needs them).",[17,3932,3934],{"id":3933},"automated-optimization-and-safety-constraints","Automated Optimization and Safety Constraints",[22,3936,3937],{},"Stanford's Meta-Harness uses agentic proposer (Claude Code + Opus 4.6) to rewrite harness from failure traces (10M tokens\u002Fiteration, 82 files), evaluator scores proposals. Raw traces irreplaceable (50% to 34.6% without); hits 76.4% TerminalBench 2 (auto-optimized #1), 48.6% text classification (+7.7pts, 4x fewer tokens).",[22,3939,3940],{},"Complements: AutoHarness compiles rules to code (0% illegal moves in 145 games); AgentSpec DSL prevents 90% unsafe executions. Evolving field: harness assumptions expire with models—prune 80% tools (Vercel) or rewrite 5x in 6mo (Manus) for gains. Invest here over model waits: larger, faster, reliable returns.",{"title":36,"searchDepth":37,"depth":37,"links":3942},[3943,3944,3945],{"id":3910,"depth":37,"text":3911},{"id":3920,"depth":37,"text":3921},{"id":3933,"depth":37,"text":3934},[42],{"content_references":3948,"triage":3980},[3949,3956,3961,3964,3967,3971,3974,3977],{"type":3950,"title":3951,"author":3952,"publisher":3953,"url":3954,"context":3955},"paper","Natural-Language Agent Harnesses","Pan et al.","Tsinghua University","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.25723","cited",{"type":3950,"title":3957,"author":3958,"publisher":3959,"url":3960,"context":3955},"Meta-Harness: Automated Optimization of Agent Harnesses End-to-End","Lee et al.","Stanford University","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.28052v1",{"type":3950,"title":3962,"url":3963,"context":3955},"AutoHarness: improving LLM agents by automatically synthesizing a code harness","https:\u002F\u002Farxiv.org\u002Fabs\u002F2603.03329",{"type":3950,"title":3965,"url":3966,"context":3955},"AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agents","https:\u002F\u002Farxiv.org\u002Fabs\u002F2503.18666",{"type":3880,"title":3968,"author":3969,"url":3970,"context":3955},"Building Effective Agents","Anthropic","https:\u002F\u002Fwww.anthropic.com\u002Fresearch\u002Fbuilding-effective-agents",{"type":3880,"title":3972,"author":3969,"url":3973,"context":3955},"Effective Harnesses for Long-Running Agents","https:\u002F\u002Fwww.anthropic.com\u002Fengineering\u002Feffective-harnesses-for-long-running-agents",{"type":3880,"title":3975,"url":3976,"context":3955},"Harness engineering: leveraging Codex in an agent-first world","https:\u002F\u002Fopenai.com\u002Findex\u002Fharness-engineering\u002F",{"type":3880,"title":3978,"url":3979,"context":3955},"Improving Deep Agents with harness engineering","https:\u002F\u002Fwww.langchain.com\u002Fblog\u002Fimproving-deep-agents-with-harness-engineering",{"relevance":49,"novelty":50,"quality":50,"actionability":50,"composite":51,"reasoning":3981},"Category: AI & LLMs. The article discusses the significant performance improvements achieved through harness engineering, which directly addresses the audience's need for practical applications of AI tooling. It provides specific examples of performance metrics and optimization techniques that can be applied in real-world scenarios.","\u002Fsummaries\u002Fc2092be3dd970841-harness-engineering-delivers-6x-agent-performance-summary","2026-04-14 11:00:56","2026-05-03 16:59:38",{"title":3900,"description":36},{"loc":3982},"c2092be3dd970841","AI Summaries (evaluation playlist)","https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=Xxuxg8PcBvc","summaries\u002Fc2092be3dd970841-harness-engineering-delivers-6x-agent-performance--summary",[66,65,3992,67],"prompt-engineering","AI agent orchestration code (harness) drives 6x performance variation vs. model choice; natural language harnesses and automated optimization boost accuracy 16+ points while cutting compute 14x.",[67],"l2lnpVwsl0vG-AtPHBWgpF_DqoIbIVwiwKcbehmie8k",{"id":3997,"title":3998,"ai":3999,"body":4004,"categories":4094,"created_at":43,"date_modified":43,"description":36,"extension":44,"faq":43,"featured":45,"kicker_label":43,"meta":4095,"navigation":53,"path":4114,"published_at":43,"question":43,"scraped_at":4115,"seo":4116,"sitemap":4117,"source_id":4118,"source_name":4119,"source_type":61,"source_url":4120,"stem":4121,"tags":4122,"thumbnail_url":43,"tldr":4123,"tweet":43,"unknown_tags":4124,"__hash__":4125},"summaries\u002Fsummaries\u002F176b270d6050d162-ai-agents-speed-up-gpu-kernels-1-81x-with-scaffold-summary.md","AI Agents Speed Up GPU Kernels 1.81x with Scaffolding",{"provider":7,"model":8,"input_tokens":4000,"output_tokens":4001,"processing_time_ms":4002,"cost_usd":4003},8277,2360,15037,0.00281275,{"type":14,"value":4005,"toc":4087},[4006,4010,4013,4016,4020,4023,4033,4036,4040,4043,4046,4050,4053,4056,4058],[17,4007,4009],{"id":4008},"benchmark-refinements-unlock-realistic-kernel-optimization-measurement","Benchmark Refinements Unlock Realistic Kernel Optimization Measurement",[22,4011,4012],{},"METR addressed KernelBench's limitations—naive PyTorch baselines, outdated tasks from mid-2010s architectures, and noisy measurements—by filtering 45 low-quality tasks and adding Level 5 with 14 frontier workloads (DeepSeek-V3, Llama 3, Hunyuan Video, State Space Models like Mamba2). Filters targeted issues like low signal-to-noise outputs (-0.01 to 0.01 range), uniform tensors, constant functions (e.g., mean(softmax(x))), and seed-independent computations. They modified tasks with randomized weights or inputs to prevent caching cheats and switched to triton.testing.do_bench for reliable timings. Excluded Level 4 due to HuggingFace dependencies requiring codebase parsing. Result: 225 tasks across Levels 1-5, all single-H100 inference, emphasizing fusions like attention and convolutions in higher levels.",[22,4014,4015],{},"This setup better mirrors small research teams' needs, where naive PyTorch is common, but highlights gaps like no multi-GPU comms, fixed shapes, or training backprop. \"KernelBench initial implementations are naive PyTorch, rather than highly optimized CUDA. This makes KernelBench much easier, more representative of small research groups, and not representative of large scale applications.\"",[17,4017,4019],{"id":4018},"kernelagents-parallel-search-drives-cost-effective-speedups","KernelAgent's Parallel Search Drives Cost-Effective Speedups",[22,4021,4022],{},"KernelAgent uses parallel tree search: 8 initial attempts (PyTorch\u002FTriton\u002FCUDA), resampling from best-so-far (weighted by speedup) for 300 total attempts\u002Fproblem (40 for costly o1). Includes Triton\u002FCUDA docs, ground-truth verification. Best-of-k across GPT-4o, Claude 3.5 Sonnet, o1 yields 1.81x geometric mean speedup vs. original KernelBench's 1.05x—15x better—attributed to scaffolding, prompt tuning, $20\u002Ftask spend (vs. \u003C$1 originally). o3-mini-high hits 1.81x alone; best across all models: 2.01x, doubling in 6 months.",[22,4024,4025,4026,4032],{},"Per-cost\u002Fper-attempt: o3-mini excels (power-law gains to 300 attempts), breakeven at 27 H100-hours\u002Fworkload. Kernels: 80% Triton\u002FCUDA (outperform PyTorch), Level 5 averages 500 LOC. Fine-tuning GPT-4o on 1200 solutions nearly matches o3-mini on Level 5 (except DeepSeek MOE). Released best solutions: ",[4027,4028,4029],"a",{"href":4029,"rel":4030},"https:\u002F\u002Fgithub.com\u002FMETR\u002FKernelBenchFiltered",[4031],"nofollow",".",[22,4034,4035],{},"\"Using our KernelAgent, o3-mini-high sped up code by 1.81x, and taking the best of all models per problem using KernelAgent achieved 2.01x speedup, representing a large increase from models released only 3 months earlier.\"",[17,4037,4039],{"id":4038},"tradeoffs-strong-on-niche-tasks-far-from-frontier-expertise","Tradeoffs: Strong on Niche Tasks, Far from Frontier Expertise",[22,4041,4042],{},"Agents succeed on 69-95% tasks (>2% speedup), 93% >5% with best-of-all, peaks at 30x. But vs. humans\u002Ffrontier labs: 4 engineer-weeks vs. 5 engineer-years\u002Fmodel; agents can't adapt FlashAttention-2 or match expert novelty (token limits, no context factoring). Torch.compile wrappers lag (best-of-k flags \u003C1.81x). Economic: Models beat humans for \u003C$500 niches (hundreds compute dollars), not billions-scale.",[22,4044,4045],{},"Limitations persist: no human baselines, inference-only, 0.01 tolerance (vs. end-to-end stability), flawed tasks remain. Original KernelBench elicited fraction of capabilities sans scaffolding. \"Our results do not imply that current LM agents can automate kernel engineering... kernels produced by our agents are never as novel and sophisticated as the best open source kernels produced by top experts.\"",[17,4047,4049],{"id":4048},"broader-implications-for-ai-rd-automation-risks","Broader Implications for AI R&D Automation Risks",[22,4051,4052],{},"1.81-2.01x speedups show agents automate kernel bottlenecks (hundreds millions $\u002Fyear savings), accelerating non-frontier ML (open-source research). Withheld agent code due to proliferation; sharing emphasizes evaluation rigor for safety policy. Capabilities advance fast; proper elicitation critical. \"We believe our results highlight some challenges of doing evaluations, especially the importance of proper capability elicitation, commensurate to the economic value that models can actually provide.\"",[22,4054,4055],{},"\"Model written kernels could fill the underserved niche of accelerating machine learning projects that use only hundreds of dollars of compute.\"",[17,4057,3842],{"id":3841},[3784,4059,4060,4063,4066,4069,4072,4075,4078,4081,4084],{},[3787,4061,4062],{},"Filter benchmarks ruthlessly: Remove low-SNR, cheat-prone tasks (e.g., constants, uniform outputs) to isolate real optimization signal.",[3787,4064,4065],{},"Invest in scaffolding: Parallel tree search + high compute ($20\u002Ftask) unlocks 15x better elicitation than zero-shot.",[3787,4067,4068],{},"Scale attempts power-law: o3-mini gains to 300+; breakeven at 27 H100-hours for PyTorch models.",[3787,4070,4071],{},"Prioritize Triton\u002FCUDA: Agents favor them (80%), outperforming PyTorch for complex fusions.",[3787,4073,4074],{},"Benchmark small-team realities: Naive PyTorch + single GPU reveals niche where AI > humans economically.",[3787,4076,4077],{},"Add frontier tasks: Level 5 (DeepSeek-V3 etc.) stresses agents; fine-tuning closes gaps fast.",[3787,4079,4080],{},"Context matters: 1.81x vs. 1.05x shows eval pitfalls; always compare to baselines like torch.compile.",[3787,4082,4083],{},"Safety via sharing: Measure R&D automation transparently for policy, despite capability risks.",[3787,4085,4086],{},"Humans still win frontiers: Agents lag expert novelty by orders of magnitude in effort\u002Fquality.",{"title":36,"searchDepth":37,"depth":37,"links":4088},[4089,4090,4091,4092,4093],{"id":4008,"depth":37,"text":4009},{"id":4018,"depth":37,"text":4019},{"id":4038,"depth":37,"text":4039},{"id":4048,"depth":37,"text":4049},{"id":3841,"depth":37,"text":3842},[42,131],{"content_references":4096,"triage":4112},[4097,4100,4103,4106,4109],{"type":3950,"title":4098,"url":4099,"context":3955},"DeepSeek-V3","https:\u002F\u002Farxiv.org\u002Fhtml\u002F2412.19437v1",{"type":3711,"title":4101,"url":4102,"context":3714},"KernelBench","https:\u002F\u002Fscalingintelligence.stanford.edu\u002Fblogs\u002Fkernelbench\u002F",{"type":3711,"title":4104,"url":4105,"context":3714},"FlashAttention 2","https:\u002F\u002Fgithub.com\u002FDao-AILab\u002Fflash-attention",{"type":3880,"title":4107,"url":4108,"context":3955},"Thoughts on sharing information about language model","https:\u002F\u002Fwww.alignmentforum.org\u002Fposts\u002FfRSj2W4Fjje8rQWm9\u002Fthoughts-on-sharing-information-about-language-model",{"type":3711,"title":4110,"url":4029,"context":4111},"KernelBenchFiltered","recommended",{"relevance":49,"novelty":50,"quality":50,"actionability":50,"composite":51,"reasoning":4113},"Category: AI Automation. The article provides a detailed analysis of how AI agents can optimize GPU kernels, addressing a specific pain point for developers looking to improve performance in AI applications. It offers actionable insights on using KernelAgent for practical speedups, making it relevant for product builders.","\u002Fsummaries\u002F176b270d6050d162-ai-agents-speed-up-gpu-kernels-1-81x-with-scaffold-summary","2026-04-15 15:30:30",{"title":3998,"description":36},{"loc":4114},"176b270d6050d162","__oneoff__","https:\u002F\u002Fmetr.org\u002Fblog\u002F2025-02-14-measuring-automated-kernel-engineering\u002F","summaries\u002F176b270d6050d162-ai-agents-speed-up-gpu-kernels-1-81x-with-scaffold-summary",[65,66,3727,67],"METR's KernelAgent, using o3-mini and others, achieves 1.81x average speedup on filtered KernelBench tasks via parallel tree search and high test-time compute, costing ~$20\u002Ftask—far below human engineers for small ML projects.",[3727,67],"EfpvZbC0IB4JJA4YtygyC1UVDynNSAkAV5xl9_YPWfs"]