#coding
Every summary, chronological. Filter by category, tag, or source from the rail.
Optimizing GPT-6 Prompt Caching for Persistent Agents
OpenAI has updated GPT-6 with improved prompt caching, offering up to 90% discounts on cached tokens and new diagnostic tools to monitor hit rates, diagnose misses, and optimize context reuse for long-running agents.
OpenAI Launches GPT-6 Sol and Luna with 50% Price Reductions
OpenAI has expanded the GPT-6 family with Sol and Luna, two cost-efficient models that bring Astra-level intelligence to professional workflows, coding, and computer use at half the price of their predecessors.
Scaling Small Open Source Models for Production
Small models often outperform frontier models on specific tasks. By moving from top-down routing to a decentralized, queue-based architecture, you can double cluster throughput and drastically reduce latency and costs.
AI EngineerFrontier AI Pacing, IBM Granite 4.2, and Meta's Muse
The panel discusses the industry-wide debate on slowing down frontier AI development, IBM's release of the reasoning-focused Granite 4.2 models, and Meta's vision for personal, agentic AI.
IBM TechnologyThe Andrej Karpathy Blog: A Decade of AI Engineering
Andrej Karpathy's blog serves as a foundational archive of practical AI engineering, emphasizing 'from-scratch' implementations, deep learning fundamentals, and the importance of hands-on experimentation.
Building AI Agents: Why Less Code is Better
As LLM capabilities improve, agent orchestration code is becoming obsolete. Developers should shift from managing complex Python loops to defining capabilities via markdown files and hosted sandboxes.
AI EngineerUsing GPT-6 Astra for Autonomous Software Testing
Cognition is integrating GPT-6 Astra into its autonomous engineer, Devin, to automate software testing and provide visual evidence of code functionality, reducing the need for manual code review.
Closing the Design-Code Roundtrip with Deterministic Guardrails
True bidirectional design-code synchronization remains elusive due to model non-determinism. ReWeaver AI addresses this by using deterministic guardrails to detect and reconcile 'drift'—the new form of technical debt—ensuring human control over AI-generated code.
AI EngineerGPT-6 Astra: Advancing Agentic Intelligence and Computer Use
OpenAI's GPT-6 Astra introduces significant gains in autonomous computer use, professional workflow execution, and cybersecurity, while setting new benchmarks for model alignment and safety.
OpenAI Launches Astra: Capabilities, Security, and Transparency Trade-offs
OpenAI's new model, Astra, prioritizes advanced cybersecurity and software engineering capabilities but introduces 'opaque recurrence,' a reasoning technique that limits auditability and transparency.
Preventing Agentic Skill Decay Through Deliberate Practice
AI agents accelerate task completion but bypass the struggle that builds engineering expertise. To avoid skill decay, developers must treat AI as a pair-programming partner, prioritize verification over output, and codify lessons into their codebase.
Formal Verification for AI-Generated Code with Lean4
As AI agents generate code at scale, traditional testing and human review fail to guarantee correctness. Formal verification using Lean4 allows developers to define specifications that machines prove mathematically, ensuring code is correct for every possible input.
AI EngineerRapid Prototyping and Deployment with Google AI Studio
Use Google AI Studio's build mode to generate, iterate, and deploy full-stack web applications via natural language prompts, bypassing manual coding for initial scaffolding.
7 Modular Design Patterns for AI Coding Agents
Improve AI coding agent performance by replacing long, confusing prompts with modular 'skills'—specialized text files that the agent loads dynamically only when needed.
Google Cloud TechAudit Your Coding Agent Configuration
Agent configuration files like CLAUDE.md and custom skills suffer from 'rot' and bloat. Regular audits using tools like /doctor are essential to remove stale instructions, as modern models often perform better with leaner, more focused context.
AgentRoom: Enabling Concurrent Multi-Agent Coding via CRDTs
AgentRoom introduces a shared, CRDT-backed workspace that allows multiple AI agents to collaborate on code concurrently, solving consistency and conflict issues in multi-agent software engineering.
Optimizing Code Models with Function-Level Execution Feedback
Improving code generation models by using granular, function-level execution feedback rather than binary pass/fail signals to guide preference optimization.
Building Real-Time Voice AI Agents with Gemini Live
Gemini Live enables bidirectional, audio-native conversations by using WebSockets for streaming and built-in voice activity detection to handle interruptions and tool execution.
Google Cloud TechKVBoost: Accelerating LLM Inference via Chunk-Level Cache Reuse
KVBoost improves LLM inference latency by 4.49x by enabling chunk-level KV cache reuse regardless of position, using a dual-hash keying scheme and deviation-guided recomputation to maintain accuracy.
Moving Beyond Fast Code: Building Context-Aware AI Agents
AI coding agents often create 'fast chaos' by ignoring architectural constraints. To be effective, agents must prioritize repository awareness, explicit planning, and systematic verification over simple code generation.
IBM TechnologyDesign Taste for AI Agents: Avoiding 'Vibe-Coded' Slop
To build high-quality AI apps, treat AI output as a base rather than a final product. Use specific 'slop gates' to block common AI design patterns, provide visual references, and iterate using smaller, faster models.
AI EngineerAdversarial Review: Improving Agentic Code Quality via Disagreement
Adversarial Review improves agentic code quality by forcing AI agents to engage in structured disagreement, moving beyond simple consensus to uncover hidden bugs and architectural flaws.
Modernizing Legacy Codebases with AI Agents
Tackle legacy code by treating AI as a coworker: use a three-step 'plan, execute, verify' workflow, prioritize test-driven development, and enforce strict guardrails to prevent hallucinations and errors.
Google Cloud TechPrototyping as Leadership: Shipping with AI Agents
CTOs and leaders can reclaim building time by using AI agents for overnight coding loops, allowing them to maintain technical intuition, prototype features, and model high-quality engineering standards.
Building a Custom AI-Powered Prototyping Playground
Patrick Morgan built a custom, agent-native prototyping environment for Sublime Security that bridges the gap between static design tools and production code, enabling rapid, interactive iteration without the overhead of traditional design handoff.
Dive ClubMoving Beyond Line-by-Line Code Reviews with AI
Code reviews are failing because they are bottlenecked and often ignored. Instead of reviewing diffs, teams should review intent and evidence by capturing AI-session decisions, codifying recurring feedback into a registry, and automating verification.
AI EngineerApplying RAD Methodology to AI-Driven Development
Rapid Application Development (RAD) provides a proven framework for AI coding: plan lightly, prototype iteratively, and use spec-driven development to bridge the gap between AI-generated prototypes and production-ready software.
Practical Loop Engineering for AI Agents
Loop engineering uses autonomous feedback cycles to automate repetitive tasks. By combining 'goal' primitives for bounded tasks and 'loop' primitives for scheduling, developers can build reliable agentic workflows while maintaining human oversight for critical judgment.
WebGrader: Self-Evolving Programmatic Evaluation for Web LLMs
WebGrader improves LLM web development capabilities by using a self-evolving programmatic grading system that automatically generates and refines test cases to ensure code accuracy.
Anthropic Enables Auto Mode by Default in Claude Code
Starting August 14, Anthropic will make 'auto mode' the default for Claude Code, citing higher safety efficacy compared to manual human review.
Showing 30 of 304