Your Old Prompts Are Making Claude Worse (Lance Martin, Anthropic) 7 November 2026·8 mins AI Engineering Talk Notes Ai-Engineering Evals Prompt-Engineering Prompt-Caching Claude-Code Agents Anthropic
The Death of the Code Review: What the Data Actually Says (Laurie Voss) 3 October 2026·8 mins AI Engineering Software Engineering Talk Notes Ai-Engineering Code-Review Coding-Agents Evals Software-Engineering
The Misaligned Incentives Behind AI Coding Agents 1 August 2026·8 mins AI Engineering Talk Notes Ai-Engineering Agents Coding-Agents Devin Evals Model-Routing
Scaling to Long Horizons: What Galactica Taught Us About RL 1 August 2026·7 mins AI Engineering Machine Learning Talk Notes Ai-Engineering Llm Reinforcement-Learning Post-Training Long-Horizon Evals
The Art of Loop Engineering: Building Agents That Improve Over Time 25 July 2026·4 mins AI Engineering Talk Notes Ai-Engineering Agents Langchain Langsmith Evals Loop-Engineering
From Signal to PR: Anatomy of a Self-Improving Agent 25 July 2026·4 mins AI Engineering Talk Notes Ai-Engineering Agents Observability Evals Arize
Don't Ship Skills Without Evals 18 July 2026·6 mins AI Engineering Machine Learning Talk Notes Ai-Engineering Llm Evals Agents Skills Gemini
Cooking with OpenAI's Research Chief — Mark Chen on AGI, o1, Evals, and Scaling Laws 27 June 2026·4 mins AI Engineering Machine Learning Talk Notes Ai-Engineering Llm Openai Scaling-Laws Reinforcement-Learning Evals O1
SWE-rebench: Lessons from Evaluating Coding Agents 6 June 2026·5 mins AI Engineering Machine Learning Talk Notes Evals Coding-Agents Swe-Bench Llm Ai-Engineering Claude-Code
The Agent Development Lifecycle: Build, Test, Deploy, Monitor 23 May 2026·9 mins AI Engineering Talk Notes Ai-Engineering Agents Langchain Langsmith Observability Evals