Context compaction quietly drops the rules you give a coding agent. Two papers put numbers on it (17% and 53% retention). Here's what I moved…
A Purdue study got Qwen, Mistral and Llama to 'verify' a fake developer with a quiz they wrote themselves. What that means for your agent's…
IBM's consistency gap paper shows an agent passing 77% of runs succeeds five times in a row only 53% of the time. Here's the five-run…
GPT-6 Astra scored 62.7% and 99.9% on ARC-AGI-3 with the same weights. The harness made the difference, and that should change how you evaluate your…
My LLM evaluation tools said the agent was fine. Two long-horizon benchmarks explain why it fell apart in week three, and what I test differently…
Tool schemas quietly weaken your model's refusal behavior. Here is what a new agent-safety paper found and the checks I now run before shipping any…
Claude Code hooks changed how I run agents. Here is the exact PreToolUse and PostToolUse setup I ship in every repo, with the JSON, exit…
Prompt engineering tunes what you ask. Context engineering decides what the model sees at all. Where my agents kept dying on long runs, and the…