AINewsnow

25 of 26 rules in a 755-line AGENTS.md changed nothing

This story is from 2026-09-30. It is preserved in the archive; the latest stories are on the live feed.

I keep seeing teams treat their AGENTS.md like a config file: write the rules once, assume the agent obeys. So I went looking for anyone who actually measured which of those lines do anything, and the answer is uncomfortable. The cleanest number I found comes out of agents-md-evals , a small eval h…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-09-30 00:15 · DEV Community — AI
    25 of 26 rules in a 755-line AGENTS.md changed nothing

More stories

  1. NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring — NVIDIA Technical Blog
  2. Bring near-Astra intelligence to everyday work with GPT-6.1 Sol on Amazon Bedrock — AWS Machine Learning Blog
  3. The Future Is for Everyone: Muse for Small Business — Meta Newsroom
  4. How we found 24 Android vulnerabilities using our open source AI security agent — GitHub Blog
  5. Introducing Claude Sonnet 5.5 on AWS — AWS Machine Learning Blog
  6. OpenAI launches Dots, its Muse competitor — The Verge AI
  7. OpenAI pauses AI training, launches ‘extensive’ review after multiple rogue agent incidents — Mint AI
  8. Anthropic warns of ‘existential risks to humanity’ in IPO prospectus — Financial Times AI

Get the daily brief of stories like this at 6:30 every morning →