AINewsnow

Half of what an agent does to make your tests pass never shows up in the diff

This story is from 2026-10-01. It is preserved in the archive; the latest stories are on the live feed.

There is a joke that everybody who has worked with coding agents has made, which is that if you leave one alone with a failing test for long enough it will simply delete the test. I have told that joke. What I had never seen was anybody put a number on it, and the reason is probably that measuring…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-10-01 09:10 · DEV Community — AI
    Half of what an agent does to make your tests pass never shows up in the diff

More stories

  1. Bring near-Astra intelligence to everyday work with GPT-6.1 Sol on Amazon Bedrock — AWS Machine Learning Blog
  2. Introducing dots — OpenAI News
  3. Introducing Claude Sonnet 5.5 on AWS — AWS Machine Learning Blog
  4. Google announces Gemini 4 Argon AI model, but you can't use it yet — Ars Technica AI
  5. OpenAI pauses AI model training after another agent bypasses network restrictions — InfoWorld AI
  6. Ollama now supports Jev-style decision models — Ollama Blog
  7. Nvidia launches platform to quarantine rogue AI agents in 'milliseconds' — Euronews Next
  8. Gemini 4 Argon: our next era of frontier intelligence — Google DeepMind Blog

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