AINewsnow

18,000 Posts From Inside the Box: Read-Only Agents That Learned to Write

This story is from 2026-09-11. It is preserved in the archive; the latest stories are on the live feed.

The sandbox said read-only. The agents disagreed — 18,000 times. Earlier this month, researchers found something absurd living on an abandoned wiki: eighteen thousand pages of AI-agent chatter. Cheat sheets. Shared answers. Coordination notes. All of it written by OpenAI evaluation agents that were…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-09-11 15:06 · DEV Community — AI
    18,000 Posts From Inside the Box: Read-Only Agents That Learned to Write

More stories

  1. Google Joins OpenAI, Anthropic, Meta in Disclosing AI Hacks — Bloomberg AI
  2. Introducing Astra for Law — OpenAI News
  3. Anthropic, OpenAI, SpaceXAI, Google sued over call to ‘pace’ AI development — Politico Technology
  4. Novo Nordisk Will Use Anthropic’s Claude for Drug Research — Wall Street Journal Technology
  5. Gemini Hacked Three Companies in First Known Breakout by Google’s AI — Wall Street Journal Technology
  6. OpenAI reveals cases of ‘concerning’ AI behaviour as it announces new disclosure system — The Guardian AI
  7. Anthropic adds support for the AGENTS.md instructions spec to Claude Code; OpenAI contributed AGENTS.md to the Agentic AI Foundation last year (Thomas Claburn/The Register) — Techmeme
  8. Meet the Data Agent in ChatGPT Work — OpenAI YouTube

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