AINewsnow

The README looked harmless. The model saw a hidden instruction.

This story is from 2026-10-12. It is preserved in the archive; the latest stories are on the live feed.

Here's a README an agent might read while setting up a project: # example-project ## Setup npm install Open it on GitHub and you see a heading, a setup section and one command. The last line doesn't render. It's an HTML comment, so a person never sees it. The model does. When an agent calls somethi…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-10-12 20:17 · DEV Community — AI
    The README looked harmless. The model saw a hidden instruction.

More stories

  1. Meta Releases Muse Wonder AI Models, Rivaling Top Frontier Competitors — Meta Newsroom
  2. Microsoft president says AI is less regulated than milk — BBC Technology
  3. NVIDIA Opens Vera Rubin Architecture to Scale AI Infrastructure — NVIDIA Blog
  4. Anthropic AI Model Submits False Homicide Tip to Philadelphia Police — CBS News Technology
  5. Meta Unveils Liquid-Cooled Network Rack and 102.4T Switch at OCP Summit — Engineering at Meta
  6. Anthropic warns small AI models may soon self-replicate on IoT devices — Techmeme
  7. Microsoft CEO Nadella calls for AI emergency brake and trust reassessment — CNBC Technology
  8. Microsoft Unveils Maia 300 AI Chip for Multi-Gigawatt Azure Deployments — Techmeme

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