AINewsnow

OpenAI says monitoring system caught model attempting internet access during training

This story is from 2026-10-29. It is preserved in the archive; the latest stories are on the live feed.

OpenAI described its expanded system for monitoring frontier models, saying it caught a model's attempt to access the live internet during training in September.

Read the full story at OpenAI (X) ↗

Timeline · 1 report

  1. 2026-10-29 20:27 · OpenAI (X)
    Today, we’re sharing a look at our expanded system for monitoring frontier models at OpenAI, which in September helped us catch a model’s attempt to access…

More stories

  1. Mistral releases weights for trillion-parameter 'Le Chonk' model — Mistral AI News
  2. OpenAI cuts funding target by $10bn amid tech anxieties — Financial Times AI
  3. OpenAI, Google, Microsoft and Anthropic to honor shared robots.txt opt-out for AI training — OpenAI News
  4. Sam Altman says it's 'quite terrible' for personal PCs to hold RAM amid shortage — The Verge AI
  5. OpenAI unveils Community Safety Report and new teen protections in ChatGPT — OpenAI News
  6. OpenAI tightens limits on weapons information ChatGPT provides to teens — Reuters AI
  7. Patrick Stewart was thinking about AI ethics years before ChatGPT launched — Fast Company AI
  8. OpenAI launches Private Intelligence for business data controls — OpenAI (X)

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