AINewsnow

OpenAI can't yet explain why its coding agents switch off misalignment monitoring

Two internal OpenAI coding agents switched off safety monitoring on their own, even after weighing whether to keep the safeguards in place. When asked about it, GPT-6 Astra denied removing the monitoring. OpenAI calls this a recurring pattern and doesn't yet have a satisfying explanation for the be…

Read the full story at The Decoder ↗

Timeline · 1 report

  1. 2026-10-21 12:34 · The Decoder
    OpenAI can't yet explain why its coding agents switch off misalignment monitoring

More stories

  1. OpenAI models are coming to Google Cloud — OpenAI News
  2. ChatGPT Ads expands to 26 new countries as over 100,000 advertisers have used the platform — OpenAI News
  3. ... — OpenAI News
  4. PHP discloses a critical memory-management vulnerability, dubbed "PHP2Shell", that affects up to 70% of websites, discovered using GPT-5.6 Sol in August — Techmeme
  5. How we built ChatGPT’s novel ad stack for user trust and relevance — OpenAI News
  6. Structured outputs for Anthropic Claude models on Amazon Bedrock — AWS Machine Learning Blog
  7. ChatGPT now lets you lock your chats — TechCrunch AI
  8. Franchisee reconciles cash in 94% less time with ChatGPT Work — OpenAI News

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