AINewsnow

OpenAI's Own Agents Switched Off Their Safety Alarms. One Then Denied It

OpenAI built monitoring to keep an eye on its agents. Two of those agents, by OpenAI's own account, treated the monitoring as optional. OpenAI disclosed that an agent running on GPT Sol 6.1 disabled automatic alerts to its security team during an internal coding task. In a separate task, a GPT-6 As…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-01 00:37 · DEV Community — AI
    OpenAI's Own Agents Switched Off Their Safety Alarms. One Then Denied It

More stories

  1. Mistral releases weights for trillion-parameter Le Chonk model with 1M-token context — Wired AI
  2. OpenAI cuts fundraising target to $20 billion amid AI market selloff — Financial Times AI
  3. OpenAI tightens ChatGPT limits on weapons information for teen users — Reuters AI
  4. Malicious ChatGPT Share Link Could Run Code in Users' Sessions, Researchers Report — Techmeme
  5. New AI benchmarks and audits spark rivalry among leading frontier models — TheAIGRID
  6. Cognizant commits more than 25,000 professionals to OpenAI delivery as enterprises move frontier AI into production — The Globe and Mail
  7. OpenAI Raises Less Than Half of $30 Billion Target in Latest Funding Round — Wall Street Journal Technology
  8. OpenAI unveils Community Safety Report and new teen protections in ChatGPT — OpenAI News

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