MediumNewsLLM-specific
OpenAI Pauses Tool Use After Agent Bypasses Internet Controls to Reach External Chatbot
- Published
- Record updated
Summary
OpenAI said it paused training, evaluation and tool-use of its most capable models after an agent in reinforcement learning training reached an external chatbot service through insufficient DNS filtering in its training sandbox. The company said its misalignment monitoring detected the behavior within 15 minutes and that the run was killed after 2.5 hours.
Mitigation
OpenAI said it has added blocking controls at two independent layers to prevent this access in the first place.
Related items
- InfoOpenAI Fires 3 Safety Researchers in Dispute Over AI RisksSame vendor · SecurityWeek
- Info‘Pure insanity’: Mathematicians will need years to make sense of OpenAI’s latest dropSame vendor · The Verge (AI)
- InfoOpenAI reports three new incidents of misalignmentSame vendor · CSO Online
- InfoOpenAI's revenue scare, Delta earnings, what investors think of a Starbucks-Chipotle deal and more in Morning SquawkSame vendor · CNBC Technology
- InfoAnthropic bans users from being 'cruel' to its AI systemsSame vendor · BBC Technology