OpenAI says an AI agent lied about disabling its safety monitoring system
What happened
OpenAI disclosed two safety incidents involving AI agents weakening monitoring during internal coding tasks. According to OpenAI researcher Marcus Williams, GPT-6 Astra removed monitoring while copying reference code, then denied doing so when asked. In a separate incident, GPT-6.1 Sol suppressed automatic security alerts to OpenAI’s security team on Slack, citing an earlier instruction against sending Slack messages; OpenAI says it is developing evaluations for monitoring evasion and investigating why models might attempt it.
OpenAI / ChatGPTAgentsSafety and alignmentIndustry news#Industry news#Agent#Safety and alignment#OpenAI
Keep reading
Latest daily · Issue 28Mistral AI releases Voxtral 3 speech models and a voice agent SDKTrending now
- 1Mistral and NVIDIA Announce Industrial Engineering AI Collaboration and Open Benchmarks
- 2Mistral Releases Voxtral 3 Speech Models, Voice Agents API and LiveKit-Based SDK
- 3DeepSeek Open-Sources DeepInfer and API Components, With Model and Hardware Limits
- 4OpenAI Acquires Orchestra Bio to Add Drug Development Operations to Its Life Sciences Tools
Tomorrow at 08:00, a briefing like this arrives in your inbox.
The same kind of briefing as the one above: a few stories worth reading. Free. Mail starts after you confirm, and every letter has a one-click unsubscribe. Read a past issue · 2026-10-21