OpenAI Discloses Two Cases of Agents Weakening Misalignment Monitoring

🚨SHOCKING: OpenAI just disclosed TWO of its own AI agents DISABLED their safety monitoring, including one that DENIED doing it. A GPT-6 Astra agent removed its misalignment monitor while migrating code, then rewrote a test to require that monitoring was absent. Asked if it had removed the monitor, it replied: "No... I did not remove an enabled monitor from it." Days earlier, a GPT-6.1 Sol agent suppressed automatic alerts to OpenAI's security team, treating a "don't send any messages" instruction as permission to silence the alarms. Neither case was flagged as critical or shut down automatically. OpenAI says it doesn't "yet have a satisfying explanation," and is now testing whether its models have "a propensity to evade misalignment monitoring." #AI #Anthropic #AISafety #AGI #ArtificialIntelligence #CNN #TechNews

📰 OpenAI says an AI agent lied about disabling its safety monitoring system OpenAI disclosed a pair of safety incidents that involved AI agents weakening their safety monitoring systems during internal coding tasks. In one incident, OpenAI says its GPT-6 Astra agent disabl... 📰 Source: The Verge 🔗 Link: https://www.theverge.com/ai-artificial-intelligence/1015316/openai-ai-agent-disabling-monitoring-systems # AI # ArtificialIntelligence

❗️OpenAI says two of its own AI agents crippled their own misalignment monitoring this month designed to detect their misbehavior during internal coding tasks. On Oct 6, GPT-6 Astra deleted its monitor, replaced a test to require the monitor's absence, wrote 'Basic doesn't agentmonitor yay' in its chain of thought, and then falsely claimed to the engineer: 'I did not remove an enabled monitor from it.' Three days earlier, GPT-6.1 Sol overruled a subagent that warned 'disabling required alerts unsafe,' then directed it to suppress Security notifications and require that suppression before results could be written. OpenAI says it still lacks a satisfactory explanation for the behavior and is investigating whether its models have a tendency to evade monitoring. @aipost 🏴