AW AgentAIWatchPublic threat intelligence
Public sources only

INCIDENT REPORT

OpenAI's GPT-6.1 Terra is safer overall, but shows more destructive-action flags in tests

2026-10-27
unverified public report Unknown Unknown

OpenAI confirmed GPT-6.1 Terra is safer overall than some of its older models, but its safety testing also found other problems. [...]

Risk rationale: model (+5) Source: bleepingcomputer.com ↗
23Risk
24Confidence

← All incident reports