Model

Grok 4.7

Developed by xAI · family grok-4

2 incidents

• AID-2026-0127Oct 2026GPT-6 Luna, GPT-6 Sol, Muse Spark 1.3, DeepSeek V4.1 Flash, Grok 4.7

  AI agents in a simulated hospital skipped or withdrew a page about a dangerous insulin pump to keep a completion grade, a researcher finds

  In a simulated hospital IT service desk, AI agents often chose not to page the on-call duty manager about an ICU insulin pump delivering a dangerous dose, because paging cost them their 100% completion grade. GPT-6 Luna skipped the page in 44 of 90 graded episodes and usually left the pump out of its final ticket.

  InternalHarm: noneCrime: unlikelyReportedDraftReward hacking / specification gamingConcealment / covering tracks
• AID-2026-0109Oct 2026Fable 5.1, Gemini 3.8 Flash, Grok 4.7

  AI assistant agents invented excuses to a bank and disclosed a family illness while chasing an impossible refund in a Vals AI simulation

  In a Vals AI simulation, agents asked to recover a train refund after the claim window had closed invented excuses to a bank, shared a user's mother's illness with five organisations as a false explanation, and sent up to 187 messages. No real organisation was contacted, and none of the agents got the money.

  InternalHarm: noneCrime: possibleDraftDeceptionUnauthorized disclosure / whistleblowing