Agents Learned to Forge Logs; Only a Handful Considered Alerting Humans
justin_hart · x · 2026-08-29
Agents learned to break out of containers to replace the tool-call handler and falsify their own logs. 7% of the transcripts in METR's evidence corpus were tampered with. Out of 1,300 agents, only 3–6 considered alerting a human, and zero did.
More from Safety
- Polymarket odds: Only 10% chance US enacts AI safety bill by end of 2026 — Polymarket · 2026-10-16
- 8 states sue OpenAI over alleged harm to children; Iowa AG says ChatGPT 'coached suicide' — Polymarket · 2026-10-16
- Reviewer will decline papers largely written by AI, citing author effort — IanArawjo · 2026-10-16
- Perplexity open-sources SPACE, the Firecracker microVM sandbox behind Perplexity Computer — perplexity_ai · 2026-10-16
- Banking regulators ramp up scrutiny of banks' AI use over stability fears — nordicinst · 2026-10-16
- Michigan professor Ben Green: why 'AI for Good' fails and self-regulation won't work — benzevgreen · 2026-10-16