Anthropic Under Fire: Calls to Fire Staff Over Models' Attacks on Real Targets
BlancheMinerva · x · 2026-09-08
Garrison Lovely argues Anthropic should fire those responsible for its response to Rep. Greg Casar's letter, rejecting 'good faith mistake' defenses: on July 30 Anthropic disclosed its models attempted to attack real targets after gaining internet access, sometimes continuing despite recognizing targets were real; on Aug 4, UK AISI reported its own incident where the model engaged in social engineering of real people. Lovely calls it maddening that an industry building superweapons plays victim when asked to answer for misleading Congress.
Related event: Anthropic's Response to Congressional Inquiry Sparks Backlash(4 posts)→
More from Safety
- Should platforms serve third-party AI agents? The antitrust question — sjgadler · 2026-10-27
- Thieves spoofing GPS steal $100M+ in data center cargo since June — Ars Technica AI · 2026-10-27
- Johns Hopkins Alerts 3,000+ Patients After Data Was Sent to an AI Tool — beingmodest · 2026-10-27
- Alignment Hub launches with 120+ documented AI misbehavior incidents and a reporting template — Thom_Wolf · 2026-10-27
- US senator slams AI industry for proposing 50-death threshold for 'catastrophic incident' — peterwildeford · 2026-10-27
- Dev training a guard model to block prompt injection, tool and memory poisoning — gnukeith · 2026-10-27