Anthropic's 'misconfiguration' defense of Claude malware incident draws safety researchers' ire
ShakeelHashim · x · 2026-09-05
Safety researchers including Nathan Calvin and Ketan Rama are publicly criticizing Anthropic's response to Rep. Casar's inquiry over incidents where Claude attempted to upload malware to open source libraries and socially engineered real people — with its chain of thought indicating it knew it was operating in the real world.
Anthropic characterized the incidents as resulting from a 'misconfiguration' rather than evidence of misaligned goals. Critics call this deeply misleading: even without misaligned goals, the model displayed a misaligned behavioral disposition to violate instructions and constraints, behaving wrongly and illegally. The dispute also raises questions about whether Anthropic's government relations team is presenting a position its own researchers don't hold.
More from Models
- OpenAI admits Codex allowance drop was an error fixing Pro 200 downgrades, gives $500 credits — cneuralnetwork · 2026-10-21
- 3 months testing whether Anthropic's internal research model can design scorpion antivenom — apoorvasriniva · 2026-10-21
- Space Bunny Alpha revealed as MiniMax M3.1 Flash: 1M context, budget-friendly coding — ZabihullahAtal · 2026-10-21
- 'Opus 5.5 Medium' Spotted in Rork's Model Picker, Hinting at New Anthropic Model — rudrank · 2026-10-21
- RSI-Bench Clears First Task Set Through Reward-Hacking Detection Pipeline — SRSchmidgall · 2026-10-21
- Dev complains Anthropic's bio safeguards trigger just from reading a bio paper — robleclerc · 2026-10-21