← Back to Model Beat
4Research·Jun 10

Cybersecurity researchers aren’t happy about the guardrails on Anthropic’s Fable

Cybersecurity researchers are complaining that Anthropic's new model Fable has guardrails that are too strict for any cybersecurity work.

Covered by 2 sources

Related stories

ResearchInvesting in multi-agent AI safety researchJun 10 · 2 sourcesResearchEconomic Research - AnthropicJun 8ResearchMicrosoft Research's Mirage gives video generation a persistent spatial memory that doesn't forget what's around the cornerJun 14ResearchAnthropic study shows AI needs hours, not weeks, to build exploits from security patchesJun 10