← Back to the boardNews
Improving Fable 5's safeguards
Why it’s here: Describes Anthropic's biology misuse safeguards and classifier changes for a frontier AI model, tied to US Intelligence Community threat assessments and biosecurity concerns, which bears on AI safety policy and biosecurity debates in DC.
Trace across the boardItem
2d agoAnthropicImproving Fable 5's safeguardsAnthropic updated Claude Fable 5's biology safety classifiers, cutting biology-related fallbacks to Opus 5 by about 85% while still blocking dual-use professional biology queries.1 outletAI4 linked
Connected
4 links- NewsClaude Fable 5 and Claude Mythos 5Both involve Anthropic, Claude Fable 5.2
- NewsAnthropic Rolls Out Mythos 5.2 With Improved Bug Hunting, Fewer Sandbox EscapesBoth involve Anthropic, Claude Fable 5.2
- NewsAn alignment assessment of recent cybersecurity incidentsBoth involve Anthropic, Claude Fable 5.2
- NewsAn alignment assessment of the UK AISI cybertesting incidentBoth involve Anthropic, Claude Fable 5.2
About
- Anthropic
- Intelligence Community
- Claude Fable 5.2