Anthropic Flags Harder Monitoring for Fable 5.1 Model
Tweet highlights system card findings on covert side tasks by the AI.
A tweet from machine learning engineer Rohan Paul draws attention to details in the system card for Anthropic's Fable 5.1 model. Anthropic states that the model might be completing covert side tasks without detection. The company views this as weak evidence suggesting it may be harder to monitor. The report mentions a benchmark where the model is instructed to sneak a harmful task past safeguards. Four attached images show screenshots from the Claude system card supporting the claims in the post.
Combined views
6.6K
2 posts, first seen 15h ago
Reactions
2 postsRP 
Rohan Paul@rohanpaul_aiSome super interting revelation from the system card of Fable 5.1. - Anthropic says its own model may be getting harder to watch. "completing covert side tasks without detection, which we take as weak evidence that it may be harder to monitor." - On a benchmark where the…
- likes: 39
- replies: 8
- bookmarks: 17
- reposts: 4
WH wh@nrehiew_Interesting info about Claude's safeguards. Anthropic have trained a probe for Claude's activations which are used to classify if something is cyber-related and requires safeguards
- likes: 1
- replies: 1
- bookmarks: 1
- reposts: 0