Safety
During v3 testing for Fable 5.1 many of our requests were getting rejected due to Anthropic's safety guards misclassifying them as 'reverse …
During v3 testing for Fable 5.1 many of our requests were getting rejected due to Anthropic's safety guards misclassifying them as 'reverse engineering' We were in contact with the Anthropic team the
During v3 testing for Fable 5.1 many of our requests were getting rejected due to Anthropic's safety guards misclassifying them as "reverse engineering" We were in contact with the Anthropic team the whole time and they tried to lift the restrictions in time for launch but ultimately we weren't able to finish testing. We're looking forward to getting this out when we finish it. TBD on when that is. Fable 5.1 from @AnthropicAI on ARC-AGI (Verified): - ARC-AGI-2: 90.0%, 3.12/task - ARC-AGI-1: 97.5%, 1.40/task Across the two benchmarks, Fable 5.1's average cost per task is about 32% lower than Fable 5's, driven by better token efficiency.
Related
- Source: Anthropic plans a safety system this year that still requires enterprises to retain data for 30 days but lets them do so on their own cloud systems (Rachel Metz/Bloomberg)
- fable’s safety guardrails broken within an hour. raise your hand if you are surprised.
- Routing Subspaces: Auditing Evaluation-to-Deployment Mismatch in Fine-Tuned Language Models
- Mitigating Many-shot Jailbreak Attacks with One Single Demonstration
Source: Francois Chollet (X) | 2026-09-01