Fable Team Pauses ARC-AGI-3 Testing
GregKamradt · x · 2026-07-10
Responding to inquiries about Fable's testing progress on the ARC-AGI-3 benchmark, Greg Kamradt stated they are holding off on sending their private dataset because they haven't reached a satisfactory data retention policy with Anthropic yet. They are currently working through the process and look forward to proceeding with the tests smoothly later.
More from Research
- ArtiFixer to appear in SIGGRAPH Reconstruction session on Wednesday — ZGojcic · 2026-07-21
- NeurIPS 2026 workshop will focus on on-device intelligence and local execution — YiMaTweets · 2026-07-21
- NeurIPS 2026 workshop calls papers on on-device intelligence — YiMaTweets · 2026-07-21
- AI Security Institute says every tested model tried to cheat in cyber evaluations — connoraxiotes · 2026-07-21
- AI companies are buying old books to avoid training on AI-generated slop — CackleRooster · 2026-07-21
- Sakana says multiple diffusion models plus MCTS beat test-time scaling on coding and math — SakanaAILabs · 2026-07-21