Beth Barnes clarifies METR didn't evaluate alignment of Fable/Mythos 5.2
RyanGreenblatt · x · 2026-11-20
Beth Barnes clarifies (retweeted by Ryan Greenblatt) that METR did not evaluate alignment or communication clarity of Claude Fable 5.2 and Mythos 5.2, despite proximity in Anthropic's announcement suggesting otherwise. An eval screenshot notes Mythos 5.2 produced lengthy, unclear reports on Sunlight and, like Opus 5.5, neglected rigorous comparisons between its preferred solution and alternatives — though this weakness may matter less when the reader is another agent.
More from Models
- Local inference users want 512GB RAM and 1M context, says current boxes fall short — AIFlow_ML · 2026-11-20
- Astra xhigh is surprisingly good at ML engineering, says tester — _Stocko_ · 2026-11-20
- Leaked slide shows OpenAI's unannounced cyber model hitting 77% on ExploitGym benchmark — TheMoonMidas · 2026-11-20
- Tencent Hy4 lands in vLLM day-0: 774B MoE with 49B active, 1M context, 8-GPU FP8 recipe — vllm_project · 2026-11-20
- Google Now Ships Two Models a Week, Six of Top 10 Spots on Artificial Analysis Index — haider1 · 2026-11-20
- Developer Says Gemini Neon Is His Favorite All-Purpose Model for Technical Writing and Slides — BenBlaiszik · 2026-11-20