METR chart: permanent acceleration fits Anthropic's capability curve better (RMSE 1.9 vs 3.9)
scaling01 · x · 2026-11-06
A METR chart shared by scaling01 shows that fitting Anthropic's model capability trajectory (AECI, covering public and internal snapshots from 3 Opus to Opus 4.6) with a "permanent acceleration" hypothesis predicts later models far better (held-out RMSE 1.9) than the one-time jump hypothesis in Anthropic's August Risk Report (3.9), winning in 81% of bootstrap draws. Notably, the chart masks unreleased internal snapshots labeled Mythos Pre-Early, Mythos 5, and Model 2/3/4 Early, extending to October 2026 — suggesting Anthropic's internal capability curve keeps steepening.
More from Models
- Zhipu chief scientist reveals GLM pretraining data roadmap: GLM-5 at 28.5T tokens, 100T next — rickasaurus · 2026-11-06
- Hesamation: OpenAI Models Beat Anthropic's Only at Certain Kinds of Games — Hesamation · 2026-11-06
- Meta's new 'walrus' checkpoint reportedly matches crouton-alpha quality — ChrisGPT · 2026-11-06
- Quick test: Gemini 3.1 Pro knows the answer in its weights, Flash doesn't — giffmana · 2026-11-06
- Ripple-65B flops in single-GPU coding test against Qwen 27B despite SOTA claims — DZhang50 · 2026-11-06
- Ripple-65B open-weight model runs at 7 tok/s locally on a 64GB Mac mini — DZhang50 · 2026-11-06