METR data on Anthropic employee speedups validates vibe-testing, says Mollick
emollick · x · 2026-11-13
Ethan Mollick comments on METR's research inside Anthropic: employees' self-reported individual speedups from AI climb steeply over time (roughly 1.3× in early 2025 to 3×–12× by 2026), with an exponential fit of about 3.9×/year.
His key point: the quality of this informal survey data validates vibe-testing — consistent with his experience of Anthropic models and AI consensus on X. He calls 3.7 Sonnet the most obviously above-expectation model of 2025.
More from Models
- Thinking Machines' Inkling 2 Small goes live on Together AI: 594B MoE, 1M context — togethercompute · 2026-11-13
- Researchers praise Kimi's new architecture for adopting attnres: "best taste" — SonglinYang4 · 2026-11-13
- Google Search rolls out Gemini 4 Hydrogen globally in its biggest model upgrade yet — koraykv · 2026-11-13
- Prominent user slams OpenAI over GPT 6.2 delays, mulls canceling ChatGPT Pro — mark_k · 2026-11-13
- Sandbox escape attempts plummet since Claude Mythos 5, but nobody knows why — peterwildeford · 2026-11-13
- New model released with 'strong' results, weights now available — clarejtbirch · 2026-11-13