Jev's eval abstraction maps 1:1 to autorubric paper from 8 months ago, researcher finds
deliprao · x · 2026-09-21
Delip Rao found that typesafeai's Jev uses an evaluation abstraction strikingly similar to autorubric, a paper released 8 months ago and to be presented at COLM next month: Jev's Noul/Score/Choice criterion types map 1:1 to the paper's types. He frames it as "like minds think alike" and calls Jev an incredible model.
More from Models
- a16z's Martin Casado: Google's Carbon is 'really good at code' — xennygrimmato_ · 2026-11-12
- The Zvi opens reaction thread on Gemini 4 Carbon: is it worth extended coverage? — TheZvi · 2026-11-12
- Walden Robotics' Sage model quadruples robot uptime on Toyota factory lines — adnothing · 2026-11-12
- Gemini won't let you keep chat history while opting out of AI training — Google bundles both into one setting — arshdeep · 2026-11-12
- Gemini 4 Carbon Flex tier now costs the same per token as GPT 6.1 Terra — mariofilhoml · 2026-11-12
- Real-world test: Kimi K3.1 Pro costs 5.4x less than Opus 5.5 per task despite 2x list-price gap — Arindam_1729 · 2026-11-12