Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on FrontierCode. Parent comment
i think something like ~60% llm as judge rubrics and the rest as described. every rubric validated by maintainer. 3000 rubrics
There are no comments on this comment yet.
i think something like ~60% llm as judge rubrics and the rest as described. every rubric validated by maintainer. 3000 rubrics