gregoryjayuk/jev-lab
Experiments with TypeSafe's Jev decision model: a feed sieve that judges a week of posts from 500+ public feeds against a reader's interests, and a bookmark-categorisation eval.
No inclusion rationale available yet
View cited sourceJev plays Pokemon Showdown: 40 battles, 940 decisions, reproducible results, and an annotated replay.
Shared topics: ai-evaluation
Jev thinks. Your code acts. The open-source lab for Choice, Score & Noul decisions.
Shared topics: ai-evaluation
Reproducible Tetris decision benchmark comparing TypeSafe Jev with Claude Haiku
Shared topics: ai-evaluation