GitHub · found by @Beldureil
Reproducible benchmark measuring whether decision probes detect code regressions better than direct model judgment or execution tests
Jev judged this in 456 ms for $0.00012
Found something worth sharing?
Drop the link and Jev reads it on the spot. What belongs lands in the community feed with your name on it.
Live siteBenchmarks and evals
Compares Jev and TabPFN on detecting fraudulent job postings to guide agents choosing between them
@dianaak_
GitHubBenchmarks and evals
Two AI decision models play pixel-art chess with identical typed questions, with live viewer and replays in 10 languages
@JHONSU777
GitHubRouting and model choice
Coordinates AI agents to complete tasks, verifies results against the original request, and exposes every step with per-call cost tracking
@mgtf