Developer tools1 sources·Published
Reliability audit tool for LLM-as-judge evaluation pipelines
Teams ship evals built on an LLM judge and trust its verdicts, but a judge can be perfectly self-consistent while being systematically wrong. There is no cheap way to test whether a judge actually tracks quality.
Score 721 sources
Competition check
Still openWe searched
llm judge auditjudge bias detectoreval reliability checker
Found · 0 repos · 7731 packages
Little open-source competition so far — the space is still open. Discussion is moderate.
Signal strength
Why this is worth a look — three verifiable signals, not a black-box score.
- Weak
Cross-source
1 independent platforms · 1 related discussions
- Medium
Discussion heat
Discussion heat medium · 122 Hacker News mentions
- Strong
Freshness
5 days ago
Related topics
LLM-as-judgeevalsjudge biasbenchmark reliability
Summaries are AI-generated from public discussions.