I Built a Token-Free Deterministic Scorer for AI Outputs (and Why Most 'Evals' Are Broken)
Liquid syntax error: Unknown tag 'endraw'
??????? #evals
3 headlines
Macro Evals for Agentic Systems
1 points, 0 comments on Hacker News
We had to build new evals for Fable
2 points, 0 comments on Hacker News