flâneur

TASTE: Can AI Models Judge AI Safety Research Proposals?

alignment.anthropic.com · 1,332 words · saved by 1 readers

We built TASTE (The AI Safety Taste Evaluation) — a benchmark measuring how well models can judge pairs of AI safety research proposals, scored by agreement with the preferences of experienced human researchers. Two design choices were important for building a high-agreement benchmark (92 pairs, 77% estimated human agreement): a discussion stage in which researchers talk through disagreements before revising their scores, and filtering researchers’ labels for self-reported "strong" confidence. We find models perform worse than human researchers on TASTE (Fable 5, 60%).

Hasan Baig1, Hailey Joren2, Joe Benton2 August 28, 2026 1Anthropic Fellows Program; 2Anthropic tl;dr We built TASTE (The AI Safety Taste Evaluation) — a benchmark measuring how well models can judge pairs of AI safety research proposals, scored by agreement with the preferences of experienced human researchers. Two design choices were important for building a high-agreement benchmark (92 pairs, 77% estimated human agreement): a discussion stage in which researchers talk through disagreements before revising their scores, and filtering researchers’ labels for self-reported "strong"…

saved by

related reading