Skip to content
Hacker News front page

Don't ask an LLM for a confidence score

Justin Flick argues that asking an LLM to output a 0–100 confidence score is scientifically invalid. Models can't reliably self-assess; even Anthropic's introspection research calls the capability unstable. Worse, 'confidence' conflates correctness, coherence, and intent fulfillment into one number. Classical ML has calibration methods for probability scores, but an LLM collapsing per-token likelihoods into a verbalized number is a vibe, not a measurement. The post doesn't propose a specific alternative but points to semantic entropy as a better direction.

Why it matters: The author argues that asking an LLM for a 0-to-100 confidence score has no scientific basis, citing Anthropic's introspection research and unpacking what confidence mixes together.

Read the original ↗Export Markdown