Using LLM for confidence scoring is a bad idea

Article URL: https://rumple.github.io/blog/2026/10/20/asking-llm-for-confidence.html Comments URL: https://news.ycombinator.com/item?id=50176082 Points: 69 # Comments: 43

Read the full story at Hacker News Front Page ↗

Timeline · 1 report

2026-10-21 04:27 · Hacker News Front Page
Using LLM for confidence scoring is a bad idea

More stories

OpenAI brings frontier models and Codex to Google Cloud — OpenAI News
Recursive Releases Flint, an Open-Weight 40B MoE Local Coding Model for Agents with 2.5B Active Params — MarkTechPost
Ensemble forecasting with IBM Granite time-series models — Hugging Face Blog
Meta to create a new class of shares to fund AI push — The Verge AI
Websites pulled offline worldwide as AI finds critical security flaws — South China Morning Post Tech
NVIDIA Cosmos Opens New Tools to Train, Evaluate and Deploy World Models — NVIDIA Blog
How Companies Are Using NVIDIA DSX to Break the Power Bottleneck — NVIDIA Blog
Solving a 31-year-old grand challenge in mathematics – the KLS conjecture — Microsoft Research Blog

Get the daily brief of stories like this at 6:30 every morning →