AINewsnow

My demo refused 96% of off-topic questions but only 39% of tricky ones. I know because of a test set

Here are two numbers from my document Q&A demo. Ask it about something that is not in the knowledge base at all, and it refuses correctly 96.1% of the time. Ask it a question that sits close to a document but is not answered by it, and it refuses only 39% of the time. If I had tried the demo by han…

Read the full story at DEV Community — Machine Learning ↗

Timeline · 1 report

  1. 2026-11-01 04:43 · DEV Community — Machine Learning
    My demo refused 96% of off-topic questions but only 39% of tricky ones. I know because of a test set

More stories

  1. Anthropic files paperwork for IPO as investors weigh funds and credit outlook — New York Times Technology
  2. Mistral releases weights for trillion-parameter Le Chonk model with 1M-token context — Wired AI
  3. DeepSeek open-sources prototype of always-on autonomous coding agent — Techmeme
  4. Big Tech sheds nearly $900bn as AI spending fears trigger market rout — Financial Times AI
  5. DeepSeek Releases Enhanced Coding Agent to Rival Anthropic's Claude Code — Bloomberg AI
  6. Foxconn hints at new OpenAI tie-up for AI hardware, says no AI bubble — Economic Times Tech
  7. Developers Build Día de los Muertos AI Projects for Hacktoberfest Open-Source Challenge — DEV Community — AI
  8. OpenAI cuts latest funding round target to $20 billion amid tech stock selloff — Financial Times AI

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