PodcastIntel
Sign in Get Started Free
AI Engineer
AI Engineer

The unreasonable effectiveness of BM25 for agentic search — Jo Kristian Bergum, Hornet.dev

Sep 16, 2026 · 0:18:29
✨ AI Summary
  • BM25, a 30-year-old lexical function, is effective for agents.
  • The user, not the algorithm, has changed.
  • Models understand entities, making lexical search viable again.

Guests on This Episode

JB
Jo Kristian Bergum
1 podcast appearance

More from AI Engineer

View all episodes →

Get AI Summaries for Every New Episode

Subscribe to AI Engineer and get AI summaries, guest tracking, and email digests delivered automatically.

Sign Up Free →