PodcastIntel
Sign in Get Started Free
AI Engineer
AI Engineer

Stop Rationing Tokens: Let the Harness Pick the Model — Kimchi by Cast AI

Oct 2, 2026 · 0:18:08
✨ AI Summary
  • Token budgets cripple developer productivity and increase costs.
  • Cast AI uses a harness to select optimal models per task.
  • Measure cost per task and let the harness dynamically choose models.

Guests on This Episode

LG
Laurent Gil
researcher · 1 podcast appearance
›
ZU
Zilvinas Urbonas
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 →