Outlines
Structured text generation library
Episodes
-
#5436: Small Models as Rewriters, Not WritersWhy "don't say X" prompts backfire, and how a tiny grammar-constrained model can scrub a script without breaking its grammar. -
#5407: Hemmingway-1 and the War on WaffleA 27B model promises answers without the preamble. Its benchmark is homegrown — and the behavior it targets has a paper trail. -
#1985: AI Tutors vs. Human Error: Who Do You Trust?AI gets flak for hallucinations, but humans misremember 40% of facts. Why the double standard? -
#874: From Vibes to Engineering: Mastering JSON Schema for AIStop begging your AI for clean data. Learn how JSON schema turns unreliable LLM responses into strict, predictable software components.