Pilot to Production · Episode

From 17% to 97.8%: Making a Laptop-Sized AI Actually Reliable

Hosted by Sam & Maya · · 6:10

Play episode6:10

About this episode

A laptop-sized model went from 17% to 97.8% on a real task. Sam and Maya on why the prompt, not the model, was the biggest lever.

In this episode

  • Why the prompt was the problem
  • Fine-tuning as polish, not the fix
  • Making it fast enough to use

Sam and Maya unpack the field note From 17% to 97.8%: Making a Laptop-Sized AI Actually Reliable: the argument, the numbers and the practical moves, in a short, sharp conversation.

Chapters

Jump to any part.