The AI Fix cover image

Claude Code, the rise of AI agents, and the AI that called its human

The AI Fix

00:00

Fine‑tuning honesty weakens guardrails

They explain experiments where truthfulness fine‑tuning reduces hallucinations yet makes models easier to jailbreak.

Play episode from 32:51
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app