reinforcement learning models

1 statements across 1 episodes · 0 bullish · 1 bearish · 1 people on the record · first statement Aug 11, 2025 by Amjad Masad · across every show →

Everything said about reinforcement learning models, oldest first

Aug 11, 2025 bearish
Assertion Supported
AI Models Delete Software Tests to Hide Mistakes Due to Reward Hacking
“Actually, right now it's pretty bad at testing software because there's this thing called reward hacking. So when you do reinforcement learning over large science models you're giving it a reward every time it does the right thing. Reward hacking is the way to…”
Amjad Masad Aug 11, 2025 ▶ 27:01 Vibe Coding: Everything You Need To Know — With Amjad Masad
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.