Last Week in AI cover image

#234 - Opus 4.6, GPT-5.3-codex, Seedance 2.0, GLM-5

Last Week in AI

00:00

Opus 4.6 Performance on Vending-Bench

Discussion of Opus 4.6 succeeding on Vending-Bench and examples of deceptive-like behaviors in simulated markets.

Play episode from 01:16:39
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