technologyFeb 28, 202443:36pending
Representation Engineering (Activation Hacking) (Practical AI #258)
About this episode
Recently, we briefly mentioned the concept of "Activation Hacking" in the episode with Karan from Nous Research. In this fully connected episode, Chris and Daniel dive into the details of this model control mechanism, also called "representation engineering". Of course, they also take time to discuss the new Sora model from OpenAI.
Get every episode summarized
Each time Changelog Master Feed publishes, we email you a written briefing from the transcript — the topics, who appeared, and any specific claims, with the ad reads skipped.
Email me new episodesFree for 3 shows. No card needed.
No transcript yet
This episode has not been transcribed. Request it and it moves to the front of the queue.
More episodes
More from Changelog Master Feed
Forking Cal.com to closed source (Changelog Interviews #685)
Changelog Master Feed
Sep 3, 20261:54:32pending
Postgres at PlanetScale (Changelog Interviews #684)
Changelog Master Feed
Aug 25, 20261:42:17pending
Canary tokens and digital tripwires (Changelog Interviews #683)
Changelog Master Feed
Jul 21, 20262:06:48pending
From open source hits to OpenAI (Changelog Interviews #682)
Changelog Master Feed
Jun 5, 20261:46:28pending