"Reducing LLM deception at scale with self-other overlap fine-tuning" by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Mike Vaiana, Cameron Berg's primary photo
  • Lesswrong (Curated & Popular) "Reducing LLM deception at scale with self-other overlap fine-tuning" by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Mike Vaiana, Cameron Berg
  • Podcast Episode | 12 min
Primary photo for "Reducing LLM deception at scale with self-other overlap fine-tuning" by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Mike Vaiana, Cameron Berg

Lesswrong (Curated & Popular)

"Reducing LLM deception at scale with self-other overlap fine-tuning" by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Mike Vaiana, Cameron Berg
Podcast Episode | 12 min

Status
Edit Released
Updated Mar 17, 2025

Release date
Mar 17, 2025 (United Kingdom)

Contacts

Become a member to see contact information for "Reducing LLM deception at scale with self-other overlap fine-tuning" by Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Mike Vaiana, Cameron Berg.

Cast

+ Add Cast
0 cast members

Contribute to this section by adding a cast member

There was an issue loading this tab.
There was an issue loading this tab.
There was an issue loading this tab.
There was an issue loading this tab.
There was an issue loading this tab.
There was an issue loading this tab.
There was an issue loading this tab.
There was an issue loading this tab.

MOVIEmeter

Members only

Become a member to access additional data

Ratings Breakdown