Mike Vaiana

Karma: 556

Mistral Large 2 (123B) seems to exhibit alignment faking

Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Cameron Berg, Judd Rosenblatt, Mike Vaiana and AE Studio

Mar 27, 2025, 3:39 PM

80 points

4 comments13 min readLW link

Reducing LLM deception at scale with self-other overlap fine-tuning

Marc Carauleanu, Diogo de Lucena, Gunnar_Zarncke, Judd Rosenblatt, Cameron Berg, Mike Vaiana and AE Studio

Mar 13, 2025, 7:09 PM

155 points

41 comments6 min readLW link

Self-prediction acts as an emergent regularizer

Cameron Berg, Judd Rosenblatt, Mike Vaiana, Diogo de Lucena, florin_pop and AE Studio

Oct 23, 2024, 10:27 PM

91 points

9 comments4 min readLW link

Self-Other Overlap: A Neglected Approach to AI Alignment

Marc Carauleanu, Mike Vaiana, Judd Rosenblatt, Diogo de Lucena, Cameron Berg and AE Studio

Jul 30, 2024, 4:22 PM

222 points

51 comments12 min readLW link

Video Intro to Guaranteed Safe AI

Mike Vaiana, Diogo de Lucena and AE Studio

Jul 11, 2024, 5:53 PM

27 points

0 comments1 min readLW link

(youtu.be)

DIY RLHF: A simple implementation for hands on experience

Mike Vaiana and AE Studio

Jul 10, 2024, 12:07 PM

28 points

0 comments6 min readLW link