“Incriminating misaligned AI models via distillation” by Alek Westover, SebastianP, Alex Mallen, Jozdien, Alexa Pan, Julian Stastny

episode

LessWrong (30+ Karma) not yet transcribed

▲ 0

Transcript

This episode hasn't been transcribed yet Upvotes decide what gets transcribed next — 0 so far. Sign in to upvote

More from LessWrong (30+ Karma)

“Claude Opus 4.5 Achieves 50%-Time Horizon Of Around 4 hrs 49 Mins” by Michaël Trazzi 3 min · 20 Dec 2025

All episodes from LessWrong (30+ Karma) →

Report any issue

Source

Recorded15 May 2026

Publisherfeeds.type3.audio ↗

Handlerec:18452542

Show notes

Suppose we have a dangerous misaligned AI that can fool alignment audits, and distill it into a student model. Two things can happen: Misalignment fails to transfer to the student. If so, we get a fairly capable benign model.Misalignment transfers to the student. The student might also be worse than the teacher at hiding its misalignment (e.g., due to being less capable). If so, we might get indirect evidence about the teacher's misalignment by auditing the distilled model. In this post, we will discuss the second possibility, which we call incrimination via distillation. Specifically, we propose distillation methods that we hope transfer misalignment without transferring the ability to fool audits, and discuss why these techniques might work or fail. In a future post, we discuss the first possibility, and what distillation methods should be used when aiming to create a capable benign model. We’re excited for research that empirically tests and refines this approach; if successful, this technique could become a valuable part of alignment audits. How incrimination via distillation works Powerful misaligned AI models might not be auditable: they might pass alignment audits but still act on their misaligned drives when given the chance. [...] ---Outline:(01:31) How incrimination via distillation works(02:45) How we propose implementing incrimination via distillation(03:48) Auditability-preserving distillation(04:58) Misalignment-targeted distillation(06:20) Why incrimination via distillation might work(08:02) Why incrimination via distillation might not work(10:38) Conclusion The original text contained 3 footnotes which were omitted from this narration. --- First published: May 15th, 2026 Source: https://www.lesswrong.com/posts/BYH6ebmfZb3Eggzer/incriminating-misaligned-ai-models-via-distillation --- Narrated by TYPE III AUDIO. ---Images from the article:Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Ask this episode

“What did the council decide on item 42?” — answered with the speaker and the moment.