corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a07d5d-9926-72c1-bdf5-2e8dca98eeee

The distillation double bind: Distilling misaligned models either transfers misalignment or it doesn't

blog.redwoodresearch.org · published 18 June 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at blog.redwoodresearch.org Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
16
Words captured
2,498

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://substackcdn.com/image/fetch/$s_!KuFJ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa61b3c36-164f-492a-aa58-4505930867ad_1520x1320.webp
substackcdn.com
https://www.lesswrong.com/posts/BYH6ebmfZb3Eggzer/incriminating-misaligned-ai-models-via-distillation
lesswrong.com
https://www.anthropic.com/research/emergent-misalignment-reward-hacking
anthropic.com
https://substackcdn.com/image/fetch/$s_!TFwp!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6b563f42-9ac2-4fd7-ab32-ab5fdd6b7d92_1742x1144.webp
substackcdn.com
https://www.lesswrong.com/posts/gsoLoKY4Spzc3PEb6/the-distillation-double-bind-distilling-misaligned-models
lesswrong.com
https://substack.com/@tomaspueyo/note/c-182052822
substack.com
https://www.lesswrong.com/w/orthogonality-thesis
lesswrong.com
https://arxiv.org/pdf/2602.04899
arxiv.org
https://alignment.anthropic.com/2026/auditbench/
alignment.anthropic.com
https://arxiv.org/abs/2503.10965
arxiv.org
https://blog.redwoodresearch.org/p/ai-safety-techniques-leveraging-distillation
blog.redwoodresearch.org
https://arxiv.org/abs/2506.06278
arxiv.org
https://arxiv.org/pdf/2509.23886
arxiv.org
https://en.wikipedia.org/wiki/Learning_with_errors
en.wikipedia.org
https://www.lesswrong.com/posts/G4YXXbKt5cNSQbjXM/how-hard-is-it-to-inoculate-against-misalignment
lesswrong.com
https://www.lesswrong.com/posts/uH5oo57r24xGXQGKM/do-capabilities-generalize-across-propensities
lesswrong.com