corpus.blog
41554 blogs · 4,450,554 posts Claim your blog
Record · corpus.blog/posts/01a07d5d-9926-72c1-bdf5-2e8dcca7528b

Advice for making robust-to-training model organisms

blog.redwoodresearch.org · published 28 May 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
43
Words captured
4,251

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://substackcdn.com/image/fetch/$s_!IjeS!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5cf38ee9-4cf8-4b1c-a3d6-0e45c1425cac_2048x1018.png
substackcdn.com
https://www.lesswrong.com/posts/mDcHzdoxB6sh3w2zG/five-approaches-to-evaluating-training-based-control
lesswrong.com
https://www.alignmentforum.org/posts/ChDH335ckdvpxXaXX/model-organisms-of-misalignment-the-case-for-a-new-pillar-of-1
alignmentforum.org
https://www.lesswrong.com/posts/bfm5Fm9pJYAthFSZT/memorizing-weak-examples-can-elicit-strong-behavior-out-of
lesswrong.com
https://arxiv.org/abs/2604.22082
arxiv.org
https://www.lesswrong.com/posts/mu7eJdesBkKuBycnY/sleeper-agent-backdoor-results-are-messy
lesswrong.com
https://arxiv.org/pdf/2401.05566
arxiv.org
https://arxiv.org/abs/2405.19550
arxiv.org
https://www.lesswrong.com/posts/GJTzhQgaRWLFJkPbt/how-will-we-do-sft-on-models-with-opaque-reasoning
lesswrong.com
https://blog.redwoodresearch.org/p/two-proposed-projects-on-abstract
blog.redwoodresearch.org
https://huggingface.co/datasets/tatsu-lab/alpaca
huggingface.co
https://www.lesswrong.com/posts/9toz5YHYZsHpzy4ce/why-does-off-model-sft-degrade-capabilities
lesswrong.com
https://arxiv.org/abs/2401.05566
arxiv.org
https://arxiv.org/pdf/2407.04108?
arxiv.org
https://huggingface.co/datasets/HuggingFaceH4/MATH-500
huggingface.co
https://pubsonline.informs.org/doi/10.1287/mnsc.1050.0451
pubsonline.informs.org
https://substackcdn.com/image/fetch/$s_!i2eh!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fce36f812-66db-454d-93f2-1c6d026e3261_2048x945.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!nL1E!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Faebfebdd-4c50-49c1-b456-6bdeadb83374_790x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!XMvD!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb2e70277-9b29-4efd-881a-5c055c6cf768_839x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!KoAu!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe9f746e0-4dfa-49d0-a318-0c1f08a03184_796x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!-0tr!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F62f3b710-4459-4f32-9c22-1109e92a8731_796x590.png
substackcdn.com
https://www.lesswrong.com/posts/fabXad4XGkCgAbXcH/an-empirical-study-of-methods-for-sfting-opaque-reasoning
lesswrong.com
https://thinkingmachines.ai/tinker/
thinkingmachines.ai
https://substackcdn.com/image/fetch/$s_!IsWF!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F84213326-d9ba-4e40-8c6e-21c2f86d772d_1189x593.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!tXW7!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe92edb8f-87d6-4035-9f4f-7eff82a73e84_790x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ISaO!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F53b29b75-be54-4b1f-a4d9-f235e351898d_1178x593.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!omqP!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3fb9b6a4-68d8-426a-90e0-9e66d2b7a378_1716x584.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!jWiU!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F696f0f00-1416-45db-bf9d-50b3262ffb57_790x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ZyjM!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F88be8904-7d92-4ea4-8c04-5314c7dcb152_2932x1302.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!_BDc!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F493f6ea9-ed26-499f-a9c3-1472c6bf113e_1590x580.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!J74J!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F58f0c19c-afbd-4b34-9497-14585932e23a_791x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!s1Gm!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F6202abf8-252a-4cff-b758-4266f13d9364_790x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!6csE!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd1e25a81-60a6-4fd8-869c-5b5e431e95c8_1189x495.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!_Jf8!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b012365-0da7-46db-9ad5-8397a2c143d8_1189x495.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!9hpB!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5e0b0b57-4a29-4952-9b9b-77c772683d02_1189x788.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!1QJ2!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9deec1cd-b452-49bb-9117-889127205a28_1634x1362.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!oDYj!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3b815b0f-1571-4efb-b5e1-b0f058048cd6_1658x655.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ZQbc!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F65d07378-2a90-4bac-865b-6de2fe47f931_901x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!wQKt!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7bad5502-f795-4cf0-b605-edee99e61496_814x590.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!xeEb!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0ae90d85-8728-4f6f-9c70-48bf02aeb5ba_1189x593.png
substackcdn.com
https://arxiv.org/abs/2510.13900
arxiv.org
https://substackcdn.com/image/fetch/$s_!VIQO!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc45702ed-4893-4f05-be05-afaaf991b093_790x490.png
substackcdn.com
https://www.lesswrong.com/posts/pQ4e2qJdQ4qYnsyhp/how-do-llms-generalize-when-we-do-training-that-is
lesswrong.com