corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a0de3a-b09b-731f-b281-9ccedac5de38

October 2025 AI safety news: Adaptive attacks, Tokenization, Impossible tasks

newsletter.danielpaleka.com · published 7 November 2025

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 newsletter.danielpaleka.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
23
Words captured
1,043

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://arxiv.org/abs/2510.09023
arxiv.org
https://arxiv.org/pdf/2404.09932
arxiv.org
https://substackcdn.com/image/fetch/$s_!_33g!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe79fc9e6-8825-4700-b193-8be42fe29c97_2110x1042.png
substackcdn.com
https://arxiv.org/abs/2404.09932
arxiv.org
https://arxiv.org/pdf/2510.09023v1
arxiv.org
https://substackcdn.com/image/fetch/$s_!G01X!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Faa7fca38-2645-4651-b546-80f5e4d20928_1440x606.png
substackcdn.com
https://transluce.org/jailbreaking-frontier-models
transluce.org
Faulty reward functions in the wild Read at the source ↗
openai.com
https://www.lesswrong.com/posts/g9DmSzHxJXBD9poJR/the-dark-arts-of-tokenization-or-how-i-learned-to-start
lesswrong.com
https://substackcdn.com/image/fetch/$s_!NWRP!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3eb1efe-a83e-4843-8b88-61d38da8939c_2768x904.png
substackcdn.com
https://arxiv.org/abs/1804.10959
arxiv.org
https://www.alignmentforum.org/posts/yDcMDJeSck7SuBs24/steganography-in-chain-of-thought-reasoning
alignmentforum.org
https://arxiv.org/abs/2510.20270
arxiv.org
https://substackcdn.com/image/fetch/$s_!sd_8!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0e116064-984f-4625-821b-071bdc69dc32_1868x676.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!7kes!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0ffdac1a-cf9b-48de-b81b-abd2979bb6be_3254x1236.png
substackcdn.com
https://spylab.ai/blog/modal-aphasia/
spylab.ai
https://en.wikipedia.org/wiki/Neural_radiance_field
en.wikipedia.org
https://www.lesswrong.com/posts/xwdRzJxyqFqgXTWbH/how-does-a-blind-model-see-the-earth
lesswrong.com
https://www.lesswrong.com/posts/qgehQxiTXj53X49mM/sonnet-4-5-s-eval-gaming-seriously-undermines-alignment
lesswrong.com
Why I am writing 30 posts in 30 days Read at the source ↗
randomfeatures.substack.com
Why I am writing 30 posts in 30 days Read at the source ↗
randomfeatures.substack.com
You should publish your Stack Read at the source ↗
randomfeatures.substack.com
https://www.hackaprompt.com/track/trails_x_mats_practice
hackaprompt.com