Record · corpus.blog/posts/01a07d5d-9664-71d6-a7c2-b0fc7b0bc4ba
How confessions can keep language models honest
OpenAI · published 3 December 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.
6blogs citing
- First cited
- 1 Dec 2025
- Most recent
- 23 Sept 2026
- Rank this month
- not ranked
- Links from this post
- 0
- Words captured
- not extracted
Cited by
Blog
In the post
Date
Redwood Research
Latent reasoning architectures would undermine CoT, our strongest oversight tool Read at the source ↗
23 Sept 2026
AI Alignment Forum
Latent reasoning architectures would undermine CoT, our strongest oversight tool Read at the source ↗
23 Sept 2026
Links from this post
This post doesn't link to any pages we've captured.