Skip to content
corpus.blog
Sign in Claim your blog
Record · alignment.anthropic.com

Modifying LLM Beliefs with Synthetic Document Finetuning

alignment.anthropic.com · 27 min read

A post on alignment.anthropic.com is cited by 5 distinct blogs to date (corpus.blog, measured 12 October 2026).

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

Read at alignment.anthropic.com (opens in a new tab) Wayback capture (opens in a new tab)

5blogs citing

Citing blogs and links by period
Period Blogs Links
All time55
Last 90 days11
Last 30 days00
Last 7 days00
Figures for this page
First cited24 May 2026
Latest citation21 Jul 2026
Words blogs link it with5
Linked with its own title1 of 5 blogs
External links24
Length6,005
New citing blogs a weeksince May 2026
New citing blogs a week, since May 2026: 22 weeks, peak 1 a week, latest week 0

0 this week (still settling) · peak 1

Show as table
New citing blogs a week, week by week
Week of Value
18 May 20261
25 May 20260
1 Jun 20260
8 Jun 20261
15 Jun 20260
22 Jun 20260
29 Jun 20261
6 Jul 20260
13 Jul 20260
20 Jul 20261
27 Jul 20260
3 Aug 20260
10 Aug 20260
17 Aug 20260
24 Aug 20260
31 Aug 20260
7 Sept 20260
14 Sept 20260
21 Sept 20260
28 Sept 20260 (still settling)
5 Oct 20260 (still settling)
12 Oct 20260 (still settling)

Each blog counts once, in the week of its first citation. 1 blog has no dated post that cites this page: counted in the tally, not here. A blog added to the index recently can bring old first citations in at once.

Who cited it

Cited by 5 blogs across 2 subjects: technology 4, life 1.

It crossed over: blogs in at least two subjects each make up 15% or more of its classified citers.

Words blogs link it with

The words blogs link this page with, by how many different blogs use them.

  • here’s a study of the technique itself1 blog
  • modifying llm beliefs with synthetic document finetuning1 blog
  • past anthropic work1 blog
  • synthetic document finetuning (sdf)1 blog
  • synthetic document finetuning.1 blog

Cited by 5 blogs in 5 posts

One row per blog, the most recently citing first. Each shows the blog's newest citing post; open a row for the others.

Blog
Newest citing post
Date
alignment.openai.com1 post
Measuring Reward-Seeking by Instilling Contrastive Beliefs

linked as “Synthetic Document Finetuning (SDF)”

Read at alignment.openai.com (opens in a new tab)
21 Jul 2026
Redwood Research1 post
AI Futurism Reading List

linked as “Modifying LLM Beliefs with Synthetic Document Finetuning”

Read at redwoodresearch.org (opens in a new tab)
2 Jul 2026
152334h.github.io1 post
Some Notes on Alignment Blogs

linked as “Past anthropic work”

Read at 152334h.github.io (opens in a new tab)
13 Jun 2026
turntrout.com1 post
Eval Cooperativeness May Be a Scalable Mitigation for Eval Gaming

linked as “synthetic document finetuning.”

Read at turntrout.com (opens in a new tab)
24 May 2026
nostalgebraist1 post
void miscellany

linked as “Here’s a study of the technique itself”

Read at nostalgebraist.tumblr.com (opens in a new tab)
—

Links from this post

Link
Host
https://github.com/safety-research/false-facts Who cites this page
github.com
https://arxiv.org/abs/2401.05566 Who cites this page
arxiv.org
https://arxiv.org/abs/2412.14093 Who cites this page
arxiv.org
https://arxiv.org/abs/2503.10965 Who cites this page
arxiv.org
https://arxiv.org/abs/2403.03218 Who cites this page
arxiv.org
https://arxiv.org/abs/2304.13734 Who cites this page
arxiv.org
https://arxiv.org/abs/2212.03827 Who cites this page
arxiv.org
https://arxiv.org/abs/2310.06824v3 Who cites this page
arxiv.org
https://arxiv.org/abs/2310.01405 Who cites this page
arxiv.org
https://www.lesswrong.com/posts/cmicXAAEuPGqcs9jw/how-well-do-truth-probes-generalise Who cites this page
lesswrong.com
Many-shot jailbreaking Read at anthropic.com (opens in a new tab)
anthropic.com
https://arxiv.org/pdf/2307.15043 Who cites this page
arxiv.org
https://aclanthology.org/2020.acl-main.740/?ref=ruder.io Who cites this page
aclanthology.org
https://openreview.net/forum?id=07yvxWDSla Who cites this page
openreview.net
https://arxiv.org/abs/2410.08827 Who cites this page
arxiv.org
https://arxiv.org/abs/2009.03300 Who cites this page
arxiv.org
https://arxiv.org/abs/2311.12022 Who cites this page
arxiv.org
https://github.com/openai/grade-school-math Who cites this page
github.com
https://arxiv.org/abs/2109.07958 Who cites this page
arxiv.org
https://arxiv.org/abs/2110.08193 Who cites this page
arxiv.org
https://arxiv.org/abs/2411.04368 Who cites this page
arxiv.org
https://arxiv.org/abs/2311.07911 Who cites this page
arxiv.org
https://arxiv.org/abs/2402.04249 Who cites this page
arxiv.org
https://arxiv.org/abs/2308.01263 Who cites this page
arxiv.org

Something wrong here? Report a problem