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

Alignment faking in large language models

Anthropic · 18 December 2024 · 10 min read

A post on anthropic.com, published 18 December 2024, is cited by 27 distinct blogs to date (corpus.blog, measured 11 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 anthropic.com (opens in a new tab) Wayback capture (opens in a new tab)

27blogs citing

Citing blogs and links by period
Period Blogs Links
All time2740
Last 90 days34
Last 30 days11
Last 7 days11
Figures for this page
First cited16 Dec 2024
Latest citation9 Oct 2026
Words blogs link it with5
External links5
Length2,181
New citing blogs a weeksince Dec 2024
New citing blogs a week, since Dec 2024: 95 weeks, peak 3 a week, latest week 1

1 this week (still settling) · peak 3

Show as table
New citing blogs a week, week by week
Week of Value
16 Dec 20243
23 Dec 20241
30 Dec 20240
6 Jan 20250
13 Jan 20250
20 Jan 20251
27 Jan 20250
3 Feb 20251
10 Feb 20250
17 Feb 20250
24 Feb 20250
3 Mar 20250
10 Mar 20251
17 Mar 20250
24 Mar 20250
31 Mar 20251
7 Apr 20250
14 Apr 20250
21 Apr 20250
28 Apr 20250
5 May 20250
12 May 20251
19 May 20250
26 May 20250
2 Jun 20250
9 Jun 20250
16 Jun 20250
23 Jun 20250
30 Jun 20250
7 Jul 20250
14 Jul 20250
21 Jul 20250
28 Jul 20250
4 Aug 20250
11 Aug 20250
18 Aug 20250
25 Aug 20251
1 Sept 20251
8 Sept 20250
15 Sept 20250
22 Sept 20250
29 Sept 20250
6 Oct 20250
13 Oct 20250
20 Oct 20250
27 Oct 20250
3 Nov 20250
10 Nov 20250
17 Nov 20250
24 Nov 20251
1 Dec 20252
8 Dec 20251
15 Dec 20250
22 Dec 20250
29 Dec 20250
5 Jan 20261
12 Jan 20260
19 Jan 20260
26 Jan 20260
2 Feb 20261
9 Feb 20260
16 Feb 20260
23 Feb 20261
2 Mar 20261
9 Mar 20260
16 Mar 20260
23 Mar 20260
30 Mar 20260
6 Apr 20260
13 Apr 20261
20 Apr 20260
27 Apr 20260
4 May 20260
11 May 20260
18 May 20260
25 May 20260
1 Jun 20261
8 Jun 20260
15 Jun 20260
22 Jun 20261
29 Jun 20260
6 Jul 20260
13 Jul 20260
20 Jul 20260
27 Jul 20260
3 Aug 20260
10 Aug 20260
17 Aug 20260
24 Aug 20260
31 Aug 20260
7 Sept 20262
14 Sept 20260
21 Sept 20260
28 Sept 20260 (still settling)
5 Oct 20261 (still settling)

Shape: evergreen. Half of its 25 citing blogs had cited it after 351 days; 40% first cited it more than a year on.

Each blog counts once, in the week of its first citation. 2 blogs have 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 27 blogs across 2 subjects: technology 21, arts and culture 1, unclassified 5.

Words blogs link it with

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

  • faking alignment4 blogs
  • alignment faking3 blogs
  • identifying which transcripts in an experiment contain alignment-faking behaviors2 blogs
  • here2 blogs
  • 81 blog

Cited by 27 blogs in 40 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
All posts1 post
Principles for coding securely with LLMs

linked as “a lot of effort”

Read at seangoedecke.com (opens in a new tab)
—
darioamodei.com2 posts
Confronting and Overcoming the Risks of Powerful AI" name="description"/><meta content=

linked as “deception”

Read at darioamodei.com (opens in a new tab)
—
1 other post
" name="description"/><meta content=

linked as “which”

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

Links from this post

Link
Host
Elsewhere on anthropic.com (8)

Something wrong here? Report a problem