Record · alignment.anthropic.com
AuditBench: Evaluating Alignment Auditing Techniques on Models with Hidden Behaviors
alignment.anthropic.com · 12 min read
A post on alignment.anthropic.com is cited by 1 distinct blog 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.
1blog citing
| Period | Blogs | Links |
|---|---|---|
| All time | 1 | 3 |
| Last 90 days | 1 | 1 |
| Last 30 days | 0 | 0 |
| Last 7 days | 0 | 0 |
| First cited | 18 May 2026 |
|---|---|
| Latest citation | 31 Jul 2026 |
| Words blogs link it with | 1 |
| External links | 8 |
| Length | 2,597 |
Words blogs link it with
The words blogs link this page with, by how many different blogs use them.
- auditbench1 blog
Cited by 1 blog in 3 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
Redwood Research3 posts
SOTA alignment assessments don’t strongly update us against misalignment
linked as “AuditBench”
Read at redwoodresearch.org (opens in a new tab)31 Jul 2026
2 other posts
The distillation double bind: Distilling misaligned models either transfers misalignment or it doesn't
linked as “AuditBench”
Read at blog.redwoodresearch.org (opens in a new tab)18 Jun 2026
Incriminating misaligned AI models via distillation
linked as “AuditBench”
Read at blog.redwoodresearch.org (opens in a new tab)18 May 2026
Links from this post
Elsewhere on alignment.anthropic.com (3)
Something wrong here? Report a problem