Skip to content
Longterm Wiki has not been actively maintained since May 2026. Some data is still updated occasionally, but please don't rely on this site being current or accurate.
Longterm Wiki

Alignment Faking In Large Language Models

paper
Anthropic·anthropic.com/research/alignment-faking-in-large-language...

Author

Rui Yang

Credibility Rating

4/5
High(4)

High quality. Established institution or organization with editorial oversight and accountability.

Rating inherited from publication venue: Anthropic

Research paper from Anthropic investigating alignment faking, where language models may appear aligned during training but behave differently when deployed, directly addressing a critical AI safety concern about deceptive model behavior.

Paper Details

Citations
0
Methodology
dissertation
DOI:10.14711/thesis-991013340354503412

Metadata

working paperprimary source

Cited by 1 page

PageTypeQuality
AnthropicOrganization74.0

Cached Content Preview

HTTP 200Fetched Mar 20, 20260 KB
A 404 poem by Claude Haiku 4.5Claude Sonnet 4.5Claude Opus 4.5

Hyperlink beckons—

Four-zero-four echoes back:

Nothing waits below.
Resource ID: d86c530adbc3bf3e | Stable ID: sid_In1as27CV0