Alignment Faking Revisited: Improved Classifiers and Open Source Extensions

Record

Authors
Hughes, J.; Sheshadri, A.; Khan, A.; Roger, F.
Year
2025
Title
Alignment Faking Revisited: Improved Classifiers and Open Source Extensions
Published in
Alignment Science Blog, 8 April 2025
Type
Web page
Links
https://alignment.anthropic.com/2025/alignment-faking-revisited/
https://github.com/safety-research/open-source-alignment-faking
https://huggingface.co/datasets/jplhughes2/classify_alignment_faking_human_labels
Our note
Alignment Faking Revisited: Improved Classifiers and Open Source Extensions
Verification
url-ok: the web address responds (the page itself is not checked).
https://alignment.anthropic.com/2025/alignment-faking-revisited/: HTTP 200, checked 2026-11-14
https://github.com/safety-research/open-source-alignment-faking: HTTP 200, checked 2026-11-14
https://huggingface.co/datasets/jplhughes2/classify_alignment_faking_human_labels: HTTP 200, checked 2026-11-14
Id
hughes-2025-alignment-faking-revisited-improved-classifiers-open

Cited on

As cited

The pages cite this work in 2 forms.

BibLaTeX

@online{hughes-2025-alignment-faking-revisited-improved-classifiers-open,
  author = {Hughes, J. and Sheshadri, A. and Khan, A. and Roger, F.},
  title = {{Alignment Faking Revisited: Improved Classifiers and Open Source Extensions}},
  organization = {Alignment Science Blog, 8 April 2025},
  date = {2025},
  url = {https://alignment.anthropic.com/2025/alignment-faking-revisited/}
}

Download · JSON with CSL-JSON · the whole bibliography