Record
- Authors
- Wen, J.; Qiu, L.; Benton, J.; Kirchner, J. H.; Leike, J.
- Year
- 2026
- Title
- Automated Weak-to-Strong Researcher
- Published in
- Alignment Science Blog, April 2026
- Type
- Web page
- Links
- https://alignment.anthropic.com/2026/automated-w2s-researcher/
https://github.com/safety-research/automated-w2s-research - Our note
- none yet
- Verification
- url-ok: the web address responds (the page itself is not checked).
https://alignment.anthropic.com/2026/automated-w2s-researcher/: HTTP 200, checked 2026-11-14
https://github.com/safety-research/automated-w2s-research: HTTP 200, checked 2026-11-14 - Id
wen-2026-automated-weak-strong-researcher
Cited on
- Automated Alignment Researchers: Using large language models to scale scalable oversight read status: not stated
- Automated researchers can reliably mitigate alignment failures read status: not stated
As cited
The pages cite this work in 2 forms.
-
Wen, J., Qiu, L., Benton, J., Kirchner, J. H., and Leike, J. (2026). Automated Weak-to-Strong Researcher. Alignment Science Blog, April 2026. https://alignment.anthropic.com/2026/automated-w2s-researcher/
-
Wen, J., Qiu, L., Benton, J., Kirchner, J. H., and Leike, J. (2026). Automated Weak-to-Strong Researcher. Alignment Science Blog, April 2026. https://alignment.anthropic.com/2026/automated-w2s-researcher/ (section numbers in this note refer to this post). Code and data: https://github.com/safety-research/automated-w2s-research
BibLaTeX
@online{wen-2026-automated-weak-strong-researcher,
author = {Wen, J. and Qiu, L. and Benton, J. and Kirchner, J. H. and Leike, J.},
title = {{Automated Weak-to-Strong Researcher}},
organization = {Alignment Science Blog, April 2026},
date = {2026},
url = {https://alignment.anthropic.com/2026/automated-w2s-researcher/}
}