Record
- Authors
- OpenAI
- Year
- 2025
- Title
- Findings from a pilot Anthropic–OpenAI alignment evaluation exercise: OpenAI Safety Tests
- Type
- Web page
- Links
- https://openai.com/index/openai-anthropic-safety-evaluation/
- Our note
- none yet
- Verification
- url-ok: the web address responds (the page itself is not checked).
https://openai.com/index/openai-anthropic-safety-evaluation/: HTTP 200, checked 2026-11-14 - Id
openai-2025-findings-from-pilot-anthropic-openai-alignment
Cited on
- Findings from a Pilot Anthropic—OpenAI Alignment Evaluation Exercise read status: not read
As cited
The pages cite this work in one form.
-
OpenAI. (2025, August 27). Findings from a pilot Anthropic–OpenAI alignment evaluation exercise: OpenAI Safety Tests. https://openai.com/index/openai-anthropic-safety-evaluation/ [introduction and summary read in the Wayback Machine capture 20250827215024; detailed results not read].
BibLaTeX
@online{openai-2025-findings-from-pilot-anthropic-openai-alignment,
author = {{OpenAI}},
title = {{Findings from a pilot Anthropic–OpenAI alignment evaluation exercise: OpenAI Safety Tests}},
date = {2025},
url = {https://openai.com/index/openai-anthropic-safety-evaluation/}
}