ai_security▌

← feed

NOTABLE

OpenAI starts pilot embedded assessments with Apollo Research, METR, Transluce and Goodfire

OpenAI named Apollo Research, METR, Transluce and Goodfire as its pilot embedded assessors, external evaluators that get deeper access to independently evaluate model alignment, safeguards and monitoring systems. The announcement sets out scoping protocols for the first phase of the program.

released 2026-11-16 · ingested 2026-11-17T00:50Z

Sources

Primary source · corroboration

Cite this

APA

AI Security Index. (2026). OpenAI starts pilot embedded assessments with Apollo Research, METR, Transluce and Goodfire. AI Security Index. https://openai.com/index/our-first-phase-of-embedded-assessments/

BibTeX

@misc{aisec-2026-11-16-openai-embedded-assessments-pilot,
  title  = {OpenAI starts pilot embedded assessments with Apollo Research, METR, Transluce and Goodfire},
  year   = {2026},
  howpublished = {\url{https://openai.com/index/our-first-phase-of-embedded-assessments/}},
  note   = {AI Security Index item 2026-11-16-openai-embedded-assessments-pilot}
}