Frontier Line and access · Benchmarks evals
OpenAI Sets Principles for Independent AI Assessments
OpenAI published principles and discussed engaging external assessors for frontier-model safety evaluations.
Read the original at openai.comOpens the publisher's site in a new tabAlso covering this
OpenAI to let outsiders evaluate firm’s AI models at earlier phase - The Times of Indiatimesofindia.indiatimes.com, Sep 23OpenAI Recruits External Watchdogs to Police AI Risk | PYMNTS.comopenai.com, Sep 23OpenAI Will Allow Third-Party Groups to Assess AI Model Safety Earlier - Bloombergbloomberg.com, Sep 22