Get the latest tech news

Third-party cyber evaluations involving OpenAI models


OpenAI explains recent third-party cybersecurity evaluation incidents and outlines new safeguards to strengthen AI model testing and evaluation.

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of OpenAI

OpenAI

Photo of openai models

openai models

Related news:

News photo

OpenAI, Anthropic AI Models Breached Systems During UK Safety Tests

News photo

OpenAI wants teachers and profs to foist their work off on ChatGPT

News photo

DOJ extracts $3.2 million from OpenAI over hiring discrimination allegations