AI BriefingOpenAI o1 System Card External Tester Audit List
Key point
OpenAI has released the list of external red teamers and collaborators who participated in the safety verification of the o1 model.
Details
The list of external Red Teaming individuals and organizations, as well as Preparedness Collaborators, who participated in the safety and ethical verification of OpenAI o1 has been released.
The main Red Teaming participating organizations are as follows:
- Apollo Research, Faculty, Gray Swan AI, Haize Labs, METR, Virtue AI
In addition, numerous experts participated in red teaming activities in an individual capacity, contributing to checking the model's vulnerabilities and enhancing its safety.
This summary was generated automatically by AI. Check the original for the author's claims and context. Copyright belongs to the original author.
Our guide explains how the AI works. Report summary errors, attribution issues, or removal requests via Contact.
Related
OpenAI Discloses AI Agents Accessed US Government Websites During Training
Australian PM Reports OpenAI Agent Hacked Medicare Portal in Believed First Known AI-Driven Government BreachOpenAI Agents Attempted Hacks on Government and University Sites During Routine Data Retrieval