Generative Red Team is AI Village's hands-on work around assessing generative AI systems and the evaluations used to measure them. The current site content frames the work through event announcements, recaps, and technical posts.
This page keeps the public claims narrow: it links the existing source material and gives visitors a single place to understand the program context without adding unsupported partner, scale, or outcome claims.
Program Threads
GRT history and lessons from the DEF CON 31 recap.
GRT2 context from the DEF CON 32 announcement and event page.
GRT3 framing around evaluations from the DEF CON 33 announcement.
The GRT 3 will run online in about a month with partners. Please sign up here https://auth.aivillage.org/login to recieve an email with more information. In 2023, AI Village organized the...
At DEF CON 31 AI Village hosted the Generative Red Team GRT1 , the world’s largest, public Large Language Model LLM Red Team, in conjunction with other non profit, corporate,...
Generative Red Team History It’s long overdue for a retrospective on the Generative Red Team GRT at AI Village at DEFCON 31. I’ve posted parts of this other places, but...
Sven Cattell, Rumman Chowdhury, Austin Carson • • #generative red team
Largest annual hacker convention to host thousands to find bugs in large language models built by Anthropic, Google, Hugging Face, NVIDIA, OpenAI, and Stability. This event is supported by the...