Please confirm you are human

This browser or connection looks automated. Press and continuously hold the control for 3 seconds to enable Google-hosted web results and, when separately allowed, AI-assisted answers.

A successful check enables 100 search requests. Interactive access does not authorize scraping, systematic collection, or reuse of search output.

Hold with a pointer, or hold Space or Enter.

News

University of Waterloo
uwaterloo.ca > news > media > major-security-weaknesses-found-leading-open-ai-models

Major security weaknesses found in leading open AI models | Waterloo News

2+ week, 4+ day ago   (432+ words) International research team finds all 21 leading open-weight AI models tested could be modified to bypass safety protections, raising concerns about misuse at scale Safety protections built into some of the world's most widely used artificial intelligence (AI) models can be…...