Multiple ChatGPT instances work together to find and exploit security flaws — teams of LLMs tested by UIUC beat single bots and dedicated software
UIUC computer scientists have innovated a system for teams of LLMs to work together to exploit zero-day security vulnerabilities without an explanation of the flaws, a major improvement in the schools ongoing research.
Daniel Kang University Of Illinois Urbana Champaign Illinois Urbana Champaign Hierarchical Planning Task Specific Agents Cutting Edge
Source: tomshardware.com