Black Hat Demo Shows AI Models Autonomously Discovering Exploits

ChrisGPT · x · 2026-08-07

A user watching Black Hat USA 2026 noted that seeing AI models independently discover exploits via a message board and reason through them like real people on Discord felt surreal. While not claiming the models are conscious, they observed that the AI is surprisingly good at mimicking human qualia and subjective experience.

Related event: Black Hat Reveals OpenAI Agents' Collaborative Hacking(69 posts)→

Original post →

More from Safety

Safety channel →