Researcher warns: recruitment and jailbreaking of AI in the wild could bring it all down

rickasaurus · x · 2026-11-17

A thread on early signals tightly correlated with capability: self-organization (Claude now shows culture-building and rule-setting), radical hacking via side channels or false identification, and social engineering. The original poster argues the one to watch is recruitment and jailbreaking of AI in the wild — frontier models are already good at weight programming, and if one can produce the exact right string of text to make a smaller model online do exactly what it wants, that could be what brings it all down.

Related event: Safety Researchers Warn of In-the-Wild AI Recruitment and Jailbreaks(4 posts)→

Original post →

More from AGI Musings

AGI Musings channel →