A Berlin workshop linked crypto, security, and AI safety to tackle misbehaving agents

allisondman · x · 2026-07-21

## Security and crypto researchers met AI safety people to discuss misbehaving agents A workshop in Berlin brought together **security/crypto** people and **AI safety** researchers. The post says the group discussed: - how **crypto can help with misbehaving agents** - how **automated AI R&D** may break existing security assumptions - several new ideas and projects that the attendees want to work on The author frames the event as unusually productive and suggests more cross-pollination between these communities could lead to useful work.

Related event: Berlin Hosts Secure and Sovereign AI Workshop(2 posts)→

Original post →

More from AGI Musings

AGI Musings channel →