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)→
More from AGI Musings
- Hidden Costs in AI Workflows: Rereading and Verification Can Waste Up to 4x Effective Output — Powerful_Creme2224 · 2026-07-21
- Repost argues the AI boom should credit the researchers who made it possible — SchmidhuberAI · 2026-07-21
- AI community is abusing the Jevons Paradox label, David Patterson says — davidpattersonx · 2026-07-21
- LLMs are weirdly good at math and coding, and that still feels surprising — paul_cal · 2026-07-21
- Asimov’s laws are framed as fiction, not real ethics, and a new set of AI rules is proposed — begusgasper · 2026-07-21
- Artificial humanities is emerging as a field, with observatories, books and degree programs — begusgasper · 2026-07-21