[un]prompted II AI security conference unveils agenda: 81 sessions over 3 days in SF
WeldPond · x · 2026-10-16
The [un]prompted II AI security practitioner conference (Oct 27-29, San Francisco) has published its full agenda: 3 days, 81 sessions, 4 villages, workshops and two social events, with online attendance available. Highlights include Google DeepMind distinguished research scientist Elie Bursztein presenting Capsem, an open-source Rust co-designed hardware sandbox for taming AI agents granted data, network and code-execution access amid prompt injection and rogue-agent risks, plus Caleb Sima and Alec Eckmann on dispatches from an agent swarm gone wrong. Evening events include an AI Hacker Jeopardy.
More from Companies & People
- AI billboards take to the LA skies as startup hires plane to tow ad banner — TarlonKhoubyari · 2026-10-16
- SUNY Albany to offer Topological Deep Learning course, from Perceptrons to WL test — burny_tech · 2026-10-16
- Palantir opens third year of merit-only Meritocracy Fellowship applications — eliano · 2026-10-16
- Why hiring 'technical people who can create content' is so hard, from a Cerebras dev — charles_irl · 2026-10-16
- Sentry to host System Update panel on agentic coding with OpenAI, Linear, DoorDash leaders — zeeg · 2026-10-16
- Anthropic gives METR employee-level access, waives right to block its risk assessments — TechCrunch AI · 2026-10-16