[un]prompted conference to stage three AI security debates on vulns, defenses, jailbreaks
WeldPond · x · 2026-10-16
Weld Pond previews three AI security debates at [un]prompted II's After Hours: Sergej Epp (Zero Day Clock) vs Jeremiah Grossman (WhiteHat Security/Root Evidence) on whether AI noise has moved the needle on cyber risk; Tim Brown (Team8, ex-SolarWinds CISO) vs Gadi Evron (Knostic) on building security programs that defend against agent swarms; and Katie Moussouris (Luta Security) vs Stefano Zanero (Politecnico di Milano) on whether human attackers also get misalignment and escape sandboxes.
Related event: [un]prompted Conference to Host Three AI Security Debates(2 posts)→
More from Safety
- Polymarket prices 28% odds a US state enacts data center moratorium by year-end — Polymarket · 2026-10-16
- Prompt-injection test: general-purpose decision models catch 17/18 attacks, Shieldstral only 6/18 — WolframRvnwlf · 2026-10-16
- Researcher shows WhatsApp chat history can be permanently rewritten by editing the local message DB — cyb3rops · 2026-10-16
- Top mathematician Tsimerman founds MAISI safety institute, with $10M in OpenAI API credits — burny_tech · 2026-10-16
- Security firm decompiles on-chain propAMM to Rust, finds critical bug risking $6.1M — banteg · 2026-10-16
- Claude Code 2.1.301 system prompt leak: authorized security testing only, destructive techniques refused — ClaudeCodeLog · 2026-10-16