Prompt2Pwn kicks off in Oakland: hackers target real AI scopes, streamed live
rez0__ · x · 2026-11-19
Prompt2Pwn launches in two days in Oakland (Nov 20–21, 2026), where hackers work on real partner-supplied AI scopes with partner teams on site; talks stream worldwide.
The NahamCon lineup is heavily AI-security focused: Johann Rehberger on becoming an AI hacker and breaking frontier models, Ciarán Cotter on weird ways to hack Gemini, Zenity red teamer Mike Takahashi on a year of exfiltrating data from AI agents, plus talks on LLM-automated device hacking, hacking agents that don't get lost, and supply chain attacks in the AI era.
More from Safety
- Palisade's AI self-replication study under fire: prompt shortcuts and reused credentials skew results — jessi_cata · 2026-11-19
- MIT's test-time adaptation keeps AI text detectors robust against new models — CurieuxExplorer · 2026-11-19
- Anthropic fractures: employees urged unilateral frontier training pause, Dario refused — AndyMasley · 2026-11-19
- Analysts: frontier intelligence vs enterprise readiness gap is widening, big security upgrade cycle coming — BenBajarin · 2026-11-19
- OpenAI wants labs to report recursive self-improvement metrics, but its own definitions drift — tallmetommy · 2026-11-19
- Google report details autonomous AI hacking system, but no confirmed breaches — TruthIsAllYouNeed_ · 2026-11-19