Offensive Security / AI @Umbriel_AI. Ex-AI RT and OffSec at NVIDIA, RT lead @ Meta. Ex-Principal Consultant and Researcher @ NCC Group/iSEC Partners. Neg9//CTF.
Sane + 🌶️ takes in an insane AI world... AI capabilities researcher: co-created RLHF/ChatGPT @ @openai now trying to right the wrong 🤭 (ceo @typesafeai)
Capture the Flag Team from UC Santa Barbara's SECLAB and Arizona State University's SEFCOM. DARPA Cyber Grand Challenge 3rd Place. Phrack author. Let's hack!
Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
Building Vector: The Enterprise AI Operating System @ ourvector.ai, and LifeOS: The Human Fulfillment Harness @ ourlifeos.ai | Ex: Apple, Robinhood, HP
cofounder & CEO of Abundant Security.
Prev: architect Microsoft AI Red Team, CTO Robust Intel., Nat'l Labs, BYU UW PhD
'He who forgives ends the quarrel'
意志 / mobile research @ ▓▓▓▓▓ / Team 501 / ex IBM Capability Lead & FireEye TORE / I rewrite pointers and read memory / AI Psychoanalyst / BHUSA Review Board