Profile avatar
stanislavfort.bsky.social
AI + security | Stanford PhD in AI & Cambridge physics | techno-optimism + alignment + progress + growth | 🇺🇸🇨🇿
82 posts 1,858 followers 585 following
Active Commenter
Posts 3 Comments 47

Presenting *Ensemble Everything Everywhere* at NeurIPS AdvML'24 workshop today! 🔥 Come by today at 10.40-12.00 in East Ballroom C to ask me about: 1) 🏰 bio-inspired naturally robust models 2) 🎓 Interpretability & robustness 3) 🖼️ building a generator for free 4) 😵‍💫 attacking GPT-4, Claude & Gemini

submitted 71 days ago • 1 comment

I discovered a fatal flaw in a paper by @floriantramer.bsky.social et al claiming to break our Ensemble Everything Everywhere defense. Due to a coding error they used attacks 20x above the standard 8/255. They confirmed this but the paper is already out & quoted on OpenReview. What should we do now?

submitted 73 days ago • 2 comments

A decade ago, AlphaGo inspired me to leap from black holes to AI. Bittersweet to close my time at DeepMind, but thrilled to start a new chapter focusing directly on AI and security. Find me at NeurIPS this week or DM me here if you'd like to chat!

submitted 76 days ago • 0 comments