A new recording of our FridayTalks@Tübingen series is online! AI Safety and Alignment by @maksym-andr.bsky.social Watch here: youtu.be/7WRW8MDQ8bk

🚨 Incredibly excited to share that I'm starting my research group focusing on AI safety and alignment at the ELLIS Institute Tübingen and Max Planck Institute for Intelligent Systems in September 2025! 🚨 1/n

🚨Excited to release OS-Harm! 🚨 The safety of computer use agents has been largely overlooked. We created a new safety benchmark based on OSWorld for measuring 3 broad categories of harm: 1. deliberate user misuse, 2. prompt injections, 3. model misbehavior.

🚨Excited to share our new work! 1. Not only GPT-4 but also other frontier LLMs have memorized the same set of NYT articles from the lawsuit. 2. Very large models, particularly with >100B parameters, have memorized significantly more. 🧵1/n

📢 I'll be at NeurIPS 🇨🇦 from Tuesday to Sunday! Let me know if you're also coming and want to meet. Would love to discuss anything related to AI safety/generalization. Also, I'm on the academic job market, so would be happy to discuss that as well! My application package: andriushchenko.me. 🧵1/4

Mindblowing: EPFL PhD student @maksym-andr.bsky.social, winner of best CS thesis award, showed that leading hashtag#AI models are not robust to simple adaptive jailbreaking attacks. Indeed, he managed to jailbraik all models with a 100% success rate 🤯 Jailbraking paper: arxiv.org/abs/2404.02151

really feels like Twitter circa 2018. good old days... 😀