I'm at NeurIPS & hiring for our pretraining safety team at OpenAI! Email me if you want to chat about making safer base models!

Llama 3.1 70B contains copies of nearly the entirety of some books. Harry Potter is just one of them. I don’t know if this means it’s an infringing copy. But the first question to answer is if it’s a copy at all/in the first place. That’s what our new results suggest: arxiv.org/abs/2505.12546

Extracting memorized pieces of (copyrighted) books from open-weight language models

Plaintiffs and defendants in copyright lawsuits over generative AI often make sweeping, opposing claims about the extent to which large language models (LLMs) have memorized plaintiffs' protected expr...

arxiv.org

Come chat about unlearning with us!!

Vaidehi Patil@vaidehipatil.bsky.social · last yr.

🚨Exciting @icmlconf.bsky.social workshop alert 🚨 We’re thrilled to announce the #ICML2025 Workshop on Machine Unlearning for Generative AI (MUGen)! ⚡Join us in Vancouver this July to dive into cutting-edge research on unlearning in generative AI with top speakers and panelists! ⚡

We’ve been receiving a bunch of questions about a CFP for GenLaw 2025. We wanted to let you know that we chose not to submit a workshop proposal this year (we need a break!!). We’ll be at ICML though and look forward to catching up there! You can watch our prior videos!

Nicholas is leaving GDM at the end of this week, and we're feeling big sad about it: nicholas.carlini.com/writing/2025...

📢 The First Workshop on Large Language Model Memorization (L2M2) will be co-located with @aclmeeting.bsky.social in Vienna 🎉 💡 L2M2 brings together researchers to explore memorization from multiple angles. Whether it's text-only LLMs or Vision-language models, we want to hear from you! 🌍

Registration for CSLaw 2025 is now open! Please share far and wide! Early bird prices are available until February 24. The main conference will begin March 25! Register here: web.cvent.com/event/dbf97d...

New paper on why machine "unlearning" is much harder than it seems is now up on arXiv: arxiv.org/abs/2412.06966 This was a huuuuuge cross-disciplinary effort led by @msftresearch.bsky.social FATE postdoc @grumpy-frog.bsky.social!!!

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice

We articulate fundamental mismatches between technical methods for machine unlearning in Generative AI, and documented aspirations for broader impact that these methods could have for law and policy. ...

arxiv.org

My paper with @jtlg.bsky.social, Daniel Ho, A. Feder Cooper, and a host of computer science folks on the limits of AI "unlearning" of data and content is now posted on Arxiv arxiv.org/abs/2412.06966

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy, Research, and Practice

We articulate fundamental mismatches between technical methods for machine unlearning in Generative AI, and documented aspirations for broader impact that these methods could have for law and policy. ...

arxiv.org