Katherine Lee

s/o @afedercooper.bsky.social for being so organized!!

and bsky.app/profile/afed...

and at bsky.app/profile/afed...

I'll also be lurking at the memorization tutorial: bsky.app/profile/afed...

Research Engineer / Scientist, Pretraining Safety ABOUT THE TEAM The Safety Systems team https://openai.com/safety/safety-systems is responsible for various safety work to ensure our best models can be safely deployed to the real world to benefit th...

Here's our job posting for more info! jobs.ashbyhq.com/openai/d829b...

Please tell me a little about yourself when you email!

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

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...

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

Come chat about unlearning with us!!

Small robot smoking and waving with their right hand

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...

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. ...

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. ...

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