New job update! I’m excited to share that I’ve joined the Hoover Institution and the Stanford Intelligent Systems Laboratory (SISL) in the Stanford University School of Engineering as a Research Fellow, starting September 1st.

ICYMI: The 2025 SERI Symposium explored the risks that emerge from the intersection of complex global challenges & policies designed to mitigate them, bringing together leading experts & researchers from across the Bay Area who specialize in a range of global risks www.youtube.com/watch?v=wF20...

In their latest blog post for Stanford AI Lab, CISAC Postdoc @mlamparth.bsky.social and colleague Declan Grabb dive into MENTAT, a clinician-annotated dataset tackling real-world ambiguities in psychiatric decision-making. ai.stanford.edu/blog/mentat/

Thank Stanford AI Lab for featuring our work in a new blog post! We created a dataset that goes beyond medical exam-style questions and studies the impact of patient demographic on clinical decision-making in psychiatric care on fifteen language models ai.stanford.edu/blog/mentat/

The Helpful, Honest, and Harmless (HHH) principle is key for AI alignment, but current interpretations miss contextual nuances. CISAC postdoc @mlamparth.bsky.social & colleagues propose an adaptive framework to prioritize values, balance trade-offs, and enhance AI ethics. arxiv.org/abs/2502.06059

🚨 New paper! Medical AI benchmarks over-simplify real-world clinical practice and build on medical exam-style questions—especially in mental healthcare. We introduce MENTAT, a clinician-annotated dataset tackling real-world ambiguities in psychiatric decision-making. 🧵 Thread:

Now also on arxiv.org/abs/2502.14143 !

Check out our new report on multi-agent security led by Lewis Hammond and the Cooperative AI Foundation! With the deployment of increasingly agentic AI systems across domains, this research area becomes more crucial.

Submitting a benchmark to ICML? Check out our NeurIPS Spotlight paper BetterBench! We outline best practices for benchmark design, implementation & reporting to help shift community norms. Be part of the change! 🙌 + Add your benchmark to our database for visibility: betterbench.stanford.edu

It was fun to contribute to this new dataset evaluating at the frontier of human expert knowledge! Beyond accuracy, the results also demonstrate the necessity for novel uncertainty quantification methods for LMs attempting challenging tasks and decision-making. Check out the paper at: lastexam.ai

Getting rejected with one 10/10 review score and the same reviewer arguing that the other reviewers have unrealistic expectations hits different.🤔 Oh well, time to refine 😁

Want to learn more about safe AI and the challenges of creating it? Check out the public syllabus (slides and recordings) of my course: "CS120 Introduction to AI Safety". The course is designed for people with all backgrounds, including non-technical. #AISafety #ResponsibleAI

As one of the vice chairs of the EU GPAI Code of Practice process, I co-wrote the second draft which just went online – feedback is open until mid-January, please let me know your thoughts, especially on the internal governance section! digital-strategy.ec.europa.eu/en/library/s...

Check out our new op-ed in @statnews.com about mental-health blind spots of chatbots posing risks to users in mental health emergencies with Declan Grabb, M.D.! www.statnews.com/2024/12/19/a...

In case its helpful for junior female academics, a strategy I often use when I suspect I'm getting asked to do service bc I'm female is to Suggest-A-Man. Safest to suggest someone w/roughly same seniority as you. Doesn't hurt to throw in a "They seem to have ideas on [topic of service]." 1/2

A short list of tips for keeping a clean, organized ML codebase for new researchers: eugenevinitsky.com/posts/quick-...

We're excited to join the @bsky.app community. Follow us here for research and insights into international affairs from scholars at Stanford's Freeman Spogli Institute for International Studies.

Check out our poster at #NeurIPS today and chat with us! #5308: BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices 4:30 PM - 7:30 PM West Ballroom A-D

In our latest brief, Stanford scholars present a novel assessment framework for evaluating the quality of AI benchmarks and share best practices for minimum quality assurance. @ankareuel.bsky.social @chansmi.bsky.social @mlamparth.bsky.social hai.stanford.edu/what-makes-g...

I'm seeking a postdoc to work with me and @kenholstein.bsky.social on evaluating AI/ML decision support for human experts: statmodeling.stat.columbia.edu/2024/12/10/p... P.S. I'll be at NeurIPS Thurs-Mon. Happy to talk about this position or related mutual interests! Please repost 🙏

Our new policy brief with @stanfordhai.bsky.social is out! We outline 46 AI benchmark design criteria based on stakeholder interviews and analyze 24 commonly used AI benchmarks. We find significant quality differences leaving gaps for practitioners and policymakers relying on these AI benchmarks.

I’m at #NeurIPS2024 @neuripsconf.bsky.social in Vancouver this week! Hit me up if you’d like to chat about LM decision making, Interpretability, robustness, UQ, or AI safety in general 😁☕️

Wait, are the AnthropicAI people seriously claiming to “unlock a rich theoretical landscape” for AI evaluation by proposing the use of…. error bars? And this secret trove of deep statistical insight starts with “use the Central Limit Theorem”? Befuddling

I'm teaching a grad seminar this winter on Prediction for Decision-making. We'll look at what it means to make good predictions for decision-making from various angles, with a focus on decisions for & about people. Reading list: statmodeling.stat.columbia.edu/2024/12/06/n... Suggestions welcome!

CISAC postdoc @mlamparth.bsky.social presented the paper he coauthored with colleagues, including CISAC's @htrinkunas.bsky.social & Oriana Skylar Mastro, "Humans vs Machine..." at the Harms and Risks of AI in the Military Workshop in Montreal this past week. Read more below⤵️

In a new spotlight paper at @neuripsconf.bsky.social, CISAC postdoc @mlamparth.bsky.social & colleagues identify 46 benchmark design criteria from stakeholder interviews. They analyze 24 AI benchmarks, uncovering key differences & areas for improvement. openreview.net/forum?id=hcO...

Excited to present two papers on LM decision-making at the Harms and Risks of Military AI workshop at Mila today! It's great that the organizers created a space for the timely and crucial interdisciplinary discussions and I'm looking forward to the feedback/questions!

New MIT Tech Review article about our recent NeurIPS spotlight paper on how to measure and improve benchmark quality aspects! Great collaboration with @ankareuel.bsky.social, Amelia Hardy, @chansmi.bsky.social, Malcolm Hardy, and Mykel Kochenderfer. www.technologyreview.com/2024/11/26/1...

Many of the most popular benchmarks for AI models are outdated or poorly designed.

🚨New paper is out and accepted as NeurIPS 2024 Spotlight! Given their importance for model comparisons and policy, we outline 46 benchmark design criteria based on interviews and analyze 24 commonly used benchmarks. We find significant differences and outline areas for improvement.

🚨 NeurIPS 2024 Spotlight Did you know we lack standards for AI benchmarks, despite their role in tracking progress, comparing models, and shaping policy? 🤯 Enter BetterBench–our framework with 46 criteria to assess benchmark quality: betterbench.stanford.edu 1/x