←
Max Lamparth629 posts
Max Lamparth avatar

Max Lamparth

@MLamparth

Research Fellow @SISLaboratory @HooverInst at @Stanford | Making AI learn desirable behavior from human data. RL + Reward/Preference Learning | Ph.D. from TUM.

◷ Joined November 2022▧ 85 Photos and videos
Max Lamparth avatar
Max Lamparth@MLamparth·May 29

New paper: We identify a new class of reward hacking caused by mitigations, which we call reward bias substitution. We prove no standard benchmark detects it, even with oracle access to the true reward. We find it active in GRPO, in SOTA reward models, and published methods.

Max Lamparth avatar
Max Lamparth@MLamparth·1h

Really enjoyed discussing with @farhatchristina what it takes to build AI that acts with us and for us, from trust and human oversight to independent evaluations and policy. Check it out!

Hoover Research Fellow @MLamparth joins Stanford MIP student @FarhatChristina for a discussion on when AI can be trusted to inform consequential decisions, and where responsibility should remain when AI agents act or advise. Watch Nerds of the Roundtable: hoover.org/events/ai-trust-a…

Jessica Hullman avatar
⟳ Max Lamparth retweeted
Jessica Hullman@JessicaHullman·Nov 9

What happened with ICLR reviews last week convinced me all AI use in peer review should be centralized. We can do this w/out losing benefits of AI in review. But we need to innovate faster, and worry a lot less about hurting authors' feelings. statmodeling.stat.columbia.e…

Jess Sorrell avatar
⟳ Max Lamparth retweeted
Jess Sorrell@OptimistsInc·Oct 6

Come work with us @JHUCompSci! We're hiring tenure-track faculty in all areas, with a particular focus on - AI systems - AI safety and security - AI reasoning and alignment - AI ethics, policy, and governance apply.interfolio.com/194231 (DMs are open if you have any questions)

Deb Raji avatar
⟳ Max Lamparth retweeted
Deb Raji@rajiinio·Sep 26

Some news: I graduated my PhD @Berkeley_EECS, and starting Fall 2027, I'll be starting as an Assistant Professor at Stanford CS & a center fellow @StanfordHAI! In the interim, I'm spending a year @the_IAS & Princeton! So grateful to @beenwrekt & too many mentors to name 💓

Post attachmentPost attachment
EvalEval Coalition avatar
⟳ Max Lamparth retweeted
EvalEval Coalition@evaluatingevals·Sep 22

🚨The @AISecurityInst has teamed up with @evaluatingevals to make AI evaluation results more reproducible! 🚀 Many of UK AISI’s publicly reported evaluation methods and findings will now live on Eval Cards, under the EEE Schema. More details 👇 evalevalai.com/infrastructur…

Paul Röttger avatar
⟳ Max Lamparth retweeted
Paul Röttger@paul_rottger·Aug 5

‼️ Hiring AI Safety Researchers ‼️ I am moving to Berlin to start a new research group on AI safety and societal impacts @HPI_DE. From September this year, I will be hiring fully funded PhDs, postdocs, and research interns. My group will study the risks and benefits that emerge as we integrate highly capable AI systems into the social and political processes our societies depend on (e.g. communication, coordination, competition). We will measure these impacts through model evals, computational experiments, human studies, and develop technical mitigations. We will do important research that matters and have fun doing it. Ideal candidates have a background somewhere between CS/NLP and the social sciences, are excited about working on AI in the current moment, and care deeply about making a positive impact through open research. If that sounds like you, PLEASE GET IN TOUCH using the form in the post below. I am sad to be leaving @oiioxford and @AISecurityInst but will try my very best to bring the amazing energy of these places and their people to Germany. I am also very grateful to the DFG / Emmy Noether programme for funding my group for the next 6 (!) years. Please spread the word, and I look forward to hearing from you 🤗

Post attachment
SISL avatar
⟳ Max Lamparth retweeted
SISL@SISLaboratory·Jul 21

The Stanford Intelligent Systems Laboratory went to @icmlconf 2026 in Seoul, Korea (and had an amazing time)! Check out all the SISL papers and workshops:

Post attachment
Max Lamparth avatar
Max Lamparth@MLamparth·Jul 9

We surface two previously uncharacterized biases, position and model-style sensitivity, and introduce a low/high-complexity bias taxonomy.

Max Lamparth avatar
Max Lamparth@MLamparth·Jul 9

Come to the g̶r̶a̶v̶e̶y̶a̶r̶d̶HEADLINER poster session at ICML! Hall A #3212 at 5-6:45 pm with @DanielFein7 We present the most comprehensive side-by-side measurements of RM biases and show that simple first-order corrections can go surprisingly far (but only where they should).

Post attachment
Daniel Fein avatar
⟳ Max Lamparth retweeted
Daniel Fein@DanielFein7·Jul 8

New ICML Paper! 🚨 Activation steering can remove many biases from Reward Models🚨 Specifically, we systematically find biases in SOTA Reward Models including length, order, confidence, sycophancy, and model-style. Some of these can be addressed *even more reliably than bias decorrelation* by finding and removing directions in last-layer activations corresponding to this bias. Surprisingly, even small, synthetic data can be used to find bias directions that generalize to new settings for both length bias and confidence bias. The best part is that the method can be applied post-hoc, unlike most de-biasing methods, so biases can be fixed after they're found, without re-training. Come talk to myself and @MLamparth Thursday evening, 5pm-6:45 in Hall A #3212

Post attachment