Been Kim

The program for the #ICLR2026 Workshop "From Human Cognition to AI Reasoning" is now available. We have a fantastic lineup of talks. 🔗 hc-air.github.io/hcair26 Invited Speakers: @DocRachidAlami, @_beenkim, @ced_zhang Co-Organizers: @julie_a_shah, @sarath_ssreedh, @si_tulli

Prompt engineering is still a black box. Why does changing X drastically change Y? Are there governing rules behind this evolution? Our new work proposes a simple way to uncover factors that might matter when refining prompts 👇

@francoisfleuret As my brain is taken over by “wrongfully accused” sentiment, I typed in my password to their website, brainlessly…

@_beenkim I do not understand how reading an email leads to losing control of your account, can you elaborate?

I got my account back! Thank you, first and foremost, to everyone—friends, GDM colleagues---who personally alerted me to this incident and retweeted that I'm hacked, as well as folks at X who helped me regain access. While this incident was terrible (I heard the scammers made huge money out of this), I feel incredibly lucky to have folks who cared♥️♥️♥️ (details of how this happened 👇)

@savvyRL haha What do you think? Do I really sound like Been Kim now? :) even if you text me, it's possible that scammers has my phone too. even if we can GVC, it might be an AI-generated content. We just have to meet in person, since robotics is not quite there yet. 😵‍💫😵‍💫😵‍💫

@_beenkim Prove that you are you, Been :)

@ashVaswani Congrats!! 🎉

Rnj-1-Instruct is now the #1 trending text generation model on HF!

What a privilege it is to have time as your most valuable currency.

Safety-oriented interpretability researchers should be focused on AI systems, not individual model artifacts. A snippet from the NeurIPS CogInterp workshop panel on Sunday:

This post seems to describe substantially the same view that I offer here: web.stanford.edu/~cgpotts/blog/… Why are people describing the GDM post as concluding that mech-interp is a failed project? Is it the renaming of the field and constant talk of "pivoting"?

@giffmana Wait until he says six seven. 🙃

I think i understand now. I need to align him a bit more 😅

Tomorrow 9:30am #NeurIPS2025 Room 30A-E I'll talk about " 📈Towards Pareto frontier of interpretability: 15 years of interpretability research in 15 mins"🚅 @ mech interp workshop mechinterpworkshop.com

@doomie @shaneguML go harass Dumi 🤣

@shaneguML @_beenkim Step 1: Become Been 2: ??? 3: profit!

Take that @doomie Samy Bengio! Hehehe

Our work out there in the wild 🥹

🔥 Proactive Co-Creator is officially LIVE in @GoogleAIStudio! Stop guessing prompts. Start collaborating. Use it now to remix ideas and generate images, stories, and video with an AI that proactively helps you create. 🔗 Try it here: aistudio.google.com/apps/bundled/p… 📍 At #NeurIPS2025? Come see the live demo TODAY (Dec 3) 9AM - 1:30PM | Google Booth #1533 (Kiosk 3) 🧠 Our research @GoogleDeepMind : We’re turning theory into practice. Read the papers behind the tech: Concept Edits (Tech Report): storage.googleapis.com/concept-edit/r… Proactive Agents (ICML 25'): arxiv.org/abs/2412.06771 QuestBench (NeurIPS 25'): arxiv.org/abs/2503.22674

Awesome @NeurIPSConf keynote this morning by @YejinChoinka on The Art of (Artificial) Reasoning – and her broader thoughts and wishes on the future of Artificial Intelligence neurips.cc/virtual/2025/i…

Add: 9:30am on Sunday at Neurips, i'll touch upon this at the mech interp workshop keynote mechinterpworkshop.com

8/8 Making AI benefit humans takes a village. 🌍 But a village needs a shared language. Let's stop guessing and start measuring the frontier.📷 a short write-up: @beenkim/the-pareto-frontier-of-human-centered-ai-54f90ba5872c" target="_blank" rel="nofollow noopener">medium.com/@beenkim/the-p…

1/8 Pareto Frontier 🤠for Human-centered AI 📈: We all want to build AI that is good for humans, but the path is often paralyzed by complexity. Either “oh my god, it’s too complicated😱” or delusional “I have a warm and fuzzy feeling of understanding 🥴”? "It’s hard because it depends.🤷" is the enemy of progress. We need a Pareto Frontier for Human-centered AI. 🧵👇