Been Kim Profile
Been Kim

@_beenkim

Followers
26K
Following
2K
Media
97
Statuses
840

Research Scientist at Google DeepMind, PhD from MIT. Make machines empower people.

Joined August 2011
Don't wanna be here? Send us removal request.
@_beenkim
Been Kim
9 days
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
4
12
75
@suchenzang
Susan Zhang
3 years
What a privilege it is to have time as your most valuable currency.
3
6
117
@vicariusltd
Vicarius
4 days
12 Days of Cybersec Christmas On repeat 🔂
3
10
46
@ChrisGPotts
Christopher Potts
4 days
Safety-oriented interpretability researchers should be focused on AI systems, not individual model artifacts. A snippet from the NeurIPS CogInterp workshop panel on Sunday:
4
18
162
@ChrisGPotts
Christopher Potts
12 days
This post seems to describe substantially the same view that I offer here: https://t.co/LoNw7jFltD 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"?
@NeelNanda5
Neel Nanda
13 days
The GDM mechanistic interpretability team has pivoted to a new approach: pragmatic interpretability Our post details how we now do research, why now is the time to pivot, why we expect this way to have more impact and why we think other interp researchers should follow suit
4
20
127
@_beenkim
Been Kim
8 days
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
4
10
80
@JustHackingHQ
Just Hacking Training (JHT)
13 days
Cyber Monday = Cyber DECEMBER! 🎅 Let the season of giving commence and last all month. Use Code CYBER25 for 25% Off Courses. Don't forget, we have Free & NameYourPrice options, too. Just Hacking Training (JHT) is a platform providing "Focused Technical Training for All Levels"
2
17
45
@_beenkim
Been Kim
8 days
Take that @doomie Samy Bengio! Hehehe
12
5
101
@_beenkim
Been Kim
9 days
Our work out there in the wild 🥹
@ziwphd
Zi Wang, Ph.D.
11 days
🔥 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: https://t.co/YQ4JBZbYbJ 📍 At #NeurIPS2025?
0
3
27
@ziwphd
Zi Wang, Ph.D.
11 days
🔥 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: https://t.co/YQ4JBZbYbJ 📍 At #NeurIPS2025?
0
8
24
@stanfordnlp
Stanford NLP Group
10 days
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 https://t.co/Zn5y7LWOV1
1
15
100
@nautrobo
Nauticus Robotics
10 days
Highly skilled Operator vs Nauticus ToolKITT Extrapolation of the variance tells you the power of autonomy in improving operational performance - It is a must see. The transformation of autonomy to business value
13
35
84
@_beenkim
Been Kim
9 days
Add: 9:30am on Sunday at Neurips, i'll touch upon this at the mech interp workshop keynote
0
1
4
@_beenkim
Been Kim
9 days
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:
Tweet card summary image
medium.com
We all want to build AI that is good for humans, but the path is often paralyzed by complexity. Not only is human evaluation a lot of work…
1
2
3
@_beenkim
Been Kim
9 days
7/8 Example: We discovered Veo’s zero-shot capability all via prompting [ https://t.co/7IaYDyiwdD]. 🎥. Complexity: Low 📷 Efficiency: High - transfer is instant! Once you see this paper, you can start prompting Veo to do a task it wasn’t trained to do.
Tweet card summary image
video-zero-shot.github.io
Video models like Veo 3 are on a path to become vision foundation models.
1
1
3
@_beenkim
Been Kim
9 days
6/8 Example: We used AlphaZero to teach chess Grandmasters [ https://t.co/EgUnrMD5gw]. ♟️ Complexity: Superhuman (High ⬆️) Efficiency: Low (Took hours with the world's best). But it’s worth it - one student (Gukesh) became the youngest World Chess Champion.
Tweet card summary image
pnas.org
AI systems have attained superhuman performance across various domains. If the hidden knowledge encoded in these highly capable systems can be leve...
1
1
3
@_beenkim
Been Kim
9 days
5/8 By decomposing the problem, one can make a clear contribution by focusing on one axis (e.g., improving teaching efficiency of the same knowledge). It also makes the goal of human-centered AI clear: simply “discovering” the knowledge does not push the Pareto frontier without
1
0
2
@The_WHI_Podcast
WHI Podcast
6 hours
White guys get a podcast and just evolve into this 🤷
0
1
5
@_beenkim
Been Kim
9 days
4/8 The complexity can be measured by intrinsic concept complexity (e.g., MDL) and perceived complexity (e.g., NASA TLX).
1
0
2
@_beenkim
Been Kim
9 days
3/8 The transfer efficiency can be measured by the differences in human understanding/performance/satisfaction on the target task divided by time spent. We can measure the "best" human to get at our upper limit (not always PhDs). Some tasks will have high complexity and low
1
0
3
@_beenkim
Been Kim
9 days
2/8 LLMs use a Pareto curve (Performance vs. serving cost). Why don't we? Evaluating humans is messy, but we can project the chaos onto two axes: 📈 Y-Axis: Complexity of Knowledge or capability ⚡️ X-Axis: Transfer efficiency.
1
0
5
@_beenkim
Been Kim
14 days
(Only for those who care to read this far) We have an internship position-if you are interested in discovering model capabilities. Email me with CV please:)
1
0
30
@inconetwork
Inco ☁️
5 days
Navigating Privacy and Compliance in Blockchain Systems: a new report from Inco and @0xPredicate a review of the privacy + compliance landscape, exploring solutions from @AleoHQ, @AvaCloud, @fluidkey, @payy_link, @0xprivacypools, @RAILGUN_Project, @solana, @verulink, + @zksync
79
57
214
@_beenkim
Been Kim
14 days
Coming to Neurips from 5-7th! Speaking at the mechanistic interpretability workshop https://t.co/MEoMMFgKRB on the 7th about unmechanistic interpretability (as requested by the organizers) 🙃🙂 While I’ll miss this, our work will be demoed at Google booth eg veo zeroshot
4
5
122
@demishassabis
Demis Hassabis
26 days
Students in the US (and many other countries) can get their hands on all the Gemini 3 Pro goodness for free!
@GeminiApp
G3mini
26 days
With advanced reasoning and the ability to analyze hour-long videos, Gemini 3 is perfect for students. And now, college students in the US can get Gemini's Pro plan for free, with more access to Gemini 3 Pro (terms apply). See how our most accurate model can help ⬇️
83
130
3K