MATS Research @MATSprogram
MATS empowers researchers to advance AI alignment, governance, and security matsprogram.org Berkeley, CA Joined November 2023-
Tweets50
-
Followers1K
-
Following131
-
Likes87
MATS 9.0 applications are open! Launch your career in AI alignment, governance, and security with our 12-week research program. MATS provides field-leading research mentorship, funding, Berkeley & London offices, housing, and talks/workshops with AI experts.
Last chance to apply to work at MATS! Still taking applications for Research Managers, Community Managers, and Operations Generalists. Apply by May 2! matsprogram.org/careers
@MATSprogram Summer 2025 applications close Apr 18! Come help advance the fields of AI alignment, security, and governance with mentors including @NeelNanda5 @EthanJPerez @OwainEvans_UK @EvanHub @bshlgrs @dawnsongtweets @DavidSKrueger @RichardMCNgo and more!
MATS is hiring! Join us in advancing AI safety. Apply by Nov 3, 2024. - Research Manager (Berkeley) (1-3 hires) - Community Manager (Berkeley) (1 hire) - Operations Generalist (Berkeley) (1-2 hires) matsprogram.org/careers
Interested in AI safety strategy? The MATS curriculum just got updated! lesswrong.com/posts/rhEXTkDm…
Prof David Krueger is mentoring alignment researchers via MATS, deadline Oct 13th. David is great, maybe you should apply!
Prof David Krueger is mentoring alignment researchers via MATS, deadline Oct 13th. David is great, maybe you should apply!
@MATSprogram Alumni Impact Analysis published! 78% of alumni are still working on AI alignment/control and 7% are working on AI capabilities. 68% have published alignment research lesswrong.com/posts/jeBkx6ag…
@MATSprogram is holding application office hours on Fri Sep 27, at 11 am and 6 pm PT. We will discuss how to apply to MATS (due Oct 6!) and answer your Qs. Register here: airtable.com/appnMboxg76F1Q…
I’m taking applications for collaborators via @MATSprogram! It’s a great way for new or experienced researchers outside AI safety research labs to work with me/others in these groups: @NeelNanda5, @EvanHub, @MrinankSharma, @NinaPanickssery, @FabienDRoger, @RylanSchaeffer, ...🧵
MATS Winter 2024-25 applications close Oct 6! Come and kick-start your AI safety research career. Mentors include @OwainEvans_UK @bshlgrs @EvanHub @StephenLCasper and more! matsprogram.org
@MATSprogram Winter 2024-25 mentors include researchers from @AnthropicAI @GoogleDeepMind @aisafetyinst redwoodresearch.org @CNASdc @CHAI_Berkeley @AlgAlignMIT @farairesearch @ai_risks @apolloaisafety @kasl_ai @MIRIBerkeley and more! Apply by Oct 6. matsprogram.org/mentors
It was awesome speaking at @MATSprogram about vision mechanistic interpretability. There was so much fresh energy 🌻 The next talk will be streamed and materials will be made available!
This was work done at @MATSprogram , where I was mentored by @AdriGarriga . Thanks to @farairesearch for providing access to the compute cluster! We presented this work as a poster at the ICML 2024 MechInterp workshop (icml2024mi.pages.dev)
Met some good people this summer at the @MATSprogram.
Check out #ICML2024 posters by @MATSprogram scholars mentored by @AdriGarriga! July 26: NextGen AI Safety 💥Catastrophic Goodhart July 27: Mechanistic Interpretability 🔬InterpBench 🔥Adversarial Circuit Evaluation 🐍Indirect Object Identification Circuit in Mamba
Chandler Smith @MATSprogram has been awarded a Foresight AI Safety Grant for his groundbreaking Multi-Agent Safety project. Co-funded by @open_phil this research will be conducted at the prestigious @OxfordTVG Apply before September 30th: foresight.org/ai-safety/
👥Congrats to @MATSprogram scholar @phylliida, mentored by our own @AdriGarriga! 📄 Read the full paper "Investigating the Indirect Object Identification circuit in Mamba" at arxiv.org/abs/2407.14008
How do we supervise models to answer truthfully when human labellers aren’t domain experts? 🤔 Our paper shows that non-expert humans can better judge answers after observing debates between expert LLMs. I’ll share tips for automated debates and getting LLM judges to work. 🧵
How do we supervise models to answer truthfully when human labellers aren’t domain experts? 🤔 Our paper shows that non-expert humans can better judge answers after observing debates between expert LLMs. I’ll share tips for automated debates and getting LLM judges to work. 🧵
It’s actually insane how high-value @MATSprogram is - I joined as a software engineer with minimal ML exp and was able to learn research skills by collaborating with brilliant researchers on a high impact project. So grateful to the MATS team for making it happen.
It’s actually insane how high-value @MATSprogram is - I joined as a software engineer with minimal ML exp and was able to learn research skills by collaborating with brilliant researchers on a high impact project. So grateful to the MATS team for making it happen.
Applications to @NeelNanda5's mech interp @MATSprogram are now open! Apply by Aug 30. forms.matsprogram.org/general-applic…
Applications to @NeelNanda5's mech interp @MATSprogram are now open! Apply by Aug 30. forms.matsprogram.org/general-applic…
Mahdi Ghaznavi @MahdiGhaznavi78
90 Followers 549 Following
Jafar Isbarov @phylo_GENETIC
117 Followers 496 Following CS PhD student @VT_CS. Previously a visiting researcher @NYU_Courant. I work on Structured Generation, LLM Security, and Multilingual LLMs. Sapere aude.
John @JohnArtro
1 Followers 67 Following Interested in politics, philosophy, sport. Not sure if my views are entirely my own and I doubt very much if they're insightful enough to share.
Cameron Beebe, Ph.D. @BeebsMemes
450 Followers 2K Following Cybernetics and Philosophy of Physics. AGI = automating machine epistemology. Steering oracles via @sci_phi_init
Pinar Ozisik @pinar_ozisik
316 Followers 769 Following Researcher @MIT | RL, distributed systems, AI safety, blockchain | PhD UMass @manningcics I she/her | also at https://t.co/gRE0oLF3jT
一树🌴 Issue.𝟎... @issue_wong
900 Followers 1K Following 写写代码，闲聊投资 | Cofounder @0xUclub 🇭🇰 卖过彩票 @sortesfun 🐡 | Prev @Alibaba @Johnshopkins
Shradha Sehgal @shradhasgl
951 Followers 2K Following Machine Learning @ Netflix | MS CS @ UIUC | ML, NLP, Social Computing research
Ankur @Ankuryogi11
346 Followers 6K Following
xuantuyen @xuantuyen17
4 Followers 196 Following
Jing Guo @guojing0
103 Followers 1K Following *Looking for PhD and jobs!* MSc in Math from Regensburg; BSc in Math and CS minor from Utah AI/ML/DL & Extremal combinatorics and theoretical computer science
Hoang Cuong Nguyen @HoangCuongNguy2
78 Followers 2K Following
Max Ovsiankin @maxovsi
21 Followers 64 Following Ph.D. student at @TTIC_Connect, studying theoretical CS
NeuralNetNinja @DeepLearnQuest
22 Followers 580 Following curious. documenting my deep learning journey.
Yuwei Xiao @yuweixiao_
237 Followers 808 Following phd student @uclacomsci | hci, visualization, sensemaking.
Julian @juligier
24 Followers 2K Following
Arthur P.B. Laudrain ... @APB_Laudrain
1K Followers 3K Following R. Lounsbery Fellow @StanfordCISAC. DPhil, FHEA. He/him. Prev. @Politics_Oxford, @warstudies, @LeidenLaw, @SeoulNatlUni, @UMontreal.
pawrawmetrizedpossum @pawrawmetrized
1 Followers 403 Following
Veylan Solmira @VeylanSolmira
5 Followers 71 Following AI alignment researcher | Deception, interpretability, & ecological reward shaping | Toward morally coherent, life-aligned digital systems
Gökhan Altınören @altinoren
152 Followers 209 Following
Katherine Law @katalog
690 Followers 3K Following Doctor - Consultant / Attending Geriatrician on a career break 🇭🇰🇬🇧🇺🇸 Thinking about ageing / future of healthcare. What’s next? 🌞🌊
Sander Schulhoff @SanderSchulhoff
3K Followers 194 Following Founder & CEO of https://t.co/voVbs47riI | @LearnPrompting, @hackaprompt
Lukas Bongartz @lukas_bongartz
227 Followers 742 Following Thermodynamics & Neuromorphic Computing • PhD Physics (TU Dresden) • PhD Scholar @ Stanford (prev.)
Harshal Nandigramwar @hnanacc
413 Followers 847 Following ai research @intel, prev @cariad_tech, @Uni_Stuttgart • n&w @todacklabs (https://t.co/LPf3PWfbnK, https://t.co/WESRemr9Ev, corpus, marrow)
Aatman @aatman_vaidya
215 Followers 1K Following sde/researcher at tattle civic tech @tattlemade. building open-source tools and datasets to respond to online harms and abuse
freaky fish guy @samliu
362 Followers 1K Following building creativity ex- perception @waymo, spam&abuse @google https://t.co/T1kjswGzvU
BluesRandomPolitics @BluesPolitics
318 Followers 797 Following Foward-Democrat | 24’ DNC Delegate | WTCC Student
Hazel Browne @brown4748
1 Followers 53 Following
Nishant Mishra @mnishant2
153 Followers 529 Following ML researcher, Vision, NLP, Probabilistic models.PhDing in Responsible AI at University of Amsterdam. Servicenow|McGill University
Enrique Mejía Fontan... @emejiaf
215 Followers 3K Following RT o like son mis medios de comunicación pero no soy un bot solo me da amsiedad producir contenido
ggh ff @ffsd2433
1 Followers 99 Following
Seiji Eicher @seiji_________
59 Followers 351 Following Ray + vLLM = 💘 @ Anyscale | Prev: @Apple, @Stanford
Ben McCarty — secur... @apt_ben
594 Followers 998 Following Author | Inventor | Veteran | Cybersecurity Pro | Quantum R&D
Fulcrum @fulcrumML
184 Followers 3 Following
Cozmin Ududec @CUdudec
363 Followers 2K Following @AISecurityInst Testing and Science of Evals. Ex quantum foundationalist.
Yo Shavit @yonashav
7K Followers 957 Following policy for v smart things @openai. Past: CS PhD @HarvardSEAS/@SchmidtFutures/@MIT_CSAIL. Tweets my own; on my head be it.
xAI @xai
1.8M Followers 38 Following
Peter Wildeford🇺�... @peterwildeford
21K Followers 318 Following Globally ranked top 20 forecaster 🎯 Working at @IAPSai to shape AI for prosperity and human freedom.
Yoshua Bengio @Yoshua_Bengio
25K Followers 206 Following Working towards the safe development of AI for the benefit of all @UMontreal, @LawZero_ & @Mila_Quebec A.M. Turing Award Recipient and most-cited AI researcher.
Quintin Pope @QuintinPope5
3K Followers 250 Following ML researcher focusing on natural language modeling and alignment.
Thomas Woodside @Thomas_Woodside
2K Followers 282 Following Co-Founder & Senior Policy Advisor @ Secure AI Project. MA student at @GeorgetownCSS. Prev: @CSETgeorgetown, @ai_risks. Creator of the beet emoji 
Andrea Miotti @_andreamiotti
2K Followers 387 Following Trying to make the future go well. Founder and CEO @ai_ctrl
Rylan Schaeffer @RylanSchaeffer
6K Followers 2K Following CS PhD Student at Stanford Trustworthy AI Research with @sanmikoyejo. Prev interned/worked @ Meta, Google, MIT, Harvard, Uber, UCL, UC Davis
Juan @heartbulbous
383 Followers 353 Following Personal account. Leave me anonymous feedback here: https://t.co/oWXFYarrVG
FAR.AI @farairesearch
13K Followers 21 Following Frontier alignment research to ensure the safe development and deployment of advanced AI systems.
Anca Dragan @ancadianadragan
12K Followers 184 Following post training co-lead at Google DeepMind, focusing on safety, alignment, post training capabilities • associate professor at UC Berkeley EECS
Evžen Wybitul @evzen_wy
262 Followers 762 Following Incoming AI safety and technical AI governance DPhil @UniofOxford • MSc in AI at ETH Zurich • 2x @MATSprogram • Talos AI Governance Fellowship • 🇪🇺🇨🇿
Center for AI Policy @aipolicyus
720 Followers 3 Following Nonpartisan research organization dedicated to mitigating the catastrophic risks of AI through policy development and advocacy.
🚀Henry is launchin... @sleight_henry
1K Followers 677 Following AI Safety Research Manager @ Constellation, Anthropic Fellows, prev-MATS Working out how to Do Big Good, but sanely! Apologetically myself | He/Him, 26
Joe Carlsmith @jkcarlsmith
7K Followers 649 Following Philosophy, futurism, AI. Senior advisor @open_phil. Opinions my own.
Daniel Filan @dfrsrchtwts
2K Followers 189 Following Senior research manager at MATS: https://t.co/Dj9HNhMdoJ Want to usher in an era of human-friendly superintelligence, don't know how.
Andrew Critch (🤖�... @AndrewCritchPhD
5K Followers 291 Following Let's make AI doctors! Views my own; CEO @ https://t.co/wvoKT50fKX; AI Researcher @ Berkeley; If I block you it's like I'm moving to another convo at a party; nbd.
Google DeepMind @GoogleDeepMind
1.2M Followers 279 Following We’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.
OpenAI @OpenAI
4.3M Followers 3 Following OpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6Lg202
ML Safety @ml_safety
1K Followers 2 Following Course: https://t.co/XWcOJjXRVG Newsletter: https://t.co/HEe7NatYhA Papers as they come out: https://t.co/d7f799Sby2. More: https://t.co/NgGDTW4sYk
Demis Hassabis @demishassabis
488K Followers 146 Following Nobel Laureate. Co-Founder & CEO @GoogleDeepMind - working on AGI. Solving disease @IsomorphicLabs. Trying to understand the fundamental nature of reality.
Sebastien Bubeck @SebastienBubeck
56K Followers 1K Following I work on AI at OpenAI. Former VP AI and Distinguished Scientist at Microsoft.
Sham Kakade @ShamKakade6
16K Followers 495 Following Harvard Professor. Full stack ML and AI. Co-director of the Kempner Institute for the Study of Artificial and Natural Intelligence.
Chris Olah @ch402
122K Followers 181 Following Reverse engineering neural networks at @AnthropicAI. Previously @distillpub, OpenAI Clarity Team, Google Brain. Personal account.
Rob Miles @robertskmiles
34K Followers 824 Following Explaining AI Alignment to anyone who'll stand still for long enough, on YouTube and Discord. Music, movies, microcode, and high-speed pizza delivery
Markus Anderljung @Manderljung
3K Followers 915 Following Trying to design good AI policy. Director of Policy & Research @GovAI_, Adjunct Fellow @CNASdc
Catherine Olsson @catherineols
18K Followers 1K Following Hanging out with Claude, improving its behavior, and building tools to support that @AnthropicAI 😁 prev: @open_phil @googlebrain @openai (@microcovid)
Johannes Treutlein @j_treutlein
343 Followers 172 Following AI alignment stress-testing research @AnthropicAI. On leave from my CS PhD at UC Berkeley, @CHAI_Berkeley. Opinions my own.
Daniel Paleka @dpaleka
4K Followers 850 Following ai safety researcher | phd @CSatETH | https://t.co/hCoh5RJgZD
Mustafa Suleyman @mustafasuleyman
168K Followers 487 Following CEO, Microsoft AI | Author: The Coming Wave | Past: Co-founder, @InflectionAI & @GoogleDeepMind
tammy @carad0
785 Followers 0 Following
JJ Hepburn @JJ_Hepboin
528 Followers 704 Following Just trying to save the world from artificial intelligence.
Conjecture @ConjectureAI
4K Followers 4 Following We are building Cognitive Emulation, an alternative AI paradigm that is controllable, transparent, and safe. Get in touch at [email protected].
Tom Lieberum 🔸 @lieberum_t
1K Followers 196 Following Trying to reduce AGI x-risk by understanding NNs Interpretability RE @DeepMind BSc Physics from @RWTH 10% pledgee @ https://t.co/Vh2bvwhuwd
Rosie Campbell @RosieCampbell
8K Followers 1K Following Forever expanding my nerd/bimbo Pareto frontier. AI welfare 🤝 AI safety. Managing Director @eleosai, Ex-OpenAI, 2024 @rootsofprogress fellow
Katja Grace 🔍 @KatjaGrace
10K Followers 798 Following Thinking about whether AI will destroy the world at https://t.co/pMilDvd4ya. DM or email for media requests. Feedback: https://t.co/zGAm1i7SKH
Luke Muehlhauser @lukeprog
9K Followers 323 Following Open Philanthropy Program Director, AI Governance and Policy
Matthew Barnett @MatthewJBar
8K Followers 368 Following Co-founder of @MechanizeWork Married to @natalia__coelho email: matthew at mechanize dot work
Robert Long @rgblong
8K Followers 997 Following executive director of @eleosai AI consciousness and AI welfare
Future of Life Instit... @FLI_org
88K Followers 1K Following We work on reducing extreme risks and steering transformative technologies to benefit humanity. RT /=/ endorsement. Bluesky: https://t.co/IjvxJtEEeQ
Rob Bensinger ⏹️ @robbensinger
12K Followers 386 Following Comms @MIRIBerkeley. RT = increased vague psychological association between myself and the tweet.
Oliver Habryka @ohabryka
6K Followers 722 Following Building https://t.co/O5mQY6jndL and https://t.co/s49h898W4b. Join our writing residency at https://t.co/7HQag8pNUk!Trends for United States
You might like
