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
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
@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…
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)
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/
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.
117 Followers 496 FollowingCS PhD student @VT_CS. Previously a visiting researcher @NYU_Courant. I work on Structured Generation, LLM Security, and Multilingual LLMs. Sapere aude.
1 Followers 67 FollowingInterested 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.
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
690 Followers 3K FollowingDoctor - Consultant / Attending Geriatrician on a career break 🇭🇰🇬🇧🇺🇸 Thinking about ageing / future of healthcare. What’s next? 🌞🌊
215 Followers 1K Followingsde/researcher at tattle civic tech @tattlemade. building open-source tools and datasets to respond to online harms and abuse
153 Followers 529 FollowingML researcher, Vision, NLP, Probabilistic models.PhDing in Responsible AI at University of Amsterdam. Servicenow|McGill University
25K Followers 206 FollowingWorking 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.
2K Followers 282 FollowingCo-Founder & Senior Policy Advisor @ Secure AI Project.
MA student at @GeorgetownCSS.
Prev: @CSETgeorgetown, @ai_risks.
Creator of the beet emoji
6K Followers 2K FollowingCS PhD Student at Stanford Trustworthy AI Research with @sanmikoyejo. Prev interned/worked @ Meta, Google, MIT, Harvard, Uber, UCL, UC Davis
12K Followers 184 Followingpost training co-lead at Google DeepMind, focusing on safety, alignment, post training capabilities • associate professor at UC Berkeley EECS
262 Followers 762 FollowingIncoming AI safety and technical AI governance DPhil @UniofOxford • MSc in AI at ETH Zurich • 2x @MATSprogram • Talos AI Governance Fellowship • 🇪🇺🇨🇿
720 Followers 3 FollowingNonpartisan research organization dedicated to mitigating the catastrophic risks of AI through policy development and advocacy.
1K Followers 677 FollowingAI Safety Research Manager @ Constellation, Anthropic Fellows, prev-MATS
Working out how to Do Big Good, but sanely!
Apologetically myself |
He/Him, 26
2K Followers 189 FollowingSenior research manager at MATS: https://t.co/Dj9HNhMdoJ
Want to usher in an era of human-friendly superintelligence, don't know how.
5K Followers 291 FollowingLet'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.
1.2M Followers 279 FollowingWe’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.
4.3M Followers 3 FollowingOpenAI’s mission is to ensure that artificial general intelligence benefits all of humanity. We’re hiring: https://t.co/dJGr6Lg202
1K Followers 2 FollowingCourse: https://t.co/XWcOJjXRVG
Newsletter: https://t.co/HEe7NatYhA
Papers as they come out: https://t.co/d7f799Sby2.
More: https://t.co/NgGDTW4sYk
488K Followers 146 FollowingNobel Laureate. Co-Founder & CEO @GoogleDeepMind - working on AGI. Solving disease @IsomorphicLabs. Trying to understand the fundamental nature of reality.
16K Followers 495 FollowingHarvard Professor.
Full stack ML and AI.
Co-director of the Kempner Institute for the Study of Artificial and Natural Intelligence.
34K Followers 824 FollowingExplaining AI Alignment to anyone who'll stand still for long enough, on YouTube and Discord.
Music, movies, microcode, and high-speed pizza delivery
18K Followers 1K FollowingHanging out with Claude, improving its behavior, and building tools to support that @AnthropicAI 😁
prev: @open_phil @googlebrain @openai (@microcovid)
4K Followers 4 FollowingWe are building Cognitive Emulation, an alternative AI paradigm that is controllable, transparent, and safe. Get in touch at [email protected].
10K Followers 798 FollowingThinking about whether AI will destroy the world at https://t.co/pMilDvd4ya. DM or email for media requests. Feedback: https://t.co/zGAm1i7SKH