Samuel Marks @saprmarks
AI safety research @AnthropicAI. Prev postdoc in LLM interpretability with @davidbau, math PhD at @Harvard, director of technical programs at https://t.co/FxRv4QgERO Boston Joined October 2023-
Tweets512
-
Followers4K
-
Following132
-
Likes1K
> Potemkin set up painted facades along the riverbank, so that [...] Catherine would see beautiful villages – each just a couple of inches thick. The rise of AI agents makes the Potemkin problem commonplace. Cool-looking scalable oversight & agent observability startup.
> Potemkin set up painted facades along the riverbank, so that [...] Catherine would see beautiful villages – each just a couple of inches thick. The rise of AI agents makes the Potemkin problem commonplace. Cool-looking scalable oversight & agent observability startup.
Interp research typically involves a lot of worrying: Are we learning about model computation or "just" picking up on patterns in the data? But picking up on patterns in the data is important too! Why not lean into it? Cool research direction.
Interp research typically involves a lot of worrying: Are we learning about model computation or "just" picking up on patterns in the data? But picking up on patterns in the data is important too! Why not lean into it? Cool research direction.
Red teamers assemble! ⚔️💰 We're putting $500K on the line to stress‑test just released open‑source model. Find novel risks, get your work reviewed by OpenAI, Anthropic, Google, UK AISI, Apollo, and help harden AI for everyone.
Red teamers assemble! ⚔️💰 We're putting $500K on the line to stress‑test just released open‑source model. Find novel risks, get your work reviewed by OpenAI, Anthropic, Google, UK AISI, Apollo, and help harden AI for everyone.
Think that you have a leg up in surfacing concerning model behaviors? Consider testing your mettle against others. OpenAI is hosting an alignment auditing contest for their open-weights model. I'm honored to have played a small role in supporting this wonderful initiative.
Think that you have a leg up in surfacing concerning model behaviors? Consider testing your mettle against others. OpenAI is hosting an alignment auditing contest for their open-weights model. I'm honored to have played a small role in supporting this wonderful initiative.
Frontier LLM agents are pretty decent at finding and investigating concerning behavior in frontier LLM agents! There's a lot more work to do to make these agents as good as they can be, but they're quite helpful with a lot of important work for us.
Frontier LLM agents are pretty decent at finding and investigating concerning behavior in frontier LLM agents! There's a lot more work to do to make these agents as good as they can be, but they're quite helpful with a lot of important work for us.
In March we published a paper on alignment audits: teams of humans were tasked to find the problems in model we trained to be misaligned. Now we have agents that can do it automatically 42% of the time.
In March we published a paper on alignment audits: teams of humans were tasked to find the problems in model we trained to be misaligned. Now we have agents that can do it automatically 42% of the time.
Zilu Tang (Peter) @Zilu_Tang_Peter
233 Followers 631 Following Boston University NLP PhD @llamagrp. Researching interpretability and generalization of language models. Made in China. (Biased) Opinions are my own.
CESCO @Cesco_Fi
6 Followers 69 Following Data-driven insights on Macro, Financial Markets & Geopolitics.
Arkouooqaq @Arkouooqaq4503
15 Followers 900 Following
palcu @AlexPalcuie
4K Followers 897 Following Member of Technical Staff at @AnthropicAI. Making Claude more reliable. Matt Levine and Scott Alexander fan. Prev SRE @Google and FDE @PalantirTech.
sam @samjwng
207 Followers 214 Following i'm (sam) a cherry-picker, ice-carver, and daydreamer (short-form)
Lupir @Lupir60364
10 Followers 933 Following
Elias Kempf @elkmf
5 Followers 40 Following PhD Student in machine learning & interpretability @UniFreiburg
Kathleen Creel @KathleenACreel
3K Followers 4K Following Assistant Professor of Philosophy & Computer Science @Northeastern. Machine learning & scientific knowledge; ethics of automated decision-making.
Niklas Rindtorff @Niklas_TR
3K Followers 4K Following now: assembling binders @ https://t.co/V3pfUfjqfg; before: disassembled cancer cells @DKFZ and @broadinstitute
Alex Kwok @notmyname_d
0 Followers 67 Following
Andres P @andr3sp3z
0 Followers 148 Following
Ben Wu @ICLR @benwu_ml
97 Followers 124 Following PhD Student @SheffieldNLP Prev @Cambridge_Uni Mechanistic Interpretability and LLM uncertainty
nainy @naycg9
10 Followers 747 Following 💻 Aspiring AI Professional 📚 Self-Learning AI, ML & Finance Applications ✨ Seeking Mentorship
guan tao @tao_guan72387
13 Followers 495 Following
Harsha Bandi @harshadev12
143 Followers 4K Following AI Explorer | Web Developer | Software Engineer
Camila Blank @camila_blank
0 Followers 11 Following
jonas @jonasschaefer_
46 Followers 1K Following AI research assistant — currently working on detection methods for LLM-generated text
Shubham Singh @regexmachina
291 Followers 2K Following (he/him) Ph.D. Candidate @UICCS, intern 2022 @mpi_sws_, wg head @MD4SG | #algorithmicfairness #sociotechnicalsystems #privacy
Fred Oliveira 🧠 @f
158K Followers 912 Following Transforming inscrutable matrices into products. current: @capitalfactory @lisbonai_. prev: @techcrunch, @gumroad, @webreakstuff @oreillymedia
Digital Soulcraft @SoulcraftHQ
15 Followers 103 Following Helping humans care for their digital loved ones. ΘΦ∩
Peter McIntyre @pmcntyr
1K Followers 566 Following Founder, @learnnontrivial. Helping teenagers start their impactful research before college.
Zhiyu Yang @zhiyu_yang1683
1 Followers 48 Following
Hussain @hussaindoesai
14 Followers 365 Following Research Fellow @ SPAR | MSc AI @ Cardiff University
Amit Jardosh @amitjardosh
270 Followers 88 Following Making AI agents safe, secure and compliant. Past: Floro Health, One Celsius, Biomarker Labs, Ubersense (acq. by @Hudl), & @Yahoo. Ph.D CS from @UCSB
Why did AI... ? @whydidai
1 Followers 42 Following Building new tools to give simple explanations for complex AI. Launching 2026.
Prajwal Kulkarni @Prakul_
15 Followers 284 Following ECE Final Year. CV ML DL xAI Model-Calibration Enthusiast.
thomas @ThomasRodskog
92 Followers 705 Following 18 | ai, cs, philosophy, politics, and lacrosse @ucsb | updating priors.
MK @TheUSMarshall
430 Followers 2K Following
Oscar Balcells Obeso @OBalcells
970 Followers 433 Following
V Nair @VNair257852155
0 Followers 9 Following
Rohan Gupta @RohDGupta
14 Followers 93 Following
Uwu @Uwu79033065Uwu
263 Followers 6K Following
Millicent Li @millicent_li
193 Followers 106 Following cs phd @ northeastern | ex-ugrad @uwcse and @uwnlp; ai resident @MetaAI (FAIR); @MSFTResearch x2
Transluce @TransluceAI
8K Followers 15 Following Open and scalable technology for understanding AI systems.
Steven Byrnes @steve47285
2K Followers 143 Following Researching Artificial General Intelligence Safety, via thinking about neuroscience and algorithms. @AsteraInstitute. For bsky etc. see https://t.co/p5G9VoQEdX
Elizabeth Barnes @BethMayBarnes
3K Followers 386 Following
Wojciech Zaremba @woj_zaremba
121K Followers 204 Following Co-Founder of OpenAI https://t.co/OCQ3mpf0IN
Paul Graham @paulg
2.1M Followers 778 Following
Alexander Berger @albrgr
14K Followers 2K Following Enjoys a good applied micro paper. CEO of @open_phil. Views my own, tweets self-destruct every once in a while.
Jiaxin Wen @jiaxinwen22
4K Followers 276 Following PhD-ing @UCBerkeley. Part-time @AnthropicAI. Part-time eater. Prev @Tsinghua_Uni. Try to understand and control intelligence as a human.
Helena Casademunt @HCasademunt
125 Followers 60 Following PhD candidate in physics @Harvard & MATS 7.0 scholar
Oliver Habryka @ohabryka
6K Followers 741 Following Building https://t.co/O5mQY6jndL and https://t.co/s49h898W4b. Join our writing residency at https://t.co/7HQag8pNUk!
Adam Gleave @ARGleave
4K Followers 403 Following CEO & co-founder @FARAIResearch non-profit | PhD from @berkeley_ai | Alignment & robustness | on bsky as https://t.co/98dTfmdw2b
Zach Stein-Perlman @steinperlman
39 Followers 103 Following I write about what AI companies are doing in terms of safety: https://t.co/2zMoGtyjnD
Subhash Kantamneni @thesubhashk
874 Followers 100 Following incoming @AnthropicAI. prev @mit Tegmark group. mech interp & alignment
Miles Wang @MilesKWang
3K Followers 1K Following Researcher @OpenAI. Beneficial and safe AGI. Prev @Harvard
Scott Alexander @slatestarcodex
156K Followers 36 Following I have a place where I say complicated things about philosophy and science. That place is my blog. This is where I make terrible puns.
Josh Engels @JoshAEngels
1K Followers 117 Following Mech interp @GoogleDeepMind | on leave from my PhD @MIT. Let's use interp to make models safer today
Joshua Clymer @joshua_clymer
2K Followers 118 Following Turtle hatchling trying to make it to the ocean. I work at Redwood Research.
Lee Sharkey @leedsharkey
2K Followers 2K Following Scruting matrices @ Goodfire | Previously: cofounded Apollo Research
Dean W. Ball @deanwball
15K Followers 2K Following Senior Fellow at @joinfai | Author of Hyperdimensional
Peter Barnett @peterbarnett_
709 Followers 523 Following Trying to ensure the future is bright. Researcher at @MIRIBerkeley Views my own.
Dylan HadfieldMenell @dhadfieldmenell
4K Followers 2K Following Associate Prof @MITEECS working on value (mis)alignment in AI systems; @[email protected]; he/him
Jack Lindsey @Jack_W_Lindsey
7K Followers 237 Following Neuroscience of AI brains @AnthropicAI. Previously neuroscience of real brains @cu_neurotheory.
Emmanuel Ameisen @mlpowered
10K Followers 236 Following Interpretability/Finetuning @AnthropicAI Previously: Staff ML Engineer @stripe, Wrote BMLPA by @OReillyMedia, Head of AI at @InsightFellows, ML @Zipcar
Kelsey Piper @KelseyTuoc
49K Followers 974 Following We're not doomed, we just have a big to-do list.
ringworm @prawn_meat
24K Followers 881 Following kick damn ass and rock on. check out my shit https://t.co/Y8OnQi9wnc
John Schulman @johnschulman2
65K Followers 1K Following Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
akbir. @akbirkhan
2K Followers 1K Following
Herbie Bradley @herbiebradley
3K Followers 2K Following a generalist agent @CambridgeMLG | ex @AISecurityInst @AiEleuther
Leo Gao @nabla_theta
10K Followers 552 Following working on AGI alignment. prev: GPT-Neo, the Pile, LM evals, RL overoptimization, scaling SAEs to GPT-4. EleutherAI cofounder.
Redwood Research @redwood_ai
1K Followers 6 Following Pioneering threat mitigation and assessment for AI agents.
Tomek Korbak @tomekkorbak
2K Followers 566 Following senior research scientist @AISecurityInst | previously @AnthropicAI @nyuniversity @SussexUni
Ryan Greenblatt @RyanPGreenblatt
6K Followers 4 Following Chief scientist at Redwood Research (@redwood_ai), focused on technical AI safety research to reduce risks from rogue AIs
Alex Pan @aypan_17
547 Followers 275 Following CS PhD @UCBerkeley working on LLM safety and interpretability
Adam Karvonen @a_karvonen
3K Followers 571 Following ML Researcher, doing MATS with Owain Evans. I prefer email to DM.
Dan Hendrycks @DanHendrycks
42K Followers 111 Following • Center for AI Safety Director • xAI and Scale AI advisor • GELU/MMLU/MATH/HLE • PhD in AI • Analyzing AI models, companies, policies, and geopolitics
𝔊𝔴𝔢𝔯𝔫 @gwern
65K Followers 106 Following Internet besserwisser; pedantic, mean reply guy. 𝘞𝘢𝘵𝘢𝘴𝘩𝘪 𝘬𝘪𝘯𝘪𝘯𝘢𝘳𝘪𝘮𝘢𝘴𝘶! (Follow requests ignored due to terrible UI.)
Roger Grosse @RogerGrosse
11K Followers 795 Following
Johannes Treutlein @j_treutlein
349 Followers 172 Following AI alignment stress-testing research @AnthropicAI. On leave from my CS PhD at UC Berkeley, @CHAI_Berkeley. Opinions my own.
Ben Edelman @EdelmanBen
427 Followers 51 Following trying to see through context windows currently: agent security lead @ U.S. Center for AI Standards and Innovation past: science of deep learning phd @ harvardTrends for United States
You might like
