Sam Bowman @sleepinyourhat
AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan. cims.nyu.edu/~sbowman/ San Francisco (mostly) Joined July 2011-
Tweets2K
-
Followers35K
-
Following3K
-
Likes70K
I very distinctly remember while I was in the thick of it making GPQA telling @rgblong that “I knew the project was going to be ambitious/hard, but I didn’t appreciate what that actually meant” In retrospect I probably still would’ve done it, but we basically had to restart the…
I very distinctly remember while I was in the thick of it making GPQA telling @rgblong that “I knew the project was going to be ambitious/hard, but I didn’t appreciate what that actually meant” In retrospect I probably still would’ve done it, but we basically had to restart the…
Full lecture slides and reading list for Roger Grosse's class on AI Alignment are up: alignment-w2024.notion.site
I’m super excited to release our 100+ page collaborative agenda - led by @usmananwar391 - on “Foundational Challenges In Assuring Alignment and Safety of LLMs” alongside 35+ co-authors from NLP, ML, and AI Safety communities! Some highlights below...
I like to think of myself as a researcher, but almost certainly the most valuable use of my time is writing US Visa letters.
One of our most crisp findings was that in-context learning usually follows simple power laws as a function of number of demonstrations. We were surprised we didn’t find this stated explicitly in the literature. Soliciting pointers: have we missed anything?
One of our most crisp findings was that in-context learning usually follows simple power laws as a function of number of demonstrations. We were surprised we didn’t find this stated explicitly in the literature. Soliciting pointers: have we missed anything?
This is the most effective, reliable, and hard to train away jailbreak I know of. It's also principled (based on in-context learning) and predictably gets worse with model scale and context length.
This is the most effective, reliable, and hard to train away jailbreak I know of. It's also principled (based on in-context learning) and predictably gets worse with model scale and context length.
Interesting and concerning new results from @cem__anil et al.: Many-shot prompting for harmful behavior gets predictably more effective at overcoming safety training with more examples, following a power law.
Interesting and concerning new results from @cem__anil et al.: Many-shot prompting for harmful behavior gets predictably more effective at overcoming safety training with more examples, following a power law.
I'm incredibly excited to have Craig joining us on the Anthropic Interpretability team! I've been a huge fan of @GoogleColab for nearly a decade (I used it internally at Google!) and have really admired Craig's work on it.
I'm incredibly excited to have Craig joining us on the Anthropic Interpretability team! I've been a huge fan of @GoogleColab for nearly a decade (I used it internally at Google!) and have really admired Craig's work on it.
I'll be a research supervisor for MATS this summer. If you're keen to collaborate with me on alignment research, I'd highly recommend filling out the short app (deadline today)! Past projects have led to some of my papers on debate, chain of thought faithfulness, and sycophancy
I'll be a research supervisor for MATS this summer. If you're keen to collaborate with me on alignment research, I'd highly recommend filling out the short app (deadline today)! Past projects have led to some of my papers on debate, chain of thought faithfulness, and sycophancy
Despite the constant arguments on p(doom), many agree that *if* AI systems become highly capable in risky domains, *then* we ought to mitigate those risks. So we built an eval suite to see whether AI systems are highly capable in risky domains. x.com/tshevl/status/…
Despite the constant arguments on p(doom), many agree that *if* AI systems become highly capable in risky domains, *then* we ought to mitigate those risks. So we built an eval suite to see whether AI systems are highly capable in risky domains. x.com/tshevl/status/…
We’re hiring for the adversarial robustness team @AnthropicAI! As an Alignment subteam, we're making a big effort on red-teaming, test-time monitoring, and adversarial training. If you’re interested in these areas, let us know! (emails in 🧵)
Today we're releasing Claude 3 Haiku, the fastest and most affordable model in its intelligence class. Haiku is now available in the API and on claude.ai for Claude Pro subscribers.
🚨📄 Following up on "LMs Don't Always Say What They Think", @milesaturpin et al. now have an intervention that dramatically reduces the problem! 📄🚨 It's not a perfect solution, but it's a simple method with few assumptions and it generalizes *much* better than I'd expected.
🚨📄 Following up on "LMs Don't Always Say What They Think", @milesaturpin et al. now have an intervention that dramatically reduces the problem! 📄🚨 It's not a perfect solution, but it's a simple method with few assumptions and it generalizes *much* better than I'd expected.
Really great post on how to think about doing mech interp research, and how it requires a very different mindset to normal ML
Really great post on how to think about doing mech interp research, and how it requires a very different mindset to normal ML
I suppose this is a good time to mention that I'm looking for a research prompt engineer, in case you want to be my promptégé. (Look, you may wildly out-prompt me but I couldn't resist that portmanteau.) jobs.lever.co/Anthropic/a2c8…
Want to work at the frontier of AI policy with the most technical policy team in the business? You do? Excellent. Please consider applying - Special Projects Lead jobs.lever.co/Anthropic/5752… - Policy Analyst, Product jobs.lever.co/Anthropic/6ecd… - Outreach Lead jobs.lever.co/Anthropic/df58…
5 years! It's been unbelievable to see how CSET's team and reputation has grown. To celebrate, here are 5 papers/products, 1 from each year of CSET's existence, that I love (and that exemplify the work we do).
5 years! It's been unbelievable to see how CSET's team and reputation has grown. To celebrate, here are 5 papers/products, 1 from each year of CSET's existence, that I love (and that exemplify the work we do).
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K Following
Delip Rao e/σ @deliprao
46K Followers 5K Following Busy inventing the shipwreck. @Penn. Past: @johnshopkins, @UCSC, @Amazon, @Twitter ||Art: #NLProc, Vision, Speech, #DeepLearning || Life: 道元, improv, running 🌈
Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | Pianist
Kyunghyun Cho @kchonyc
60K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).
Sasha Rush @srush_nlp
52K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGz
Miles Brundage @Miles_Brundage
43K Followers 10K Following Policy research at @openai. I mostly tweet about AI, animals, and sci-fi. He/him. Views my own.
Tal Linzen @tallinzen
16K Followers 895 Following Professor @nyuling and @NYUDataScience, research scientist @GoogleAI
Yi Tay @YiTayML
29K Followers 97 Following chief scientist / cofounder @RekaAILabs 🫠 past: research scientist @google brain 🤯 currently learning to be a dad 🍼
Jacob Andreas @jacobandreas
13K Followers 956 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJw
Rosanne Liu @savvyRL
33K Followers 966 Following Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS. Writing https://t.co/IbycyGfnDR
Felix Hill @FelixHill84
9K Followers 776 Following Research Scientist, Deepmind I try to think hard about everything I tweet, esp on 90s football and 80s music None of my opinions are really someone else's
Sara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.
Zachary Lipton @zacharylipton
59K Followers 2K Following Professor: CMU/@acmi_lab, CTO / CSO: @AbridgeHQ, Creator: @d2l_ai & https://t.co/QQt98VNLUp, Relapsing 🎷
Yoav Artzi @yoavartzi
13K Followers 163 Following Research/prof @cs_cornell + @cornell_tech🚡 / https://t.co/9YnWry7yHs / https://t.co/3VmRSyYm2d / asso. faculty director @arxiv / building https://t.co/f9QkzO5kaC
Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳
Danish Pruthi @danish037
7K Followers 628 Following Faculty at Indian Institute of Science, Bangalore. PhD from @LTIatCMU.
Luca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai (makin Dolma 🍇), open source science fan, @QueerInAI organizer 🤖☕️🍕they/them
Deniz Birlikci @denizbirlikci
22 Followers 108 Following cs + ai @CarnegieMellon, scholar @neo, prev @MercedesAMGF1
Acuitize AI @Acuitize_AI
34 Followers 50 Following
Christian Moya Calder.. @chrismoya86
2 Followers 413 Following
knut g. berdal @KnutBerdal
12K Followers 5K Following World citizen and public servant focused on facts and values, not conventional narratives. Multilateralism/ governance/ technology/ trade/ environment/ health
Alex Kim @greenblacke
0 Followers 15 Following
the_sven @the___sven
0 Followers 58 Following Sr. Fullstack developer with an interest in Data Engineering and Machine Learning.
Mr.Li 李先生 @FelixLee2022
11 Followers 76 Following Shenzhen,China. Business travel in USA. Mobile phone/ tablet/ IOT etc.
Todd Kueny — e/acc @techgazetteco
3K Followers 5K Following Empowering worlds where AI enriches lives, solves complex problems, and inspires continuous learning.
Loki Vera @loki_vera2
0 Followers 92 Following
dev potatopotato @devpotatopotato
9 Followers 115 Following CS student in Seoul National University, deeply passionate about Data Science
Ted Fujimoto 💡 @tedfujimoto
99K Followers 91K Following Co-CEO AsterAlpine Capital. Managing Dir EF International Advisors. Co-Founded @NewTechNetwork. Married to @Unleighshed
Data Engines @dataengines
355 Followers 393 Following Working on making the world safer for robots and humans. Holders of the world's 1st patent (2010) on distribution-free evaluation of noisy judges.
Lavrentiy @blyatzkrieg
598 Followers 1K Following
punctut @punctut
67 Followers 378 Following
iwes @iweswgy
73 Followers 378 Following
Ahmed Yousef @mennanour12
27 Followers 334 Following
David Almog @davidalmog25
2K Followers 2K Following Managerial Economics and Strategy Ph.D. student @KelloggSchool • Behavioral and Experimental Economics • AI-Human interactions • LV Raiders • Backpacking
Konika Karmokar @Freelencerkoni
64 Followers 726 Following Hello, I am Konika Karmokar. I have lots of skills like B2B Lead Generation, Bulk Email Collection, ASO, YouTube SEO, and social media etc
bizika @bizika7
17 Followers 347 Following
simrat hanspal @simsimsandy
79 Followers 422 Following Data scientist with a curious engineering mind| Tech Evangelist @Hasurahq
Rob May #BeCyberSmart @robmay70
20K Followers 9K Following ⭕ CyberSecurity Ambassador 💡#AI Thought Leader ⚙ Founder @ramsac_ltd 🎙️TEDx, Vistage & Keynote Speaker 📚Author | Human Firewall ⚡ #HarnessingAI #Infosec
Trevor Loy @trevorloy
17K Followers 2K Following VC investor emerging ecosystems @FlywheelVC. Lecturer entrepreneurship & VC @Stanford. Prev: BoD @NVCA; Mentor @KauffmanFellows; 3x founder; Chip design @Intel.
Margaretta Colangelo @realmargaretta
3K Followers 5K Following Leading AI Analyst - Subscribe to my AI In Healthcare Newsletter (52,000 subscribers)
Spencer @Superior_Kitsch
20 Followers 5K Following
David Stillwell @david_stillwell
4K Followers 2K Following Professor of Computational Social Science at Cambridge University Judge Business School.
Danielle Perszyk @drperszyk
84 Followers 264 Following Artificial Intelligence. PhD in Cognitive Science.
Oksana Vickers @oksanavickers
437 Followers 2K Following University of Chicago | Associate at UChicago XLab | Research on Tactical Nuclear Weapons, Emerging Tech Risk, and Ukraine/Russia | Ukrainian-American
ArpitBhardwaj9817 @bhardwaj9874475
6 Followers 982 Following
tao yuan @yuanttttao
4 Followers 50 Following
Tlamatiliztli @tlamatiliztli_
126 Followers 291 Following Humano. Práctica de atención plena. Cemanahuatl namantzin. Aumentado⌚🕑
aman chourasia @aman245_tweets
21 Followers 55 Following
Avi Yashchin @aviyashchin
1K Followers 1K Following CEO @ Subconscious. Data-driven founder +2x public exits. Ex-PM @ Engine No 1, Two Sigma & IBM Watson Research. My deviations are normal. Super-Dad, WIP-Human.
Roman Eng @NightFae007
0 Followers 140 Following
Mike Channon Ⓜ️ @XDA_Forum_Admin
6K Followers 5K Following Forum Admin at https://t.co/mFiBmgsI4b, Director at https://t.co/iH1LoXoajp
Aman Hanspal @hanspaa2017108
167 Followers 2K Following
Armando Vieira @Lidinwise
1K Followers 4K Following CTO MedgicalAI, dad, Deep Learning pioneer, blockchain enthusiast, flanêur. Author of the book "Business Applications of Deep Learning".
Ant A @AntDX316
690 Followers 880 Following The real envy shouldn't be the richest of this world but the envy of those resting in a peaceful afterlife. Play @Planetside2
Paul Clarke @plarke4
18 Followers 625 Following
(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K Following
Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | Pianist
Kyunghyun Cho @kchonyc
60K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).
Sasha Rush @srush_nlp
52K Followers 464 Following Professor, Programmer in NYC. Cornell Tech, Hugging Face 🤗 https://t.co/cZl0wTfqGz
Christopher Manning @chrmanning
126K Followers 114 Following Director, @StanfordAILab. Assoc. Director, @StanfordHAI. Founder, @stanfordnlp. Prof. CS & Linguistics, @Stanford. IP @aixventureshq. 🇦🇺 Do #NLProc & #AI. 👋
Anthropic @AnthropicAI
260K Followers 26 Following We're an AI safety and research company that builds reliable, interpretable, and steerable AI systems. Talk to our AI assistant Claude at https://t.co/aRbQ97uk4d.
Miles Brundage @Miles_Brundage
43K Followers 10K Following Policy research at @openai. I mostly tweet about AI, animals, and sci-fi. He/him. Views my own.
Tal Linzen @tallinzen
16K Followers 895 Following Professor @nyuling and @NYUDataScience, research scientist @GoogleAI
Yi Tay @YiTayML
29K Followers 97 Following chief scientist / cofounder @RekaAILabs 🫠 past: research scientist @google brain 🤯 currently learning to be a dad 🍼
Graham Neubig @gneubig
30K Followers 583 Following Associate professor at CMU, studying natural language processing and machine learning.
Jacob Andreas @jacobandreas
13K Followers 956 Following Teaching computers to read. Assoc. prof @MITEECS / @MIT_CSAIL (he/him). https://t.co/5kCnXHjtlY https://t.co/2A3qF5vdJw
Rosanne Liu @savvyRL
33K Followers 966 Following Cofounded & running @ml_collective. Host of Deep Learning Classics & Trends. Research at Google DeepMind. DEI/DIA Chair of ICLR & NeurIPS. Writing https://t.co/IbycyGfnDR
Felix Hill @FelixHill84
9K Followers 776 Following Research Scientist, Deepmind I try to think hard about everything I tweet, esp on 90s football and 80s music None of my opinions are really someone else's
Sara Hooker @sarahookr
39K Followers 7K Following I lead @CohereForAI. Formerly Research @Google Brain @GoogleDeepmind. ML Efficiency at scale, LLMs, @trustworthy_ml. Changing spaces where breakthroughs happen.
Zachary Lipton @zacharylipton
59K Followers 2K Following Professor: CMU/@acmi_lab, CTO / CSO: @AbridgeHQ, Creator: @d2l_ai & https://t.co/QQt98VNLUp, Relapsing 🎷
Yoav Artzi @yoavartzi
13K Followers 163 Following Research/prof @cs_cornell + @cornell_tech🚡 / https://t.co/9YnWry7yHs / https://t.co/3VmRSyYm2d / asso. faculty director @arxiv / building https://t.co/f9QkzO5kaC
Danish Pruthi @danish037
7K Followers 628 Following Faculty at Indian Institute of Science, Bangalore. PhD from @LTIatCMU.
Luca Soldaini 🎀 @soldni
6K Followers 1K Following I like tokens! Lead for OLMo data team at @allen_ai (makin Dolma 🍇), open source science fan, @QueerInAI organizer 🤖☕️🍕they/them
Matt Darling 🌐🏗.. @besttrousers
47K Followers 2K Following Senior Employment Policy Analyst @niskanencenter. Chief Neoliberal Shill 2023. Labor/behavioral economics and causal inference.
Brianna Wu @BriannaWu
159K Followers 8K Following Executive Director of @rebellionpac. Former Candidate for US House in MA. Software engineer. Bond dog proponent. 🏎🏍🏃🏻♀️🎮 [email protected]
Ryan Briggs @ryancbriggs
11K Followers 1K Following Raising kids & bread & grant money. Cleaning data & diapers & fish. EA (bed nets not light cone). Social scientist. https://t.co/g8teKfCf91
Eric S. Raymond @esrtweet
9K Followers 51 Following Yes, I *am* that ESR. Well, it's the question people usually ask.
Craig Citro @craigcitro
1K Followers 237 Following i like math and puns | research engineer @anthropicai; previously: @GoogleColab, Google Bigquery, @sagemath, number theorist
Natasha Jaques @natashajaques
25K Followers 1K Following Senior Research Scientist at @GoogleAI and Assistant Professor @uwcse. Social Reinforcement Learning in multi-agent and human-AI interactions. PhD from @MIT.
Aleksander Madry @aleks_madry
31K Followers 165 Following Head of Preparedness at OpenAI and MIT faculty (on leave). Working on making AI more reliable and safe, as well as on AI having a positive impact on society.
FAR AI @farairesearch
1K Followers 19 Following Ensuring AI systems are trustworthy and beneficial to society by incubating new AI safety research agendas.
James Fickel 🪷 @jamesfickel
2K Followers 374 Following
Hunar Batra @hunarbatra
2K Followers 2K Following DPhil/MSc CS @UniOfOxford | prev: aligning LLMs @AnthropicAI @NYUDataScience @stanford | Tweets are my own, not through a bot 🤖
Edward Rees @ERees01
53 Followers 228 Following Software Engineer @apolloaisafety, previously ML Team Lead @speechmatics
Orowa Sikder @OrowaSikder
1K Followers 304 Following the future could be amazing. let’s get to work | Research @AnthropicAI, ex: PhD @UCLCS
mrinank ⭐️ @MrinankSharma
823 Followers 435 Following alignment, poetry, soulmaking, devotion "live to the point of tears", camus
Emmanuel Ameisen @mlpowered
7K Followers 211 Following Research Engineer @AnthropicAI Previously: Staff ML Engineer @stripe, Wrote BMLPA by @OReillyMedia, Head of AI at @InsightFellows, ML @Zipcar
Erik Schluntz @ErikSchluntz
2K Followers 238 Following Member of Technical Staff at Anthropic Co-founder at @CobaltRobotics Co-founder at Posmetrics (acquired) GoogleX, @SpaceX, @Harvard EE '15, Forbes 30u30 '18
Adam Jermyn @AdamSJermyn
1K Followers 188 Following AI Interpretability & Safety @AnthropicAI. Previously at @FlatironInst @FlatironCCA, @KITP_UCSB, PhD @Cambridge_Uni, BS @Caltech.
Francis Rhys Ward @F_Rhys_Ward
179 Followers 388 Following PhD Student | AI Safety | Imperial College London.
Internal Tech Emails @TechEmails
523K Followers 900 Following Internal tech industry emails that surface in public records. 🔍
Eric Gilliam @eric_is_weird
3K Followers 998 Following I write about how 20th C. R&D orgs operated and advise new R&D orgs @GoodSciProject | Formerly @Stanford I want to help people start historically great labs
sigfig @sigfig
9K Followers 744 Following i saw a space ship blow up once and immediately decided i wanted to get in one
Sunny Son @__sunnyson__
30 Followers 201 Following
Ekin Akyürek @akyurekekin
2K Followers 724 Following graduate student in computer science @MITEECS/@MIT_CSAIL
Egg Syntax @eggsyntax
251 Followers 296 Following “Believe me, my young friend, there is nothing - absolutely nothing - half so much worth doing as simply messing about in code."
google bard @deepfates
26K Followers 3K Following walk it like i talk it. walk it walk it like i talk it
Will Fithian @wfithian
4K Followers 876 Following UC Berkeley Statistics. Interests in multiple testing, selection bias, and post-selection inference. Belated interest in AI alignment. Views my own.
George McGowan @GjMcGowan
1K Followers 189 Following
rose linke @roselinke
370 Followers 1K Following writer & editor. unkemptable, hobbiful. wool gathering in the west.
Debora Allen @debora_allen1
1K Followers 699 Following Board Director @SFBART. CFO, biz owner, inactive CPA. Here for the accountability, transparency, oversight, and chocolate cake. @GarryTan’s calling-BS sister
David Stutz @davidstutz92
3K Followers 1K Following Research scientist @DeepMind working on robust and safe AI, previously @maxplanckpress, views my own.
Francesca Toni @fra_toni
295 Followers 98 Following RAEng/JP Morgan Chair and ERC Advanced holder. @imperialcollege, @ICComputing. Founding lead of @arg_cl. #AI @safe_trusted_ai @AI4HealthCentre. #XAI.
Erik Baker @erikmbaker
13K Followers 2K Following I teach history of science & labor at Harvard. Proud @hgsuuaw alum, associate editor @thedrift_mag. Writing MAKE YOUR OWN JOB for @harvard_press.
Aaron Bergman 🔍 �.. @AaronBergman18
2K Followers 1K Following 👎: suffering | 👍: EA, AI alignment, decoupling, R, cringe, amateur pharmacology + programming | Georgetown ‘22 (math+econ+phil) | Career status: 🤷♂️
early modern boy-actr.. @economeager
43K Followers 5K Following Despite appearances I am an applied econometrician. Also trying to write art things at https://t.co/UBlzYddnTE 🏳️⚧️🏳️🌈🇦🇺
Abundant Housing LA @AbundantHousing
8K Followers 2K Following Abundant Housing LA is a grassroots organization working to solve SoCal’s housing crisis by advocating for more housing at all levels of affordability. Join us!
Vienna Teng @viennateng
10K Followers 293 Following Gather your threads, make them hum with new music. Tour dates incl. climate action workshops at https://t.co/LXvFVFwKKK
Put This On @putthison
43K Followers 357 Following A blog about dressing like a grownup. From founder @JesseThorn and writers @DieWorkwear & @PAnderson2. https://t.co/j5iQQPozkc and https://t.co/cBilVpW2Fd
Joe Benton @JoeJBenton
248 Followers 63 Following Alignment Science at Anthropic | Previously PhD at University of OxfordTrends for United States
You might like
