hoagy @HoagyCunningham
alignment attempter London Joined April 2022-
Tweets103
-
Followers152
-
Following161
-
Likes845
Makes a lot of sense but still interesting to see. Wonder if you could remove this part of representation, training for non-toxicity even when residual stream is in that region, measuring success by difficulty of training away the change - has anyone tried to do similar?
Makes a lot of sense but still interesting to see. Wonder if you could remove this part of representation, training for non-toxicity even when residual stream is in that region, measuring success by difficulty of training away the change - has anyone tried to do similar?
First paper, finally released🥳🥰
Alignment strategy generator! "New top secret MIRI agenda hinted at. All we know is it involves {NN arch}, {math area} & {phil topic}". Fill at random & distribute..
Harshal Nandigramwar @hnanacc
343 Followers 247 Following ai @intel labs, prev: ai @cariad_tech, masters @Uni_Stuttgart, building @todackcom, @themelioaiMatthew Clarke @Matthew05049818
0 Followers 2K FollowingStellSoul_3 @stellsoul92816
19 Followers 484 FollowingAleks Petrov @AleksPPetrov
166 Followers 446 Following PhD student at @OxfordTVG, @UniofOxford. I am working on Trustworthy Machine Learning, championing friendly AI and polite robotsKai Arulkumaran @kaixhin
7K Followers 5K Following Researcher, programmer, DJ, transhumanist. @ArayaGlobal; formerly @imperialcollege/@MSFTResearch/@TwitterResearch/@facebookai/@DeepMind/@nnaisense.Krystof Mitka @krystof_mitka
120 Followers 509 Following Currently completing undergraduate double degree in Applied Mathematics and Computer Science in 🇳🇱Gabriele Sarti @gsarti_
2K Followers 2K Following PhD Student @GroNLP 🐮, core dev of @InseqLib (https://t.co/tTjrg26ygQ). Interpretability ∩ HCI ∩ #NLProc. Prev: @AmazonScience, @Aindo_AI, @ItaliaNLP_Lab.Bradley Brown @brad19brown
82 Followers 280 Following Professional bit rearranger 👨💻 | CS PhD Student at the University of OxfordAdrián F. Amil @adriamilcar
435 Followers 2K Following PhD candidate in neuroAI at @DondersInst. Working on comp neuro and DL theory. Also into drone photogrammetry, filmmaking, philosophy, and space exploration.Rishi @rishih2o
55 Followers 1K FollowingAlpaca 🦙 (e/delve) @LeetAlpaca3
211 Followers 3K Following Servant of the future. If I blocked you, I probably didn’t mean to. (Big block list from long ago) Tweets are my own.Technical AI Safety C.. @tais_2024
128 Followers 28 Following On 5th-6th April 2024, TAIS will bring together leading AI safety experts in Tokyo to discuss how to make AI safe, beneficial, and aligned with human values.Harry Mayne @HarryMayne5
119 Followers 425 Following Interpretability @oiioxford @uniofoxford. PhD student. Previously @Cambridge_Uni_original @original1126948
9 Followers 1K FollowingMikołaj Piórczyńsk.. @AjPiorczynski
4 Followers 297 FollowingVedang Lad @vedanglad
218 Followers 357 Following MIT, computer science, physics, mathematics, art, photography, cross country, track and fieldEric J. Michaud @ericjmichaud_
1K Followers 771 Following PhD student at MIT. Trying to make deep neural networks among the best understood objects in the universe. 💻🤖🧠👽🔭🚀Sun 乌龟 💖 @suntzoogway
2K Followers 1K Following Shepherd the finite through the local minima of imperfect information/ Aligning all beings w/ the lovepill I'm developing/ Putting cult back into cultureWes Gurnee @wesg52
3K Followers 198 Following Optimizer @MIT @ORCenter PhD student thinking about Mechanistic Interpretability, Optimization, and Governance.Jakub Smékal @jakub_smekal
500 Followers 1K Following I'm researching how to understand and control large-scale AI systems with physics and cognitive science. PhD student @StanfordJammehpapa @jammehpapa154
428 Followers 4K Following Believe in your lord Jesus Christ And A Lover Of Jesus Christ ✝️🙏Ebrimajatt831 @ebrimajatt45935
621 Followers 5K Following Jesus Christ is the king of all kings and he shall come back soon ✝️✝️🙏Andrew Lee @a_jy_l
262 Followers 435 Following CS PhD student @UMich advised by @radamihalcea. Prev Intern: @MetaAI x2, @MSFTResearchAlex Makelov @AMakelov
122 Followers 147 Following SERI MATS, prev @MIT @Harvard Creator of https://t.co/yKCQG7hqPm Machine learning, theoretical computer science, math.Dave @Dave73387426037
678 Followers 5K FollowingɢʀɛǟȶK̶i̶n̶g�.. @GreatKingCnut
472 Followers 2K Following But the sea came up as usual and disrespectfully drenched the king's feet and shins. I want the good ending pls, not the bad one. transhumanist, ML, RL, lmaoCharlie O'Neill @charles0neill
344 Followers 1K Following Maths + Comp Sci + Economics @ ANU. Using mech interp to build hierarchical planning modules into transformersJosh @JoshPurtell
727 Followers 2K Following ML Researcher. Ex: Cyber microexit, Yale Math. Hiring in ML Ars longaArjun Panickssery is .. @panickssery
1K Followers 2K Following Researching scalable oversight @MATSprogram | prev @METR_Evals @ai_risks | spaced repetition | AI safety | https://t.co/p887k6EsFsLucre Snooker @LucreSnooker
3K Followers 1K Followingwombo combo @marquisedgelord
88 Followers 799 Following cured count keyserling's insomnia, woke kant from his dogmatic slumber, helped ur mum cum; my views represent the coherent extrapolated volition of humanitymebubo @mebubo
10 Followers 465 FollowingAI Safety Institute @AISafetyInst
529 Followers 29 Following We’re building a team of world leading talent to tackle some of the biggest challenges in AI safety - come and join us.typedfemale @typedfemale
23K Followers 479 Following a really exciting new account "have you ever though you might be like scott alexander? very smart, but can't do math" - anonEric J. Michaud @ericjmichaud_
1K Followers 771 Following PhD student at MIT. Trying to make deep neural networks among the best understood objects in the universe. 💻🤖🧠👽🔭🚀Wes Gurnee @wesg52
3K Followers 198 Following Optimizer @MIT @ORCenter PhD student thinking about Mechanistic Interpretability, Optimization, and Governance.main @main_horse
8K Followers 474 Following AGI Believer. Haven't applied @OpenAI. Likes are not always endorsement.Andrew Lee @a_jy_l
262 Followers 435 Following CS PhD student @UMich advised by @radamihalcea. Prev Intern: @MetaAI x2, @MSFTResearchSamuel Marks @saprmarks
696 Followers 79 Following Postdoc studying interpretability for AI safety under @davidbau. PhD in math from @harvard. Previously director of technical programs at https://t.co/FxRv4QgERO.Andy Lapsa @AndyLapsa
6K Followers 51 Following CEO/Co-Founder @stoke_space - Husband/dad/engineer building 100% reusable rocketsKonstantin Mishchenko @konstmish
4K Followers 564 Following Research Scientist at Samsung AI Center Outstanding Paper Award @icmlconf 2023 Action Editor @TmlrOrg I tweet about ML papers and mathAlex Makelov @AMakelov
122 Followers 147 Following SERI MATS, prev @MIT @Harvard Creator of https://t.co/yKCQG7hqPm Machine learning, theoretical computer science, math.Lucre Snooker @LucreSnooker
3K Followers 1K FollowingSpaceX @SpaceX
34.5M Followers 113 Following SpaceX designs, manufactures and launches the world’s most advanced rockets and spacecraftWei Dai @weidai11
7K Followers 82 Following wrote Crypto++, b-money, UDT. thinking about existential safety and metaphilosophy. blogging at https://t.co/mBVFhriJVfLuke Muehlhauser @lukeprog
8K Followers 293 Following Open Philanthropy Senior Program Officer, AI Governance and PolicyLucia Quirke @lucia_quirke
212 Followers 81 Following Neural network interpretability researcher at EleutherAIRFH🦎👁🗨�.. @hollowearthterf
38K Followers 985 Following Artemis Cultist. Loosh Harvester. Peattard. At eternal war with Rome. Infinite love is the only truth everything else is illusion!!!!!🇨🇳🏴🇮🇱🇦🇷Buck Shlegeris @bshlgrs
1K Followers 199 Following CEO at Redwood Research, working on technical research for AI safety.Joe Benton @JoeJBenton
248 Followers 63 Following Alignment Science at Anthropic | Previously PhD at University of OxfordLauro @laurolangosco
883 Followers 677 Following Working on AI safety and science of deep learning @CambridgeMLG. Here to discuss ideas and have fun.Herbie Bradley @herbiebradley
690 Followers 602 Following a generalist agent | AI governance & safety @AISafetyInst | PhD student @Cambridge_Uni @AI4ER_CDT | formerly @AiEleutherChris Meserole @chrismeserole
3K Followers 775 Following Executive Director, Frontier Model Forum | Former Director, Brookings A.I. & Emerging Tech InitiativeDavid Krueger @DavidSKrueger
13K Followers 4K Following Cambridge faculty - AI alignment, deep learning, and existential safety. Formerly Mila, FHI, DeepMind, ElementAI, AISI.Scott Manley @DJSnM
513K Followers 538 Following Internet Rocket Scientist, Gamer, Astronomer, Dad, Scotsman. Makes videos about science and video games.... at the same time! https://t.co/5p7T8YmtuCDaniel Murfet @danielmurfet
699 Followers 508 Following Mathematician at the University of Melbourne. Working on Singular Learning Theory and AI alignment.Alex Turner @Turn_Trout
997 Followers 39 Following Research scientist on the scalable alignment team at Google DeepMind. All views are my own.Ryan Kidd @ryan_kidd44
945 Followers 822 Following Co-Director at @MATSprogram | Board Member at https://t.co/26oYPZwxVx | PhD in physics | Accelerate AI alignment + build a better future for allQuintin Pope @QuintinPope5
3K Followers 186 Following ML researcher focusing on natural language modeling and alignment.Jesse Hoogland @jesse_hoogland
857 Followers 1K Following Researcher and decel working on developmental interpretability. Executive Director @ TimaeusLewis Hammond @lrhammond
753 Followers 1K Following Research Director @coop_ai / DPhil Candidate @CompSciOxford and @HertfordCollege / Affiliate @FHIOxford and @GovAI_shako @shakoistsLog
6K Followers 2K Following real truth about it is, no one gets it right https://t.co/1Qoefmwmw2Tanishq Mathew Abraha.. @iScienceLuvr
54K Followers 1K Following PhD at 19 | Founder and CEO at @MedARC_AI | Research Director at @StabilityAI | @kaggle Notebooks GM | Biomed. engineer @ 14 | TEDx talk➡https://t.co/xPxwKTq6QbMikhail Parakhin @MParakhin
17K Followers 21 FollowingJamie Bernardi @The_JBernardi
915 Followers 655 Following Doing AI Governance research, ex-Co-Founder, Bluedot Impact. Climber, guitarist and sporadic musician. he/him.Yi Ma @YiMaTweets
71K Followers 123 Following Chair Professor in AI, Director of IDS, Head of CS, HKU; Professor of EECS, Berkeley; Author of Book: High-Dim Data Analysis, https://t.co/gwaqMJp8av.Tesla AI @Tesla_AI
148K Followers 14 Following Developing & deploying autonomy at scale in vehicles, robots & moreThe Suburban Pirate @suburbanpirate
941 Followers 674 Following East Dulwich Retrofit Coordinator. #1stMillionHPLogan Smith @loganriggssmith
29 Followers 12 Following Aligning AIs before they align us. 🤖🎯 #SafeSkynet#1 Rudin Prologue Sta.. @Robert_AIZI
67 Followers 115 Following Learning AI Safety, blogging at https://t.co/VQL0UnGSFi, making bad jokes here. Math PhD. Any pronouns.Marius Hobbhahn @MariusHobbhahn
2K Followers 994 Following Director/CEO at Apollo Research @apolloaisafety Ph.D. student of Machine Learning @PhilippHennig5; AI safety/alignmentStefan Schubert @StefanFSchubert
28K Followers 2K Following Philosophy, psychology, and effective altruism.Emotional to be sharing this finally. It's so incredibly special to me. It's a piece that muses on reincarnation, extra-dimensional perspectives, and the interconnectedness of lives. The music is 'Back to body' by Bethany Ley, also released today.💕(1/?)
@icantsay Yeah my suspicion is that emotions are fat soluble, and if you eat to deal with them, they come back in force when the fat burns off
Future House now has a sign so we can know when the next train is. It’s cool when people just build stuff like this.
For some reason I had to turn Andrew Cuomo’s mad coronavirus poster into a Jenny Holzer installation:
@DalrympleWill Don't miss the perfect opportunity to tweet Sala Francés' painting the Expulsion of the Jews from Spain! museodelprado.es/en/the-collect…
Data is way more like oil now than when that was originally said
why do they call them down comforters and not *ducks for cover*
@tsungxu @tferriss @lexfridman @joerogan lol, so you're saying I should stay in SF?
a witch has put me under a curse of silence about anything that is remotely unpleasant & i dont feel like talking about
That so many people buy into this reflects: (i) how we as a country are now so far removed from manufacturing that we understand so little of it (as demonstrated here and many similar replies), and (ii) the difference between ideas and execution.
When I say that China screwed Elon Musk, this is exactly how they did it:
The rebranding of the trees as “the forest” may be the most successful marketing campaign of all time.
The rebranding of linear algebra as "artificial intelligence" may be the most successful marketing campaign of all time.
AI-generated sad girl with piano performs the text of the MIT License
@karlusss Once expounded at length on this in the comments of an American linguistics blog: notoneoffbritishisms.com/2019/08/26/bal…
who called it the CFAR handbook and not What to Expect When You're Expecting
*thinking real hard about what data structure i should use in pytorch* hmm... i think i'll go with a tensor this time