Szymon Tworkowski @s_tworkowski
minimizing perplexity @xAI | prev. @GoogleAI @UniWarszawski | LongLLaMA | long-context LLMs and math reasoning | scaling maximalist syzymon.github.io Palo Alto Joined November 2021-
Tweets485
-
Followers4K
-
Following502
-
Likes344
Grok is going multimodal! It’s incredible to see how fast a small, focused team can move. Kudos to the amazing team @xai that made this possible x.ai/blog/grok-1.5v
the best ML researchers don't think that anything is beneath them. the worst ML researchers think that they are above everything "I have a PhD, why am I spending time figuring out how to resolve S3 paths?" vs "I am trying to run an experiment. I will resolve the s3 paths"
Excited to share our latest work on improving LLM pre-training! 🚀 The amazing @yuzhaouoe et al. found that focusing on how pre-training sequences are composed and attended over can significantly improve the generalisation properties of LLMs on a wide array of downstream tasks,…
A glimpse over our recent progress - exciting things to come!
Grok-1 314B running on M2 Ultra 🚀
Grok-1 314B running on M2 Ultra 🚀
Livestream of @neuralink demonstrating “Telepathy” – controlling a computer and playing video games just by thinking
Livestream of @neuralink demonstrating “Telepathy” – controlling a computer and playing video games just by thinking
x.ai/blog/grok-os Grok-1 is open sourced. Releasing Grok-1 increases LLMs' diffusion rate through society. Democratizing access helps us work through the technology's implications more quickly and increases our preparedness for more capable AI systems. Grok-1 doesn't pose…
x.ai/blog/grok-os Grok-1 is open sourced. Releasing Grok-1 increases LLMs' diffusion rate through society. Democratizing access helps us work through the technology's implications more quickly and increases our preparedness for more capable AI systems. Grok-1 doesn't pose…
Language models today are trained to reason either 1) generally, imitating online reasoning data or 2) narrowly, self-teaching on their own solutions to specific tasks Can LMs teach themselves to reason generally?🌟Introducing Quiet-STaR, self-teaching via internal monologue!🧵
The memory in Transformers grows linearly with the sequence length at inference time. In SSMs it is constant, but often at the expense of performance. We introduce Dynamic Memory Compression (DMC) where we retrofit LLMs to compress their KV cache while preserving performance…
Starship reached orbital velocity! Congratulations @SpaceX team!!
Do you want to work for @xai in London? Now you can. We're looking for software engineers. Apply if you want to get stuff done, work with smart people, and get grilled in one of my coding interviews. Backend & data: boards.greenhouse.io/xai/jobs/42769… Full-stack: boards.greenhouse.io/xai/jobs/42769…
Super happy that OpenWebMath was accepted to ICLR 2024! When we first submitted the paper to the conference, I was very unsure whether it would get in. In my experience, academia has a strong preference towards works with clever ideas, lots of math, and fancy algorithms or…
NEWS: Elon Musk announced tonight that the first human implanted with @neuralink’s brain chip has made a full recovery. The patient is able to control a mouse using only their thoughts. Incredible achievement!
Lots of instruction tuning data out there...but how to best adapt LLMs for specific queries? Don’t use ALL of the data, use LESS! 5% beats the full dataset. Can even use one small model to select data for others! Paper: arxiv.org/abs/2402.04333 Code: github.com/princeton-nlp/… [1/n]
Captspeedlol @hnxinsh44719996
5 Followers 118 FollowingJoey prince @joveeeeng
7K Followers 14 Following Follow and Dm me and ask to join the VIP ! gentleman only ...RK R WOULD SHORT TRIC.. @would_rk
5 Followers 58 FollowingMikhail Matveenko @MikhailMaTV
17 Followers 428 FollowingAmbient Earth @AmbientEarthv
16 Followers 77 Following Ambient Earth - Improve focus, relaxation and tranquility with VirtuScapes that harness the soothing sounds of the earth. 🌿🎶 #ambientearth #focus #rest #peaceSasha Veronika @Sasha1_veronika
315 Followers 2K Following I LOVE MY COUNTRY 🇺🇦❤️AND WILL FIGHT FOR MY COUNTRY 🇺🇦🦾TSA @dawg1989
41 Followers 345 FollowingMax` @Max292618236199
0 Followers 37 FollowingM rathnakar Reddy @MrathnakarRedd3
46 Followers 603 Followingopposites Reasonable @OppositesR99152
2 Followers 664 FollowingLela Bolkvadze @Lela1681
713 Followers 6K Following PhD in Education, interested in Teaching/Learning process, Cognitive Psychology, Human Relations, Social Sciences, Travelling, Photography, Naturelaretta @laretta24664281
651 Followers 477 FollowingQuant @QuantEmperor
452 Followers 596 Following Data Scientist with passion for AI, Quantitative Finance & Trading. My posts and articles are my own personal views and experiments; not financial advice.Vesnt Luca @VesntL
371 Followers 4K FollowingDarren @Darrenmay08
18 Followers 114 FollowingAndrew Thompson @AndrewT65390500
245 Followers 205 Following Christian Conservative 🍊#1a + #2a = God-given non-negotiable rights to reject totalitarianism and tyranny.straatman @straatman
816 Followers 165 Following Impact investor | Partner at https://t.co/uXdYBYHm6t | Co-founder https://t.co/nbyltA9Zbc - https://t.co/NkBRekIUu3 - https://t.co/mMiaGlOmNt | 🏃🏻♂️🎾 🏔️🚴♂️Kaiying Hou @kaiyinghou
9 Followers 134 FollowingThiosmoyth @thiosmoyth39964
5 Followers 42 Followingfo chen @fochen795010
24 Followers 324 FollowingSahil Antil @oxshitantil
7 Followers 391 Following Founder @kavachbuilders @foodkavach @arqaifashion[email protected] @aprilmvjdf25614
2 Followers 33 FollowingHURRICANE EVA! @evamagazine
8K Followers 8K Following DJ Eva aka #HurricaneEva a triple threat. DJ NFL “Denver Broncos Cheerleaders.” Author "Lies Chelsea Handler Told Me.”CEO, creator & host of global #HighFive.King of Bangis @leegend2__
29 Followers 130 FollowingASTUTE @ASTUTE0S
13 Followers 133 Following Bringing you the latest in global happenings, from breaking news to insightful analysis. Stay informed with our Twitter news feed! #StayTuned #BreakingNews #CuSteven Antipass @AntipassSt86024
11 Followers 94 Followingsixeyes @sixeyesdental
4 Followers 42 Following Sixeyes will be the bridge between an IRL well established dental business and web3. Powered by its SPL token $SIXEYEZ https://t.co/YCRGtvdBePMAB氏 @MAB1791652
1 Followers 36 Followingkahky @Kahky
328 Followers 448 FollowingJP Phillips @phillips50075
2 Followers 33 FollowingMaz Nejad @maznejad
44 Followers 51 Following Manager @AWS. Agile engineer at heart. Research-driven seeker of truth in a world of deceptionســ༅ــراب �.. @xxxy4_
2K Followers 2K Following ⠀ ⠀「 ᷂نُـور ᷂الصبايّا ᷂بسـمة ᷂الدار ᷂وَالحي 」 ᷂مُتيمة ᷂بالنصر🖤🧸Weloop @Weloop_official
9 Followers 72 Following Download “Weloop” to be a part of your friends circleAqueel @AqueelMiq
8K Followers 224 Following Building the product development infrastructure @ https://t.co/9Rq2WToSM8Heinrich Kuttler @HeinrichKuttler
2K Followers 695 Following Member of Founding Team @InflectionAI. Ex @FacebookAI, @DeepMind, @Google, @LMU_Muenchen, PhD math-ph. Opinions my own. (Can be yours for a small fee.)John Yang @jyangballin
2K Followers 447 Following CS/NLP MS student @princeton_nlp Previously @Berkeley_EECSAditya Paliwal @VastoLorde95
521 Followers 85 Following I only read books that have pictures in themKarol Hausman @hausman_k
22K Followers 141 Following @Physical_int ex: researcher @GoogleAI/@DeepMind, adj. Prof. @Stanford. Into robots, AI, NBA, philosophy, soccer and almond croissants. 🇵🇱🇺🇸Haotian Liu @imhaotian
6K Followers 396 Following building intelligence @xAI, creator of #LLaVA, cs @UWMadison, prev @MSFTResearchShunyu Yao @ShunyuYao12
7K Followers 857 Following Language agents (ReAct, Reflexion, Tree of Thoughts) for digital automation (WebShop, SWE-bench, SWE-agent)Tiffany Poon @Tiffanypianist
7K Followers 1 Following Classical pianist. Be kind. Keep striving! Classical Chats 🎙️ @withclassical 🎶Nikolay Savinov 🇺�.. @SavinovNikolay
1K Followers 0 Following Research Scientist at @GoogleDeepMind Work on LLM pre-training in Gemini ♊ 10M context length in Gemini 1.5 Pro 📈Saeed Maleki @MalekiSaeed
466 Followers 109 FollowingDavid @DavidSHolz
54K Followers 5K Following founder @midjourney, prev founder leap motion, nasa, max planckfinbarr @finbarrtimbers
8K Followers 647 Following large models @midjourney. ai hot takes at https://t.co/pSeuTpK0xO.Marc Andreessen 🇺�.. @pmarca
1.4M Followers 24K Following Techno-optimist. E/acc. Technology brother. Move Fast and Make Things. p(Doom) = 0; p(“1984”) = not 0.Yangqing Jia @jiayq
12K Followers 263 Following Founder @leptonai. @UCBerkeley alumni. ex @google & @facebook. ex vp @AlibabaGroup. Open source work on caffe, @pytorch, @tensorflow, & @onnxai.Roger Grosse @RogerGrosse
10K Followers 750 FollowingSuna Said @suna_said
1K Followers 199 Following Founder and CEO of @NimaCapital, a family office which invests in all asset classes, across geographies, industries and stages. Empowering women in business.otaviogood @otaviogood
727 Followers 82 FollowingAlex Kontorovich @AlexKontorovich
24K Followers 805 Following Mathematician (Distinguished Professor of #Math at @RutgersU). Here to learn about research, education, and community. Let’s build something together.Michal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMindChelsea Sierra Voss @csvoss
10K Followers 1K Following engineeress ✨ Member of Technical Staff @openai serious play // notice your curiosityAlbert Gu @_albertgu
9K Followers 90 Following assistant prof @mldcmu. chief scientist @cartesia_ai. leading the ssm revolution.Siyan Sylvia Li ✨ @Sylvia_Sparkle
1K Followers 503 Following 1st year PhD @columbianlp • Prev @stanfordnlp @GeorgiaTech • Weird Little Guy Academic • NLP, Dialogue Systems • Caffeine GremlinDawn Song @dawnsongtweets
29K Followers 840 Following Professor in Computer Science at UC Berkeley; Research in AI, Security, Blockchain; Serial entrepreneurDeepSeek @deepseek_ai
4K Followers 0 Following Unravel the mystery of AGI with curiosity. Answer the essential question with long-termism.chang ma @ma_chang_nlp
317 Followers 796 Following Ph.D student @HKUNLP, previously @PKU1898, I work on the intersection of #AI4Science and NLPSholto Douglas @_sholtodouglas
15K Followers 857 Following Scaling Gemini @Deepmind - working towards intelligence too cheap to meterAGI House @agihouse_org
13K Followers 412 Following Accelerating humanity's transition to AGI & honoring the greatest AI founders and researchers of our time @ https://t.co/1lJUc58gZJAllen (Simian) Luo @SimianLuo
2K Followers 438 Following Researcher. Research in Generative AI. Diffusion Models. Consistency Models. Inventor of LCM. ⚡️Author of LCM-LoRA 🚀 Boost GenAI into the Real-Time era.Yijing @Yijing_001
107 Followers 289 Followingjack morris @jxmnop
10K Followers 762 Following getting my phd in nlp @cornell_tech 🚠 // academic optimist // tweeting from the snack aisle at trader joesJohnny Ho @randomjohnnyh
3K Followers 175 Following Cofounder, chief strategy officer @perplexity_ai. Former high frequency trader, competitive programmer.Yongchao Zhou @Yongchao_Zhou_
528 Followers 301 Following Build Intelligence @xai | ML PhD @UofT @VectorInst | Prev. @GoogleAI @GoogleDeepMind | Working on LLMsNoah Smith 🐇🇺�.. @Noahpinion
321K Followers 1K Following Writes about economics, posts about rabbits. For serious opinions/analysis, read my blog: https://t.co/KfUxUlCYPzBindu Reddy @bindureddy
124K Followers 339 Following CEO of @abacusai, using Gen AI to build Applied AI and LLM agents and systems at scale, ex-AWS / Google, passionate about human behavior and open-source AGIJuntang @archanfel_anoth
242 Followers 256 Following xAI grok, ex-OpenAI, Working on LLM (GPT4, GPT4-turbo, DaLLE 3, OpenAI Embedding v3)Kanjun 🐙🏡 @kanjun
17K Followers 487 Following understanding human & machine minds to build a creative abundant future. CEO @imbue_ai. support founders @outsetcap. co-organize https://t.co/H1aXYk96ja.Huizhuo Yuan @HuizhuoY
726 Followers 914 Following Graduate student @UCLA AGI lab, Researcher on LLMs, Diffusion Models, Reinforcement Learning, Games and AI for Science. Opinions are my own.Gabriel Ilharco @gabriel_ilharco
4K Followers 1K Following Building cool things @xAI. Prev. PhD at UW, Google AI🚨 Tesla FSD 12 is running in Europe (Germany) and Tesla is giving demos to regulators 🚨 $TSLA
Having a dinner with friends who work at other self driving companies, I am the only one arrived there with self driving. 😆
Pierwsze 24 lata życia mieszkałem o kilkaset metrów stamtąd. Niezliczone zeszyty, ołówki i długopisy od podstawówki po magisterium na MIM kupowałem właśnie tam.
Jestem z Mokotowa i ten niewielki sklep papierniczy jest w tym miejscu odkąd pamiętam. Na przeciwko Szkoły Głównej Handlowej i tuż obok dawnego Aresztu Śledczego na Rakowieckiej. Dziś dowiedziałam się, że działa nieprzerwanie od 1937 r.! Do setki trochę brakuje - ale jeśli…
Among the coolest projects I helped with at Stanford. The key idea is very simple: a pragmatic response in one context is something you'd rarely say in other contexts. This basic principle lets LMs teach themselves to generally follow constitutions but has many cool implications
Constitutional AI showed LMs can learn to follow constitutions by labeling their own outputs. But why can't we just tell a base model the principles of desired behavior and rely on it to act appropriately? Introducing SAMI: Self-Supervised Alignment with Mutual Information!
Llama 3 was trained using intra-document causal masking, as suggested by @yuzhaouoe's paper "Analysing The Impact of Sequence Composition on Language Model Pre-Training"! 🚀🚀🚀 arxiv.org/abs/2402.13991
@yoavgo While working on (arxiv.org/abs/2403.09636) we discovered that we're able to retain many metrics including perplexity and many downstream tasks for very high compression ratios. Then we evaluated on MMLU and the score was terrible. From that point on our goal changed to getting…
🎉 Exciting news! Our #MathVista is excelling with the latest advances in vision-language models (VLMs). Grok-1.5V by @xai achieves a 52.8% score, surpassing leading models such as GPT-4V, Claude 3 Opus, and Gemini Pro 1.5! 🔗 Visit our project page: mathvista.github.io 👀…
Tesla FSD v13 will likely be grokking language tokens. What excites me the most about Grok-1.5V is the potential to solve edge cases in self-driving. Using language for "chain of thought" will help the car break down a complex scenario, reason with rules and counterfactuals, and…
Achieved unprecedented levels of American Dad on this vacation. I've boarded a plane with my driving license, I've answered to 'papa bear', I've lugged around a trolly of beach stuff... I've attended a time-share presentation. I'm deep in the trenches of american capitalism rn
NeurIPS introduces a track dedicated to advancing kids of rich parents even more than they already are
Just a beginning. Multimodal understanding and generation capabilities will be rapidly improving. DM open, come and join us!
Invisible to you all but an interesting change to X is that we rebuilt the entire trends system from scratch. All of the new Grok trends are generated on just two 32 core cpu machines. It's incredibly simple and efficient. While we are bringing you tonnes of new features, a lot…
Grok is going multimodal! It’s incredible to see how fast a small, focused team can move. Kudos to the amazing team @xai that made this possible x.ai/blog/grok-1.5v
This is just the beginning! 🚀
we're hiring designers, engineers, product, data, infra, and ai tutors - join us! x.ai/careers
come join us where everyone has a shovel!
we're hiring designers, engineers, product, data, infra, and ai tutors - join us! x.ai/careers
the best ML researchers don't think that anything is beneath them. the worst ML researchers think that they are above everything "I have a PhD, why am I spending time figuring out how to resolve S3 paths?" vs "I am trying to run an experiment. I will resolve the s3 paths"