Roberta Raileanu @robertarail
Research Scientist @Meta & Honorary Lecturer @UCL. ex @DeepMind | @MSFTResearch | @NYU | @Princeton. New York, NY Joined April 2013-
Tweets979
-
Followers4K
-
Following1K
-
Likes4K
Really cool to see the community building amazing things on top of Llama3 models!
Really cool to see the community building amazing things on top of Llama3 models!
Had a great time during our discussion, thanks again for having me!
Had a great time during our discussion, thanks again for having me!
self-improvement/"self-play"/continual interaction/feedback with other AI's and humans is likely the fastest path to AGI - where the latter is not a single agent but rather a community/population of intelligent agents. No intelligent agent, at any level (from insects to humans)…
self-improvement/"self-play"/continual interaction/feedback with other AI's and humans is likely the fastest path to AGI - where the latter is not a single agent but rather a community/population of intelligent agents. No intelligent agent, at any level (from insects to humans)…
Here is my selection of papers for today (27 Feb) on Hugging Face MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Check out the generative vision related release too meta.ai/?icebreaker=im… Imagine Flash generates the image as you type You can also "Animate" your images! (technique based on Emu Video emu-video.metademolab.com) Kudos to the team for putting this out :)
Frontier level Tool Calling now live on @GroqInc powered by Llama 3 🫡 Outperforms GPT-4 Turbo 2024-04-09 and Claude 3 Opus (FC version) in multiple subcategories At 300 tokens/s 🚀 I've personally been working on this feature, and man, the new Llama is good!
Excited to release a preview version of Llama3 with superb performance to the community! More to come soon!
Excited to release a preview version of Llama3 with superb performance to the community! More to come soon!
Congrats to the @AIatMeta team on Llama 3 🤯🤯 It is by FAR the best open source model i've played with! Run your personal llama 3 in a Lightning Studio now... let me know what you think about the model! lightning.ai/lightning-ai/s…
very early LMSys Arena results peg llama3-70B at 5th place (the variance is still pretty high, so it can jump up or down a bit). This is so exciting. Can't wait to see how the 405B fares once it is released. chat.lmsys.org/?leaderboard
Preliminary testing on my agent benchmark (based on github.com/aymeric-rouche…): Llama3-70B-Instruct is on par with GPT4! 🤯🤯 cc @lvwerra
And the team keeps growing! This time seeking more established researchers keen to join us in exploring the cutting edge of gaming and AI research 🎮🤖
And the team keeps growing! This time seeking more established researchers keen to join us in exploring the cutting edge of gaming and AI research 🎮🤖
Arena ELO graph updated with new models. Llama 3 70b looks impressive, but the 8b Instruct version is pure madness: it outperforms GPT-3.5, Claude 2, and Mistral Medium. High variance at the moment because not a lot of votes, but interesting to see how it evolves. (Sorry I…
Today you can experience the future of image generation with our latest version of Meta AI. Offering lightning-fast speeds, stunning high-quality images, and a revolutionary new way to create and animate custom images using simple text prompts. @savitz described it pretty well:…
In addition to Llama 3, we also made big updates to Meta AI today. We expanded to 13 new countries, made Meta AI more prominent across all of our apps, launched our meta.ai website, added search powered by Google and added new image generation capabilities! Meta…
Meta released Llama 3 on my birthday! 🎂 Best present ever, thanks Meta! 😀
Excited to share what I’ve been working on for the past 9 months. So incredibly proud of the entire team that worked tirelessly to make Llama 3 happen! And this is only the beginning… ai.meta.com/blog/meta-llam…
Big congrats to @AIatMeta on Llama 3 release🔥 A huge week for open-source AI! Both Llama-3 70B & 8B are now in the Arena thanks to @togethercompute fast support. Let's see how well it does in real-world tests by Arena power users, come challenge Llama-3🧩!
Big congrats to @AIatMeta on Llama 3 release🔥 A huge week for open-source AI! Both Llama-3 70B & 8B are now in the Arena thanks to @togethercompute fast support. Let's see how well it does in real-world tests by Arena power users, come challenge Llama-3🧩! https://t.co/JMsOUhA5RK
Early 1K votes are in and Llama-3 is on FIRE!🔥The New king of OSS model? Vote now and make your voice heard! Leaderboard update coming very soon.
Early 1K votes are in and Llama-3 is on FIRE!🔥The New king of OSS model? Vote now and make your voice heard! Leaderboard update coming very soon. https://t.co/L9h9QrCkjl
Llama 3 is officially the fastest model from release to #1 trending on Hugging Face - in just a few hours. 30,000 new models have been released based on llama 1 & 2 so I can't wait to see the impact that the third and most powerful version will have on the ecosystem! 🚀🚀🚀
Yann LeCun @ylecun
710K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Jim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Edward Grefenstette @egrefen
36K Followers 774 Following FR/US/GB AI/ML Person, Director of Research at @GoogleDeepMind, Honorary Professor at @UCL_DARK, @ELLISforEurope Fellow. All posts are personal.Eugene Vinitsky @EugeneVinitsky
13K Followers 2K Following Anti-cynic. Artificial narrow intelligence. Autonomous vehicles, multi-agent learning, and transportation. RS at Apple, Asst. Prof at @nyutandon. He/him.Tim Rocktäschel @_rockt
29K Followers 1K Following Open-Endedness Team Lead @GoogleDeepMind, Professor of AI @AI_UCL, PI @UCL_DARK, @ELLISforEurope Scholar. ex @MetaAI (FAIR), @CompSciOxford. Opinions my own.yobibyte @y0b1byte
15K Followers 2K Following Kurin ViTaly, senior research scientist @IsomorphicLabs, ML PhD from @UniofOxford on RL, Multitask learning & GraphsNatasha 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.Danijar Hafner @danijarh
14K Followers 869 Following Building AI that makes autonomous decisions using world models, artificial curiosity, and temporal abstraction @DeepMindNoam Brown @polynoamial
34K Followers 611 Following Researching reasoning @OpenAI | Co-created Libratus/Pluribus, the first superhuman no-limit poker AIs | Co-created CICERO | PhD from @SCSatCMUJakob Foerster @j_foerst
14K Followers 819 Following Assoc. Prof in ML @UniofOxford @StAnnesCollege @FLAIR_Ox, dad. Ex: {RS @MetaAI, (A)PM @Google, DivStrat @GS}, ex intern {@GoogleDeepmind, @GoogleBrain, @OpenAI}Eric Jang @ericjang11
69K Followers 3K Following physical AGI at 1X. Author of "AI is Good for You" https://t.co/eFg4WXhg0pLaura Ruis @LauraRuis
3K Followers 637 Following Currently research intern @cohere, PhD supervised by @_rockt and @egrefen. Language and LLMs. Spent time at FAIR, Google, and NYU (@LakeBrenden). She/her.Bam4d @Bam4d
2K Followers 1K Following AI Scientist at https://t.co/SUcb0CBcb7. PhD in AI. Opinions are streamed 1 token at a time. ex. @MetaAI @modl_aiMichal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMindJulian Togelius @togelius
18K Followers 1K Following AI and games researcher. Associate professor at NYU; director of @NYUGameLab; co-founder of https://t.co/FnakJLkAXW.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.Andrew Lampinen @AndrewLampinen
7K Followers 1K Following Interested in cognition and artificial intelligence. Research Scientist @DeepMind. Previously cognitive science @StanfordPsych. Tweets are mine.My Student Club @Mananbhansali42
0 Followers 17 FollowingJanhavee Shinde @SJanhavee
55 Followers 2K FollowingMary Williamson @mary_williamson
39 Followers 98 FollowingXiaolong Yang @yang_appstats
391 Followers 3K Following AM student of political methodology @HarvardGSAS. 東大教養の人間だった。因果推論。vilaht @Trend0Micro
463 Followers 5K FollowingA_bigail @Abigail20898125
35 Followers 1K FollowingAnja Šurina @AnjaSurina
25 Followers 297 FollowingGagan Jain @gaganjain1582
47 Followers 717 Following Predoc Researcher @GoogleDeepMind | IIT Bombay'22Supreme 🐐 @master_ureself
458 Followers 1K Following Naturally Selective 🔍 | Mathematically Calculating 🧮 | Scientifically Guided 👨🏾🔬 | Artificially Intelligent 🤖 | In Pursuit of Biological Harmony 🧬PetalGlow @glow_petal40561
3 Followers 721 FollowingJishuai MIAO @JishuaiM88686
24 Followers 565 FollowingHu_❤️_Li @Hu_Li_
5 Followers 119 FollowingAaditya ; @Aaditya26082004
519 Followers 7K Following CS'26 • Machine Learning • Open-Source • Web Dev. • Algorithms • Jai Shree Krishna 🦚🪈tangbinh @tangbinh2
38 Followers 118 FollowingMatt Fleisher @FFMattFleisher
169 Followers 1K FollowingTasour @TasourR
33 Followers 238 Following Error code: 0xF2024 (Lost in the virtual world). Backup failed. All data lost.Jitendra Sharma @jkumarsharma998
799 Followers 6K Following Curious about Research in AI. NLP and Computer Vision Interest me. Curious about truth and existence. Views are personal.吴学东 @wxudng2
59 Followers 2K Following光与肥肥 @wangxinhahaha
1 Followers 399 FollowingPetko Petkov @mnogoqkoime
35 Followers 507 FollowingNauman Ahmad @naumanxyz
152 Followers 968 Following Working on AI for Code @ Meta. LLMs, dev tools, agents. NYU alumImad Khwaja @flyingblackswan
162 Followers 2K Following SaaS Growth || SEO Marketing Agency || EntrepreneurMike Lewis @ml_perception
6K Followers 227 Following Llama3 pre-training lead. Partially to blame for things like the Cicero Diplomacy bot, BART, RoBERTa, kNN-LM, top-k sampling & Deal Or No Deal.Kelly W. Zhang @kewzha
138 Followers 174 Followinghuifuhha @alsdnlbsc
0 Followers 125 FollowingPensé FFun @inftyCategory
118 Followers 5K FollowingDeepa_kdiaz524 @kdiaz52446472
4 Followers 929 FollowingShubham Chandra @ShubhamMChandra
175 Followers 838 Following Just a guy trying to figure a few things out | working on stuff @ other people’s companies and eventually my own | working on myself at homeparia @pariawshahi
130 Followers 6K FollowingMichael Johnson @onemoremichael
457 Followers 5K Following Co-Founder of Ref | Leaving the resume behind. Al-native platform that surfaces relevant & authentic context on candidates, validated by Al-assisted referrals.Hugh @HughABrown
130 Followers 83 FollowingCapybara ai @capybara_ai
60 Followers 491 Following Capybara doing PhD@TsinghuaCS, checkout my blog @ https://t.co/2Iz05C84xd. Interested in Reinforcement Learning, LLM-based Agents, Alignment.Garrett -DeepWriterAI @DeepAIWriter
12K Followers 6K Following Over-engineering Agentic Systems for long-form writing. Generating scripts, fiction or non, breakthrough ideas, whole universes, etc. The Deep Writer. DM4demo.Tariq Ullah @Tariq_Ullah67
6 Followers 121 Followingvasudev anubrolu @vasudevanubrolu
70 Followers 1K Following ML enthusiast, Engineer. Sr. SE @koredotai. ex @deloitte @vmware. @bitspilaniindia 2015-20.AB M @abdelmehdi_ab
46 Followers 1K FollowingNexus @Bryanjnexus
17K Followers 14K Following Investor, Futurist, Web 3, Technology, I love robots and AI, Crypto, Sports lover 🏈🏀⛳Thomas FASTIER @TFastier83115
11 Followers 81 FollowingV Sriram @VSriram23
140 Followers 3K FollowingYann LeCun @ylecun
710K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Google DeepMind @GoogleDeepMind
942K Followers 275 Following We’re a team of scientists, engineers, ethicists and more, committed to solving intelligence, to advance science and benefit humanity.AK @_akhaliq
309K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxJim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Kyunghyun Cho @kchonyc
61K Followers 2K Following a combination of a mediocre scientist, a mediocre manager, a mediocre advisor & a mediocre PC at @nyuniversity (@CILVRatNYU) & @genentech (@PrescientDesign).Edward Grefenstette @egrefen
36K Followers 774 Following FR/US/GB AI/ML Person, Director of Research at @GoogleDeepMind, Honorary Professor at @UCL_DARK, @ELLISforEurope Fellow. All posts are personal.Eugene Vinitsky @EugeneVinitsky
13K Followers 2K Following Anti-cynic. Artificial narrow intelligence. Autonomous vehicles, multi-agent learning, and transportation. RS at Apple, Asst. Prof at @nyutandon. He/him.Sergey Levine @svlevine
79K Followers 122 Following Associate Professor at UC Berkeley Co-founder, Physical IntelligenceTim Rocktäschel @_rockt
29K Followers 1K Following Open-Endedness Team Lead @GoogleDeepMind, Professor of AI @AI_UCL, PI @UCL_DARK, @ELLISforEurope Scholar. ex @MetaAI (FAIR), @CompSciOxford. Opinions my own.Soumith Chintala @soumithchintala
185K Followers 877 Following Cofounded and lead @PyTorch at Meta. Also dabble in robotics at NYU. AI is delicious when it is accessible and open-source.yobibyte @y0b1byte
15K Followers 2K Following Kurin ViTaly, senior research scientist @IsomorphicLabs, ML PhD from @UniofOxford on RL, Multitask learning & GraphsNatasha 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.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/IbycyGfnDRDanijar Hafner @danijarh
14K Followers 869 Following Building AI that makes autonomous decisions using world models, artificial curiosity, and temporal abstraction @DeepMindNoam Brown @polynoamial
34K Followers 611 Following Researching reasoning @OpenAI | Co-created Libratus/Pluribus, the first superhuman no-limit poker AIs | Co-created CICERO | PhD from @SCSatCMUAI at Meta @AIatMeta
530K Followers 255 Following Together with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.Marc G. Bellemare @marcgbellemare
13K Followers 350 Following CSO & co-founder, Reliant AI. Ex RL research lead at Google Brain, DeepMind. Known for Atari 2600 RL benchmark, Distributional RL (MIT Press 2023).Jakob Foerster @j_foerst
14K Followers 819 Following Assoc. Prof in ML @UniofOxford @StAnnesCollege @FLAIR_Ox, dad. Ex: {RS @MetaAI, (A)PM @Google, DivStrat @GS}, ex intern {@GoogleDeepmind, @GoogleBrain, @OpenAI}Roshan Sumbaly @rsumbaly
1K Followers 683 Following Herding Llamas and Emus in Gen AI @metaai. Prior life @coursera, @linkedIn, @stanfordRick Lamers @RickLamers
2K Followers 867 Following 👨💻 AI Research & Engineering @GroqInc. I publish a weekly update about LLM Engineering on Substack, it’s free. Opinions are my own.Ahmad Al-Dahle @Ahmad_Al_Dahle
4K Followers 52 Following #Girldad of twins. Leading GenAI @ Meta (llama, imagine, meta ai and more)Rui Hou @magpie_rayhou
78 Followers 268 Following Also go by Ray. GenAI Research @AIatMeta PhD from @UMich Ann ArborSakana AI @SakanaAILabs
19K Followers 0 Following We are a Tokyo-based R&D company on a quest to create a new kind of foundational AI model based on nature-inspired intelligence. https://t.co/1q07mb3TzEAlex Chalmers @chalmermagne
463 Followers 354 Following European Dynamism @airstreet + @airstreetpress. Resisting the tyranny of low expectations. Views own. ❤️🔥Michael Chang @mmmbchang
2K Followers 2K Following Amplify human creativity Gemini @GoogleDeepMind Prev @LangChainAI, @MetaAI, @SchmidhuberAI PhD @berkeley_ai, w/ @svlevine, @cocosci_lab. BS @MIT @MITCoCoSciDibya Ghosh @its_dibya
1K Followers 392 Following I do RL research @UCBerkeley | Previously @ Google Brain MontrealPiotr Bojanowski @p_bojanowski
561 Followers 131 Following Research Scientist at Facebook AI Research. Interested in Machine Learning and Computer Vision.Michal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMindCognition @cognition_labs
123K Followers 19 Following Makers of Devin, the first AI software engineer. We are an applied AI lab focused on reasoning, and code is just the beginning. Join us: https://t.co/tpfZwEwGiqWojciech Galuba @wgaluba
488 Followers 1K Following Head of Data & Evals @Cohere | prev: Research Eng Lead @MetaAI | founded @Meta’s A/B testing platform and the AI annotation platform | @ICepfl alumnusArxiv Papers @arxivdigests
516 Followers 19 Following Transforming arXiv gems into podcasts & engaging videos. Bridging the gap between overly brief paper summaries & lengthy full reads.swyx @swyx
91K Followers 3K Following Anti-ego ideas for anti-ergodic life. Founder, @smolmodels ▹ Listen: @latentspacepod ▹ Read: @coding_career ▹ Join: @aiDotengineerQuanta Magazine @QuantaMagazine
322K Followers 657 Following Illuminating math and science. Supported by @SimonsFdn. 2022 Pulitzer Prize in Explanatory Reporting.Kevin Stone @kevinleestone
371 Followers 272 Following Research @ OpenAI, previously at FAIR, TRI, and Google working on LLMs, RL, and Robotics.Ashley Edwards @ashrewards
482 Followers 200 Following Research scientist @GoogleDeepMind. Past: Uber AI Labs, Georgia TechYuke Zhu @yukez
15K Followers 464 Following Assistant Professor @UTCompSci | Co-Leading GEAR @NVIDIAAI | CS PhD @Stanford | Building generalist robot autonomy in the wild | Opinions are my ownJing Yu Koh @kohjingyu
3K Followers 486 Following Machine Learning PhD student @CarnegieMellon. Previously: fulltime vision-and-language research @GoogleAI, undergrad @sutdsg. 🇸🇬Nick St. Pierre @nickfloats
156K Followers 2K Following Creative Director and unofficial Midjourney shill. Publicly exploring AI & sharing learnings.Magic.dev @magicailabs
10K Followers 3 Following Magic is working on frontier-scale code models to build a coworker, not just a copilot. Come join us: https://t.co/hGZKtUzsR3Alexis Chevalier @AlexisChvlr
100 Followers 79 Following NLP postdoc @PrincetonPLI. Formerly researching mathematical logic @IAS and @UniOfOxfordrabbit inc. @rabbit_hmi
83K Followers 1 Following rabbit brings the future of human-machine interface. order r1, your pocket companion, now.Yuge Shi (Jimmy) @YugeTen
4K Followers 476 Following 石宇歌 · Research Scientist @DeepMind · Past: PhD at Oxford, intern at Google Brain, FAIR, CSIRO · she/heroxen @oxen_ai
298 Followers 84 Following Build World-Class AI Datasets. Together. You a nerd? Check out our weekly #AI #ML Paper Club Arxiv Dives too! Hugs and MoosGenAI4DM Workshop @genai4dm
14 Followers 1 Following The Generative AI for Decision Making Workshop at ICLR 2024Mark Zuckerberg @finkd
760K Followers 748 FollowingPierre-Luc Bacon @pierrelux
2K Followers 751 Following Assistant prof. at @UMontrealDIRO @MILAMontrealBruno Castro Silva @BrunoSilvaUMass
172 Followers 112 Following Assistant Professor, University of Massachusetts. Reinforcement Learning & AI, Hierarchical Control, Safe/Fair Machine Learning. Opinions expressed are my own.Davide Paglieri @PaglieriDavide
83 Followers 97 Following PhD Student @UCL, @UCL_DARK. Previously Research Engineer at @bendingspoonsXian Li @xl_nlp
2K Followers 242 Following Research Scientist @MetaAI. NLP, ML. Opinions are my own.Roger Grosse @RogerGrosse
10K Followers 748 FollowingIan Hogarth @soundboy
23K Followers 3K Following investor @pluralplatform; chair UK AI Safety Institute; co-author @stateofaireport; co-founder @songkick; chair @PhasecraftLtdConference on Languag.. @COLM_conf
2K Followers 6 Following https://t.co/GhGCMEoa4A Abstract submission: March 22, 2024Yuxiang (Jimmy) Wu @YuxiangJWu
1K Followers 1K Following Co-founder @WecoAI | UCL PhD | Natural Language Processing | Machine Learning | formerly intern @allen_ai @MetaAIDominik Schmidt @schmidtdominik_
242 Followers 274 Following Research Engineer @WecoAI, previously @ucl_dark, @Microsoft, @tu_wienZhengyao Jiang @zhengyaojiang
1K Followers 261 Following Cofounder and CTO @WecoAI, building AutoML Agents. Final year PhD student at UCL @UCL_DARK @ai_ucl. (Zheng=j-uhng, j as in job; yao=y-aoww)Saffron Huang @saffronhuang
4K Followers 847 Following how shall we live together? co-founder @collect_intel ⋅ research @ uk ai safety institute was @googledeepmind • co-created @kernel_magazine ⋅ TKSuchin Gururangan @ssgrn
4K Followers 249 Following he/him Research scientist on Llama team, @meta GenAI prev: PhD @uwcse + @uwnlpSome of our first steps on developing mitigations for sleeper agents
New Anthropic research: we find that probing, a simple interpretability technique, can detect when backdoored "sleeper agent" models are about to behave dangerously, after they pretend to be safe in training. Check out our first alignment blog post here: anthropic.com/research/probe…
Really cool to see the community building amazing things on top of Llama3 models!
Delighted to release ✨Llama-3-8B-Web✨, the most capable agent built for web navigation by following instructions and replying💬. It surpasses GPT-4V* by 18% on WebLINX, a benchmark for web navigation with dialogue. Model: huggingface.co/McGill-NLP/Lla… Code: github.com/McGill-NLP/web…
Me: remove that sentence, it doesn't make any sense. Student: The sentence...that you wrote? 🤦
self-improvement/"self-play"/continual interaction/feedback with other AI's and humans is likely the fastest path to AGI - where the latter is not a single agent but rather a community/population of intelligent agents. No intelligent agent, at any level (from insects to humans)…
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing Despite the impressive capabilities of Large Language Models (LLMs) on various tasks, they still struggle with scenarios that involves complex reasoning and planning. Recent work proposed advanced
Using just MMLU for model comparison can be quite misleading/limiting as it does not capture many other model's properties and behaviors in real user interactions. The Y axis must change - or become (highly) multivariate manifold. @ethanCaballero
The current state-of-play in the key question of how good AI gets: So much depends on GPT-5. OpenAI had a year+ lead in creating a GPT-4 class model. Now there are four GPT-4 class models. If exponential growth is still possible, OpenAI should be the first to show us. Or not.
Llama3 reminds everyone of the misconception about scaling laws again: it's not that a larger model is always better, but that a larger model is cheaper to train if you want to reach the same performance. Yes, this might be somewhat counter-intuitive, but this is one of the key…
Here is my selection of papers for today (27 Feb) on Hugging Face MobiLlama: Towards Accurate and Lightweight Fully Transparent GPT Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
2 other models worth highlighting 😉 @RekaAILabs Flash 21B is very strong for its size! 💪
How good is @AIatMeta Llama 3 in real-world user scenarios?🤔 The early votes in @lmsysorg are in, and Llama-3 is the best open LLM, even outscoring @OpenAI GPT-4 (March) or @AnthropicAI Claude 3 Haiku! 👑 Llama 3 currently scores at 1199 in #7, only behind the latest @OpenAI…
There's another quieter release from @AIatMeta today that's really cool. * Live Preview: As you type your image prompt, you get a live preview, making iterating for a good image easier. * Animate: now you can animate images for short bursts
Check out the generative vision related release too meta.ai/?icebreaker=im… Imagine Flash generates the image as you type You can also "Animate" your images! (technique based on Emu Video emu-video.metademolab.com) Kudos to the team for putting this out :)
Check out the generative vision related release too meta.ai/?icebreaker=im… Imagine Flash generates the image as you type You can also "Animate" your images! (technique based on Emu Video emu-video.metademolab.com) Kudos to the team for putting this out :)
Wondering how much progress was delayed by the chinchilla optimality paper, and people assuming that was a “given” because it came from DeeepMind.
AI Showdown 🤯🚀 @AIatMeta's LLama 3 70B on @GroqInc blows out of the water Claude Opus and GPT-4 Turbo on combined Speed/Price/Quality dimension at avg 200 tokens per second (real life measurements). Read more here 👇 writingmate.ai/blog/meta-ai-l…
@RickLamers @EitanTurok @GroqInc Tell us what you find, we will try to improve it before the 400B :)
@EitanTurok @GroqInc 73.41% is the overall accuracy. Can be higher, we're looking into why the "Relevance Detection" category is relatively poor. gist.github.com/ricklamers/5c3…
Frontier level Tool Calling now live on @GroqInc powered by Llama 3 🫡 Outperforms GPT-4 Turbo 2024-04-09 and Claude 3 Opus (FC version) in multiple subcategories At 300 tokens/s 🚀 I've personally been working on this feature, and man, the new Llama is good!
Excited to release a preview version of Llama3 with superb performance to the community! More to come soon!
It’s here! Meet Llama 3, our latest generation of models that is setting a new standard for state-of-the art performance and efficiency for openly available LLMs. Key highlights • 8B and 70B parameter openly available pre-trained and fine-tuned models. • Trained on more…
Congrats to the @AIatMeta team on Llama 3 🤯🤯 It is by FAR the best open source model i've played with! Run your personal llama 3 in a Lightning Studio now... let me know what you think about the model! lightning.ai/lightning-ai/s…
Thanks @_akhaliq for promoting our work on LLM fast inference! For speculative decoding on long-context, do we really need to train a separate draft model? How about we just use a draft using retrieval and context truncation techniques (e.g., H2O/StreamLLM)? This leads to…
TriForce Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding With large language models (LLMs) widely deployed in long content generation recently, there has emerged an increasing demand for efficient long-sequence inference support.
I'm seeing a lot of questions about the limit of how good you can make a small LLM. tldr; benchmarks saturate, models don't. LLMs will improve logarithmically forever with enough good data.
Yes, both the 8B and 70B are trained way more than is Chinchilla optimal - but we can eat the training cost to save you inference cost! One of the most interesting things to me was how quickly the 8B was improving even at 15T tokens.