Wayne Chi @iamwaynechi
CS Ph.D. at @SCSatCMU. Funded by @NDSEG Fellowship. Intern @arena. Editor at https://t.co/kBygvj9Puy. waynechi.com Santa Clara Joined July 2013-
Tweets569
-
Followers1K
-
Following268
-
Likes1K
@itunpredictable Next event just serve this up!
@zhaoheri With the pace you guys are improving, I have no doubt! Starting on the next evaluation already to prepare 😂
@sethkarten This is what success looks like bud
Muse Spark 1.2 is a frontier model for game development. It matches GPT-5.6-Sol, tying for third place. Earlier this year, Meta didn’t even have a model capable of making this leaderboard. A huge leap for the team—congrats on an amazing model!
@joaomviso @AIatMeta Not that unbelievable 😊
For context, this was evaluated on gamedevbench! Paper: arxiv.org/abs/2602.11103 Github: github.com/waynchi/gamede… Leaderboard: waynechi.com/gamedevbench/
@WrongNebula The benchmark is in godot, but it likely means it's very good at three js also!
@claireszhou Going to run muse spark 1.2 on gamedevbench soon! Let me know if you guys have ran this internally / want to see any more details.
@zhaoheri I'm going to run this on gamedevbench. Will share results. If you guys have run this internally please let me know. Thanks!
Game development is the next frontier. GameDevBench is the first step, but I'm very confident progress will be measured in some way related to game dev
We're starting to leave the territory where you'd test an LLM by e.g. "create an svg of pelican on a bicycle". As one idea to generalize it, I was interested what Opus 5 would do if I gave it the first paragraph of the Lord of the Rings, a 1M token budget (~$10) and asked for
The cost efficiency of Luna for computer-use is incredible
AutoEval is here!
Today we’re launching AutoEval: a new evaluation methodology that ranks models using reward models based on millions of real Arena user preferences. Highlights: - High-quality evaluation signals calibrated on real preference data - Strong alignment with live human evaluations -
Game development is solved everyone!!! Let's pack it up and go home
Opus 5 test with a first-person shooter prototype, one shot. Took like 1.5 hrs It not only created the entire game but also spawned bots to play in multiplayer. Flight mechanics may be under-tuned, but... It's easily the most powerful model of all time full stop.
@nico_laqua Fair enough. It was more a complaint of the other placements. Im sure Corgi will revolutionize insurance.
Tommaso Settimi @settimi_tommaso
74 Followers 2K Following algorithmic composition, audio generative modelling and representation learning
Jikun Cai @Eric_Cai828
91 Followers 937 Following Research Intern @MMLabNTU, advised by Prof. @liuziwei7, Undergrad @FudanUniversity | Robot learning&Robot control, VLA&WAM
Lionel Messi @MessiiAntonela
14 Followers 866 Following "In search of the purest concepts in the depths of the roots of speech and thought."
evannico @evannico
14 Followers 54 Following
William Tenhunen @williamtenhunen
16 Followers 281 Following Deep Learning practitioner focused on solving hard problems that matter. Driven by building neural network solutions for complex real-world challenges.
Shamane Siri | Plural... @GShamane
198 Followers 717 Following Tinkering Transformers | Coding by Day, Hallucinating by Night
PiaoYangAI @CarrotBroAI
2 Followers 66 Following
Brian Expert @brianexpert267
48 Followers 1K Following Software engineer. I have worked in a wide range of technologies over two decades
Jack Wu @JackTripleU
1K Followers 1K Following Building Products @Meta Superintelligence Labs. Managing AIs and engineers who manage AIs who manage AIs who (I think) write code.
William Shen @shenbokui
2K Followers 886 Following ai @meta tbd | led unified models @ Luma/ founder CEO apparate (acq.)/Stanford PhD/Waymo/Nvidia/Google | Awards @cvpr @roboticsscisys
alex zhang @a1zhang
37K Followers 994 Following phd student @mit_csail @nlp_mit, previously undergrad @princeton 🫵🏻 go participate in the @GPU_MODE kernel competitions!
Fred @FredFRodrigues
160 Followers 2K Following Son of God Husband and father 🇧🇷 Construindo agentes rodando IA local 🇺🇸 Boring businesses builder @damngoodinspect @damngoodhs Host @dontkillmydeal
Heri Zhao @zhaoheri
62 Followers 146 Following AI Research at @Meta | prev @GoogleDeepMind, @berkeley_ai
h @joek282
16 Followers 83 Following
Raj @raj_klingon
19 Followers 306 Following
absolutelynobody @wasberries41
54 Followers 677 Following
M. Umut .Ozbek @m_umut_ozbek
1K Followers 3K Following ⚛️ Nuclear Engineer × AI Researcher | NPP Cybersecurity | Tsinghua ,Ontario Tech PhD (c) | IAEA Delegate | UNODA Youth Leader
Juan @juan__garciag
20 Followers 180 Following exploring intelligence | @ETH_AI_Center, @EPFL_en, @OfficialUoM
Ahmed Bahloul @abahloul8
11 Followers 463 Following Msc @TUM / working on #LLM #Memory #RL #Reasoning
Nairobi Villazón | �... @NairCodeVG
10 Followers 369 Following Backend Developer | Node Js | Javascript | Typescript | Feathers Js | autodidact | Never Stop Learning
Thibault Jaigu @ThibaultJaigu
1K Followers 1K Following Co-founder @RequestyAI. I post what trillions of tokens of enterprise AI traffic actually show.
sohel aafaq @sohelaafaq1
1 Followers 123 Following
anonymous086505 @anonymous086505
68 Followers 990 Following
Cntxt @ncncnd65115
61 Followers 4K Following
Yuanxin Liu @Yuanxin02
58 Followers 171 Following PhD student @NorthwesternU. Prev intern @Amazon. Working on LLMs
sanysany @leehy0357
2 Followers 364 Following
Philip C @Aknotymous
54 Followers 2K Following
Éverton Toffanetto @toffanettodev
31 Followers 672 Following 👨💻 Frontend Software Engineer | Passionate about creating amazing digital experiences with Next.js & React | TypeScript | Figma
tukumalu91 @tukumalu91
4 Followers 531 Following
Spike @SpikeMowGrass
68 Followers 2K Following
Lisan al Gaib @scaling01
55K Followers 1K Following lead them to paradise LisanBench: https://t.co/vorVk7Oks6 Impressum & Datenschutz: https://t.co/lFLgiu9cqs
Yarn.vc 🧶 @yarnvc
2K Followers 7K Following Domain = Brand 🤖 https://t.co/mrCBPiaWGx | 🔥https://t.co/MCTmWGJeZl | 🎮 https://t.co/HVaZrPl0C6 | 🔗 https://t.co/To3dlyqESv | 🏆 https://t.co/wZXjLpNQpY | 🧠 https://t.co/6lICPOYM0d |🧯https://t.co/8GH0gF6IYd | ⏳ https://t.co/Zyn9Jk6ciS | 👨🚀 https://t.co/jOGZqstk7l | 📷 https://t.co/mPBRb6JGuO | 🕹️ https://t.co/51RY6lG1GI
Jake Boggs @JakeABoggs
377 Followers 312 Following what I cannot create, I do not understand @RecensionAI
Xinyu (Shea) Zhang @xinyusheazhang
282 Followers 1K Following Agentic AI enables controllable intelligence to help people. Working on agent-based knowledge collaboration and self-improvement agentic AI system.
JTwoXX @JTwoXX
434 Followers 568 Following Music Producer Dad turned Executive Vibe Engineer. I also play fighting games.
张 @unicojackzhang
168 Followers 7K Following
haris @xPolarrr
2K Followers 7K Following head of growth @capydotai, prev founding team @runpod, @spacedriveapp, and cofounder renderflux (acquired)
Zhengyang Qi @qi_zhengyang
1K Followers 6K Following Research @SnorkelAI | Previously: @Scale_AI Multiturn RL, reward modeling, interactive environments, artificial social intelligence
Zhiqing Sun @EdwardSun0909
20K Followers 1K Following Lead agent research @Meta MSL TBD Lab. previously posttraining/agent research @OpenAI. CS PhD @LTIatCMU
Youssof Al Toukhi @Youssofal_
10K Followers 532 Following I’m a 21 y/o hyperfixated dabbler and Forbes featured viral meme building the next biggest mobile game based on memes.
AI at Meta @AIatMeta
838K Followers 353 Following Together with the AI community, we are pushing the boundaries of what’s possible through open science to create a more connected world.
Claire Zhou @claireszhou
704 Followers 126 Following code @meta superintelligence labs | prev @citsecurities, @harvard
Zi Lin @suzzzylin
1K Followers 288 Following AI researcher at @meta MSL TBD lab. Previously: @GoogleDeepMind, PhD @UCSD, AI Resident @GoogleAI, @PKU1898.
Heri Zhao @zhaoheri
62 Followers 146 Following AI Research at @Meta | prev @GoogleDeepMind, @berkeley_ai
koray kavukcuoglu @koraykv
44K Followers 102 Following SVP, Google DeepMind Chief AI Architect, Google.
Grace Li @grx_xce
10K Followers 643 Following cofounder @intelligence_ai (@designarena, @predictionbench). Prev cs + neuro harvard, swe apple
nico laqua @nico_laqua
8K Followers 724 Following techno optimist & ceo @usecorgi https://t.co/puP658NE4E
Negar Arabzadeh @NegarEmpr
2K Followers 1K Following Postdoc @UCBerkeley @BerkeleySky |👩🏻💻Prev @google, @MSFTResearch, @SpotifyResearch | 📚@UWaterloo | Interested in Information Retrieval
Lisan al Gaib @scaling01
55K Followers 1K Following lead them to paradise LisanBench: https://t.co/vorVk7Oks6 Impressum & Datenschutz: https://t.co/lFLgiu9cqs
Kimi.ai @Kimi_Moonshot
356K Followers 137 Following Built by Moonshot AI to empower everyone to be superhuman. PR: [email protected] DC: https://t.co/wBsBTn6fmE
Young @Young_AGI
10K Followers 886 Following
Xinyu Yang @Xinyu2ML
18K Followers 2K Following Building open frontier intelligence. Opinions are my own. They/Them
Xinyu Zhou @zxytim
13K Followers 1K Following
Irmak Bukey @irmakbukey
56 Followers 30 Following CS PhD student @ CMU | G-CLef Lab 🎼 | Multimodal Music AI
Guillaume @glevd
905 Followers 832 Following Professional complainer powered by caffeine, sarcasm, and questionable product decisions.
Clayton Thorrez @cthorrez
2K Followers 3K Following Rating systems and paired comparison experimentation enjoyer @arena
PixiJS @PixiJS
6K Followers 16 Following The HTML5 Creation Engine. Create beautiful games, apps, and interactive digital content with the fastest 2D WebGPU/WebGL renderer. https://t.co/wZIppsLmRu
(Luke) Donghyun Lee @lukedhlee
200 Followers 315 Following PhD student @UCBerkeley (BAIR & Sky Lab). CS master’s @UCL. Formerly visiting researcher @ Stanford AI Lab.
Lakshya A Agrawal @LakshyAAAgrawal
5K Followers 4K Following PhD @ UC Berkeley | @gepa_ai Creator | Created https://t.co/YxPZsXZJeS | AI4Code Research Fellow @MSFTResearch | Hobby Saxophonist
Melissa Pan @melissapan
4K Followers 696 Following CS PhD @UCBerkeley Sky Lab 🐻 Systems & AI & Sustainability 🌍 Prev: @google, @ibm, @CarnegieMellon🐕🦺, @UofT🇨🇦
Teddy Cross @tddyco
193 Followers 197 Following 🦄 Founder @Playco 🍸 Owner @ Calvados Garden 🎮 Building the future of games & AI
Eunsu Kim @euns0o_kim
294 Followers 300 Following Incoming PhD @LTIatCMU , MS student @kaistcsdept | prev: @cmuhcii
Lili @lchen915
2K Followers 498 Following Ph.D. student @mldcmu & visiting student @stanford. Previously undergrad @berkeley_ai
Ziniu Li @ZiniuLi
972 Followers 600 Following Research Scientist @TencentHunyuan Prev: Bytedance Seed (Seed-OSS, Seed 1.8, LoopLM Ouro) RL + LLMs: ReMax, GEM, Knapsack RL
Jerry Huang @jrrhuang
205 Followers 390 Following PhD student @SCSatCMU working on generative modeling; previously @Caltech.
Aryan Vichare @aryanvichare10
2K Followers 809 Following member of technical staff @arena | prev. @a16z @vercel @v0 @aisdk
I-Hung Hsu @IHung_Hsu
647 Followers 449 Following Building AI that’s smart, human-centric, and global.
Che-Ping Tsai @chepingt
167 Followers 677 Following Building Eval for AI @ @arena | AI PhD @ @mldcmu
Sholto Douglas @_sholtodouglas
57K Followers 2K Following Scaling RL @AnthropicAI, ex @DeepMind - working towards intelligence too cheap to meter
Chengshuai Shi @chengshuai_shi
369 Followers 735 Following Postdoc @PrincetonPLI; Previous @TechAtBloomberg @uvaece; Working on intelligent decision-making; Opinions are my own.
Moonlake @moonlake
11K Followers 4 Following World models and simulation infrastructure for embodied AI
Modal @modal
35K Followers 162 Following AI infrastructure that developers love 💚 Run inference, sandboxes, batch processing, training, and many other things on Modal
Joachim Baumann @joabaum
895 Followers 2K Following Postdoc @StanfordNLP @StanfordAILab / Prev: @MilaNLProc @UZH_en @MPI_IS @CarnegieMellon. CompSocSci, LLMs, algorithmic fairness.
Allen Roush @Hellisotherpe10
184 Followers 72 Following AI Researcher @ Thoughtworks, ex-OCI, ex-Intel, Co-host of "The Information Bottleneck" Podcast. I'm a big fan of NLP, AI, debate, and rougelike video games.
























