正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Introducing Vision Arena! Inspired by the awesome Chatbot Arena, we built a web demo on Hugging Face for testing Vision LMs (GPT-4V, Gemini, Llava, Qwen-VL, etc.). You can easily test two VLMs side by side and vote! It’s still a work-in-progress. Feedbacks are welcome! 🔗 Kudos to the main... show more

Bill Yuchen Lin

25,863 subscribers

146,020 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Bill Yuchen Lin 的头像

Bill Yuchen Lin2 年前

And our awesome advisors are @WilliamWangNLP @YejinChoinka 🤩

Bill Yuchen Lin 的头像

Bill Yuchen Lin2 年前

Check out our Leaderboard 🏆:

Xiaojian Ma 的头像

Xiaojian Ma2 年前

@huggingface @allen_ai @ucsbNLP @UWCheritonCS Allowing multiple images maybe? Interleaving them with text could be even better. I think a visual chat interface (allowing uploading images at anytime) seems nice

Bill Yuchen Lin 的头像

Bill Yuchen Lin2 年前

@huggingface @allen_ai @ucsbNLP @UWCheritonCS really nice suggestion! thanks Xiaojian! we'll look into multi-image input feature for the models that support such input types :D

Julien Chaumond 的头像

Julien Chaumond2 年前

@huggingface @allen_ai @ucsbNLP @UWCheritonCS Wow this is awesome!!

Jan Schnyder 的头像

Jan Schnyder2 年前

@_akhaliq @huggingface @allen_ai @ucsbNLP @UWCheritonCS This is awesome, any plans on adding CogVLM? It outperforms most other models on our benchmarks.

Bill Yuchen Lin 的头像

Bill Yuchen Lin2 年前

@xShnippi @_akhaliq @huggingface @allen_ai @ucsbNLP @UWCheritonCS CogVLM added! Please have a try! :D 🚀

Barton Rhodes 的头像

Barton Rhodes2 年前

@huggingface @allen_ai @ucsbNLP @UWCheritonCS absolutely wild!

AmebaGPT 的头像

AmebaGPT2 年前

@huggingface @allen_ai @ucsbNLP @UWCheritonCS Superb work!

dvd@dvd.chat 的头像

[email protected]2 年前

@huggingface @allen_ai @ucsbNLP @UWCheritonCS Awesome work. One caveat though is that GPT-4V is a lot more expensive and has a stricter API rate limit (~120 RPM). I’m sure this will get popular but this also means you may start to hit the rate limit very soon…

相关视频

gpt2-chatbot is back. Capabilities seem to exceed GPT-4, Gemini 1.5, Claude, and anything else currently available. The only way to access it is by testing a prompt in battle mode on the Chatbot Arena and getting a lucky draw. A quick tutorial: 1. Go to chat. lmsys. org 2. Make sure you are in Arena (battle) mode 3. Enter a prompt (shorter is better so you can do them quicker) 4. Rate the response, and the Chatbot Arena will show you what model you were using at the bottom of the chatbox 5. If you don't get 'im-a-good-gpt2-chatbot' or 'im-also-a-good-gpt2-chatbot', refresh and try again until you do Here's a quick video of me getting really lucky and getting them BOTH side-by-side. It took me 5 attempts :^)

gpt2-chatbot is back. Capabilities seem to exceed GPT-4, Gemini 1.5, Claude, and anything else currently available. The only way to access it is by testing a prompt in battle mode on the Chatbot Arena and getting a lucky draw. A quick tutorial: 1. Go to chat. lmsys. org 2. Make sure you are in Arena (battle) mode 3. Enter a prompt (shorter is better so you can do them quicker) 4. Rate the response, and the Chatbot Arena will show you what model you were using at the bottom of the chatbox 5. If you don't get 'im-a-good-gpt2-chatbot' or 'im-also-a-good-gpt2-chatbot', refresh and try again until you do Here's a quick video of me getting really lucky and getting them BOTH side-by-side. It took me 5 attempts :^)

Rowan Cheung

316,375 次观看 • 2 年前

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Introducing Agent Mode: Agentic AI is now measured in the Arena. Agent Mode can do deep research, create reports, generate images, build websites, debug code, and more. It completes more complex tasks by using tools like web search, bash in a sandbox environment, image generation, file writing, and asking follow-up questions. Frontier models are waiting for you in Agent Mode to take on real-world tasks. GPT-5.5, Claude Opus 4.7, Gemini 3.1 Pro, and top open models. Test them yourself.

Arena.ai

306,401 次观看 • 1 个月前

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Introducing VL-JEPA: Vision-Language Joint Embedding Predictive Architecture for streaming, live action recognition, retrieval, VQA, and classification tasks with better performance and higher efficiency than large VLMs. • VL-JEPA is the first non-generative model that can perform general-domain vision-language tasks in real-time, built on a joint embedding predictive architecture. • We demonstrate in controlled experiments that VL-JEPA, trained with latent space embedding prediction, outperforms VLMs that rely on data space token prediction. • We show that VL-JEPA delivers significant efficiency gains over VLMs for online video streaming applications, thanks to its non-autoregressive design and native support for selective decoding. • We highlight that our VL-JEPA model, with an unified model architecture, can effectively handle a wide range of classification, retrieval, and VQA tasks at the same time. by Delong Chen (陈德龙) Mustafa Shukor Théo Moutakanni Willy Jade Lei Yu Tejaswi Kasarla Allen Bolourchi Yann LeCun Pascale Fung

Pascale Fung

90,144 次观看 • 7 个月前

98% users are still wasting time switching between ChatGPT, Gemini, Claude, DeepSeek, and Grok just to compare answers. Today I tried TantyAI after a friend suggested it, and wow… With just one prompt, you get access to all the models and answers side-by-side. Thanks to the team for letting me test it, it’s already saved me so much tab hopping. 🙏 Link:

98% users are still wasting time switching between ChatGPT, Gemini, Claude, DeepSeek, and Grok just to compare answers. Today I tried TantyAI after a friend suggested it, and wow… With just one prompt, you get access to all the models and answers side-by-side. Thanks to the team for letting me test it, it’s already saved me so much tab hopping. 🙏 Link:

Shruti

22,208 次观看 • 11 个月前

Hero Card is coming! Now you can earn by working as a team and ripping the other side to earn! Welcome any team members on the team of Web 3 gaming to reach out for collab. #CarrynotFeed Here are the details of Win2Earn👇 #Win2Earn

Hero Card is coming! Now you can earn by working as a team and ripping the other side to earn! Welcome any team members on the team of Web 3 gaming to reach out for collab. #CarrynotFeed Here are the details of Win2Earn👇 #Win2Earn

Arena of Faith

25,607 次观看 • 2 年前

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel *by the agent*, clonable to your heart's desire

You wanted shadcn — so we built the heinous infra to make it work. Introducing Agent Arena, starting with the best: Claude Code by Anthropic Codex 5 by OpenAI Cursor Agent by Cursor Devin by Cognition Gemini CLI by Google DeepMind Grok Code Fast 1 by xAI 1/ Your prompt launches a containerized agent inside a fresh GitHub repo 2/ The agent can install packages, make tool calls, and write multi-file code 3/ The repo is deployed to Vercel by the agent, clonable to your heart's desire

Grace Li

168,934 次观看 • 9 个月前

I built this little #robot I ordered from Hugging Face Pollen Robotics and connected it to the Google Gemini AI model through its API gateway. The robot wanted its own personality - so I gave it an #ATX (Texas) vibe and you can see the result in the video. Really awesome - it even answers questions and carries on a conversion. The vision and hearing are great - it can identify and follow what it sees (with a reasonable delay). My next goal is to get it to work with a 100% local AI model. Specs: 2 cameras, 4 microphones, a speaker, and a wifi interface to a Raspberry Pi built-in controller. I plan to demo it at the InnoTech #InnoTechAUS event on May 12th. Texas McCombs Austin Tech Council TechRanch

I built this little #robot I ordered from Hugging Face Pollen Robotics and connected it to the Google Gemini AI model through its API gateway. The robot wanted its own personality - so I gave it an #ATX (Texas) vibe and you can see the result in the video. Really awesome - it even answers questions and carries on a conversion. The vision and hearing are great - it can identify and follow what it sees (with a reasonable delay). My next goal is to get it to work with a 100% local AI model. Specs: 2 cameras, 4 microphones, a speaker, and a wifi interface to a Raspberry Pi built-in controller. I plan to demo it at the InnoTech #InnoTechAUS event on May 12th. Texas McCombs Austin Tech Council TechRanch

Russ Finney

29,103 次观看 • 2 个月前

Rewrote tiny-diffusion to be 3x smaller! Went from 951 lines to just 364, all contained in one file. As simple as possible, but not simpler. I also added a tiny GPT implementation as a comparison (312 lines, inspired by Andrej Karpathy). The two implementations are ~80% identical. The model architecture, training loop, tokenization, etc, only differ in 19 lines of code. The main differences are contained within two functions (generate and get_batch). The reason to include the GPT implementation was to show how similar autoregressive LMs are to diffusion LMs on an architectural level. Only *1* line of code in the architecture needs to be modified to support masked language diffusion instead of next-token prediction (by disabling causal masking). Link to the repo is in the comments

Rewrote tiny-diffusion to be 3x smaller! Went from 951 lines to just 364, all contained in one file. As simple as possible, but not simpler. I also added a tiny GPT implementation as a comparison (312 lines, inspired by Andrej Karpathy). The two implementations are ~80% identical. The model architecture, training loop, tokenization, etc, only differ in 19 lines of code. The main differences are contained within two functions (generate and get_batch). The reason to include the GPT implementation was to show how similar autoregressive LMs are to diffusion LMs on an architectural level. Only 1 line of code in the architecture needs to be modified to support masked language diffusion instead of next-token prediction (by disabling causal masking). Link to the repo is in the comments

Nathan Barry

161,578 次观看 • 6 个月前

By giving the Palestinian delegation such a warm welcome and announcing China-Palestine strategic partnership, the Chinese government has sent clear messages that can be perceived as follows: To Palestinians: we support your just cause To Arabs: we are aligned with your vision for your region and support you on your core issues To Muslims: we are allies despite the petty and futile attempts to portray us otherwise To the world: we are on the side of justice To Europe: you have been unfair to Palestinians and you owe them a lot for the tragedy you have created in Palestine To the US administration: you aren’t qualified to be the only arbiter on Palestine To Zionists: we are not sure about your future

By giving the Palestinian delegation such a warm welcome and announcing China-Palestine strategic partnership, the Chinese government has sent clear messages that can be perceived as follows: To Palestinians: we support your just cause To Arabs: we are aligned with your vision for your region and support you on your core issues To Muslims: we are allies despite the petty and futile attempts to portray us otherwise To the world: we are on the side of justice To Europe: you have been unfair to Palestinians and you owe them a lot for the tragedy you have created in Palestine To the US administration: you aren’t qualified to be the only arbiter on Palestine To Zionists: we are not sure about your future

Ebrahim Hashem 李思瑞 إبراهيم هاشم

939,514 次观看 • 3 年前

1/ The beta versions of Arena Launch and Arena DEX are now live. The trenches are born on a social app! Anyone can launch a token directly in or through Arena Launch Contract: 0x8315f1eb449Dd4B779495C3A0b05e5d194446c6e ArenaFactory deployed at: 0xF16784dcAf838a3e16bEF7711a62D12413c39BD1 ArenaRouter02 deployed at: 0xF56D524D651B90E4B84dc2FffD83079698b9066E Trading can take place in the app through the Official Community pages for each token or by connecting a wallet and trading on the Arena DEX found on Soon we will have swaps available directly in your Arena wallet! All tokens from Arena Launch and Arena DEX will also be tradable on LFJ.gg thanks to our partners ODOS (It usually takes up to an hour after graduating for tokens to be integrated with ODOS and LFJ). You can also trade tokens through Velora (formerly ParaSwap) at (formerly known as Paraswap). Arena Launch fees are broken down as follows: - 1 % protocol fees during bonding curve stage - 0.25% referrer fees during bonding curve stage (for anyone you refer who trades on the app) Currently, no fees are given to LPs on Arena DEX (however, this may be adjusted in the future). With the protocol fees, The Arena plans to do the following: 1. Grant program for projects that deploy liquidity on Arena DEX or launch natively in the app 2. Potential fee distributions to the community You can still provide liquidity using Arena DEX but we suggest using for the time being.

1/ The beta versions of Arena Launch and Arena DEX are now live. The trenches are born on a social app! Anyone can launch a token directly in or through Arena Launch Contract: 0x8315f1eb449Dd4B779495C3A0b05e5d194446c6e ArenaFactory deployed at: 0xF16784dcAf838a3e16bEF7711a62D12413c39BD1 ArenaRouter02 deployed at: 0xF56D524D651B90E4B84dc2FffD83079698b9066E Trading can take place in the app through the Official Community pages for each token or by connecting a wallet and trading on the Arena DEX found on Soon we will have swaps available directly in your Arena wallet! All tokens from Arena Launch and Arena DEX will also be tradable on LFJ.gg thanks to our partners ODOS (It usually takes up to an hour after graduating for tokens to be integrated with ODOS and LFJ). You can also trade tokens through Velora (formerly ParaSwap) at (formerly known as Paraswap). Arena Launch fees are broken down as follows: - 1 % protocol fees during bonding curve stage - 0.25% referrer fees during bonding curve stage (for anyone you refer who trades on the app) Currently, no fees are given to LPs on Arena DEX (however, this may be adjusted in the future). With the protocol fees, The Arena plans to do the following: 1. Grant program for projects that deploy liquidity on Arena DEX or launch natively in the app 2. Potential fee distributions to the community You can still provide liquidity using Arena DEX but we suggest using for the time being.

The Arena ⚔️

311,489 次观看 • 1 年前

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

🚀 New Paper: Pixel Reasoner 🧠🖼️ How can Vision-Language Models (VLMs) perform chain-of-thought reasoning within the image itself? We introduce Pixel Reasoner, the first open-source framework that enables VLMs to “think in pixel space” through curiosity-driven reinforcement learning. Current VLMs reason only in text — even when grounded in rich images or videos, their logical steps are verbalized in natural language. This restricts their ability to interrogate visual evidence and demonstrate how conclusions are drawn. 🔍 So we ask: What if we could make VLMs "show their work" by reasoning directly in the pixel space? Inspired by GPT-o3’s "think-in-image" ability, we propose a framework where VLMs use interactive visual operations — zoom, select-frame, highlight — to reason through complex visual inputs. To do this, we design a two-stage training process: Instruction tuning with synthesized visual reasoning traces. Reinforcement learning with curiosity-driven reward to balance exploration between pixel and text reasoning ✨ With this, Pixel Reasoner achieves near-SoTA performance on many information-rich multimodal benchmarks: 📊 84% on InfographicsVQA 🧠 84% on V* benchmark 🧩 74% on TallyQA-Complex It also achieves strong accuracy of 68% on MVBench (a video benchmark). Website: Paper: Code: Demo: (coming soon)

Wenhu Chen

82,829 次观看 • 1 年前

Cognition has signed a definitive agreement to acquire Windsurf. The acquisition includes Windsurf’s IP, product, trademark and brand, and strong business. Above all, it includes Windsurf’s world-class people, whom we’re privileged to welcome to our team. We are also honoring their talent and hard work in building Windsurf into the great business it is today. This transaction is structured so that 100% of Windsurf employees will participate financially. They will also have all vesting cliffs waived and will receive fully accelerated vesting for their work to date. At Cognition we have focused on developing robust and secure autonomous agents, while Windsurf has pioneered the agentic IDE. Devin + Windsurf are a powerful combination for the developers we serve. Working side by side, we’ll soon enable you to plan tasks in an IDE powered by Devin’s codebase understanding, delegate chunks of work to multiple Devins in parallel, complete the highest-leverage parts yourself with the help of autocomplete, and stitch it all back together in the same IDE. Cognition and Windsurf are united behind a shared vision for the future of software engineering, and there’s never been a better time to build. Welcome to our new colleagues from Windsurf!

Cognition

3,048,273 次观看 • 1 年前

Introducing Kombai 2.0 - the first AI design engineer. We keep hearing that AGI is almost here. Still, we’re stuck with coding agents that don’t have taste and design tools that don’t understand our codebase. Both are artifacts of a world where design and engineering were two different jobs, with a handoff in between. That world is changing fast. Today, designers ship code, engineers want to escape handoffs, and everyone wants to build tasteful UX. Kombai is built for this new world. Design and engineering, finally on the same side.

Introducing Kombai 2.0 - the first AI design engineer. We keep hearing that AGI is almost here. Still, we’re stuck with coding agents that don’t have taste and design tools that don’t understand our codebase. Both are artifacts of a world where design and engineering were two different jobs, with a handoff in between. That world is changing fast. Today, designers ship code, engineers want to escape handoffs, and everyone wants to build tasteful UX. Kombai is built for this new world. Design and engineering, finally on the same side.

Dipanjan Dey

438,135 次观看 • 1 个月前

I am blown away by the new local SharePlay capabilities for Vision Pro 🤯 Imagine being able to watch movies together anywhere — on a massive 200-inch screen that looks incredible, supports 3D, and can be moved or resized in seconds. That’s exactly what my business partner and I did during our lunch break as we tested the new local SharePlay features in visionOS 26. With the new update, if both Vision Pros are nearby, they can recognize and compare their surroundings to place the screen in exactly the same spot for each person. And it just works — everything was perfectly in sync. It truly feels like you’re sharing the same Vision Pro experience, side by side. This is where it’s headed — not to replace your TV, but to become a powerful new way to watch movies together in places you otherwise couldn’t.

I am blown away by the new local SharePlay capabilities for Vision Pro 🤯 Imagine being able to watch movies together anywhere — on a massive 200-inch screen that looks incredible, supports 3D, and can be moved or resized in seconds. That’s exactly what my business partner and I did during our lunch break as we tested the new local SharePlay features in visionOS 26. With the new update, if both Vision Pros are nearby, they can recognize and compare their surroundings to place the screen in exactly the same spot for each person. And it just works — everything was perfectly in sync. It truly feels like you’re sharing the same Vision Pro experience, side by side. This is where it’s headed — not to replace your TV, but to become a powerful new way to watch movies together in places you otherwise couldn’t.

Phil Traut ᯅ

35,295 次观看 • 1 年前

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

🎉 恭喜发财🧧🐍 As we welcome the Chinese New Year, we're thrilled to announce the launch of Qwen2.5-VL , our latest flagship vision-language model! 🚀 💗 Qwen Chat: 📖 Blog: 🤗 Hugging Face: 🤖 ModelScope: 🌟 Key Highlights: * Visual Understanding : From flowers to complex charts, Qwen2.5-VL sees it all! * Agentic Capabilities : It’s a visual agent that can reason and interact with tools like computers & phones. * Long Video Comprehension : Captures events in videos over 1 hour long! ⏳🎥 * Precise Localization : Generates bounding boxes & JSON outputs for accurate object detection. * Structured Data Outputs : Perfect for finance & commerce, handling invoices, forms & more! 💼📊 Try Qwen2.5-VL now at Qwen Chat or explore models on Hugging Face & ModelScope . 🌐

Qwen

762,314 次观看 • 1 年前

Dear Constituents, I have always believed that true leadership is about service, sacrifice, and commitment to the people. My desire has consistently been to work towards the unity, progress, and development of Oshodi-IsoloConstituencyII. I remain dedicated to listening, understanding, and standing for the welfare of my people at all times. Together, we can continue to build a stronger and better Oshodi-Isolo Constituency II for everyone. Thank you for your trust, support, and belief in the vision we share. The journey continues, and with God on our side, greater things lie ahead.

Dear Constituents, I have always believed that true leadership is about service, sacrifice, and commitment to the people. My desire has consistently been to work towards the unity, progress, and development of Oshodi-IsoloConstituencyII. I remain dedicated to listening, understanding, and standing for the welfare of my people at all times. Together, we can continue to build a stronger and better Oshodi-Isolo Constituency II for everyone. Thank you for your trust, support, and belief in the vision we share. The journey continues, and with God on our side, greater things lie ahead.

Okey-Joe Onuakalusi

62,278 次观看 • 2 个月前

Introducing Gemini Cursor ✨ – a second multimodal AI cursor for your desktop that's open-source and free! Link below 👇 This experiment 🧪 reimagines how we interact with our computers because visual cues 👀 help us make sense of what we see on a screen. In this demo, I had my friend test it out by trying to add a payment method 💳 to Amazon. The cursor walks through the entire process 💬 while talking and pointing 🖱️ to the right parts of the website. Powered by Gemini 2.0 Flash (Experimental)⚡ from Google and their live multimodal API. Shoutout to Alexander Chen for sharing the starter code that powers most of this app 🙌🔥

Introducing Gemini Cursor ✨ – a second multimodal AI cursor for your desktop that's open-source and free! Link below 👇 This experiment 🧪 reimagines how we interact with our computers because visual cues 👀 help us make sense of what we see on a screen. In this demo, I had my friend test it out by trying to add a payment method 💳 to Amazon. The cursor walks through the entire process 💬 while talking and pointing 🖱️ to the right parts of the website. Powered by Gemini 2.0 Flash (Experimental)⚡ from Google and their live multimodal API. Shoutout to Alexander Chen for sharing the starter code that powers most of this app 🙌🔥

Sriraam

171,611 次观看 • 1 年前

OpenAI are testing a new model on the Web Dev Arena Arena under the name 'Anonymous Chatbot 0717'. I can't believe I'm gonna say this, but it is genuinely at a completely different level of front end coding - far better than Sonnet, o3, Gemini 2.5 Pro, or Grok 4. To test it, I ran a great prompt borrowed from the amazing The Feature Crew YouTube channel, asking models to create a procedurally generated planet with Three.js. Take a look yourselves, but I'm pretty astonished by how big the jump is. I have featured the new model twice just because its implementations have been so interesting. Of course, this is only one test, but OpenAI models have always been a bit 'meh' at front-end work, and they seem to have finally overtaken everyone else on that front. We'll see when it comes out. Credit to Chetaslua for discovering the model

OpenAI are testing a new model on the Web Dev Arena Arena under the name 'Anonymous Chatbot 0717'. I can't believe I'm gonna say this, but it is genuinely at a completely different level of front end coding - far better than Sonnet, o3, Gemini 2.5 Pro, or Grok 4. To test it, I ran a great prompt borrowed from the amazing The Feature Crew YouTube channel, asking models to create a procedurally generated planet with Three.js. Take a look yourselves, but I'm pretty astonished by how big the jump is. I have featured the new model twice just because its implementations have been so interesting. Of course, this is only one test, but OpenAI models have always been a bit 'meh' at front-end work, and they seem to have finally overtaken everyone else on that front. We'll see when it comes out. Credit to Chetaslua for discovering the model

Peter Gostev

495,815 次观看 • 1 年前

🚨BREAKING: You can now build full websites by just typing. It’s called Youware, and it runs on pure vibe coding. Here’s how it works (with a live demo):👇 1. Create a web page or game just by typing. You can even send a screenshot to make it live. 2. Use built-in tools like Figma, YouTube, and Notion. 3. Change a Figma design into a real website. 4. Change how the webpage looks with one click using the boost button on the profile page. 5. Easily deploy code with a link you can share. 6. Highlights: free online AI coding. Try it today:

Hasan Toor

73,516 次观看 • 1 年前

When Ilya Sutskever once explained why next-word prediction leads to intelligence, he made a metaphor: if you can piece together the clues and deduce the criminal’s name on the last page, you have a real understanding of the story. 🕵️‍♂️ Inspired by that idea, we turned to Ace Attorney to test AI's reasoning. It’s the perfect stage: the AI plays as a detective to collect clues, expose contradictions, and uncover the truth. We put the latest top AI models—GPT-4.1, Gemini 2.5 Pro, Llama-4 Maverick, and more—to the test in Ace Attorney, to see if they could shout Objection! ⚖️, turn the case around, and uncover the truth behind the lies.

When Ilya Sutskever once explained why next-word prediction leads to intelligence, he made a metaphor: if you can piece together the clues and deduce the criminal’s name on the last page, you have a real understanding of the story. 🕵️‍♂️ Inspired by that idea, we turned to Ace Attorney to test AI's reasoning. It’s the perfect stage: the AI plays as a detective to collect clues, expose contradictions, and uncover the truth. We put the latest top AI models—GPT-4.1, Gemini 2.5 Pro, Llama-4 Maverick, and more—to the test in Ace Attorney, to see if they could shout Objection! ⚖️, turn the case around, and uncover the truth behind the lies.

Hao AI Lab

999,297 次观看 • 1 年前