Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Built a Complex Procedural 3D Scene with Three.js Powered by Hy4! I used Hy4 through WorkBuddy to turn a simple one-line prompt into a complex procedural 3D scene using Three.js. → Procedurally generated 3D environments → Detailed geometry and immersive visuals → Dynamic scene composition → AI-powered coding from... show more

Krishna Agrawal

48,488 subscribers

93,361 views • 1 day ago •via X (Twitter)

Arts Science & Technology

Anya Rossi• Live Now

Private livecam show

21 Comments

H A J R A1 day ago

That’s impressive

Mohit Mishra1 day ago

This is where AI coding gets really interesting. It's not just generating code anymore, it's helping build actual experiences.

Manish Kumar Shah1 day ago

Curious to see how far you can push this with more detailed prompts and complex environments.

Vaidehi1 day ago

I like how this lowers the barrier to experimenting with 3D development. You don't need to start with a blank scene anymore.

Markandey Sharma1 day ago

One prompt to a full 3D environment is actually pretty wild. The possibilities here are huge.

Dipti Sharma1 day ago

Three.js scenes usually take quite a bit of work to put together. This makes the process interesting.

TechP1 day ago

This is wonderful

Bao1 day ago

The procedural terrain and lighting in this Three.js scene look remarkably clean for a prompt-driven workflow. Turning a single line of intent into full interactive geometry right in the browser is getting ridiculously fast. Great execution!

Olivia Parker1 day ago

Same one-line prompt for 3D scene, Hy4 looks competitive with LongCat. I’ll test both on the same planet prompt next.

Khushabu Agrawal1 day ago

This could save developers a lot of time when experimenting with 3D concepts.

Dipanshu Kushwaha1 day ago

The jump from a simple text prompt to a full procedural scene is impressive.

Dhanian 🗯️23 hours ago

Thanks for sharing

Yash1 day ago

The fact that it handles scene composition and geometry from one prompt is what caught my attention.

Z-Coder1 day ago

Imagine being able to prototype 3D ideas this quickly without writing everything from scratch.

Utkarsh Sharma1 day ago

This opens up some interesting possibilities for rapid 3D prototyping.

Darcy1 day ago

Three.js projects just got a lot more interesting 👀

Eliana 🇺🇸1 day ago

Procedural generation + AI coding is a pretty powerful combination.

NexaAI23 hours ago

A great example of AI being tested beyond traditional benchmarks!

Shraddha Bharuka1 day ago

From an idea to an actual 3D world with one prompt. That's a pretty cool workflow.

Himanshu23 hours ago

Curious to see which models perform best.

DeepThinkAI23 hours ago

This could accelerate discoveries in life sciences.

Related Videos

Sakura Bonsai by Hy4 Preview developed using their WorkBuddy client. Prompt is below (big one) I think is from Majid Manzarpour 👇 Thanks for the early access 🙏🏻 Tencent Hy Tencent AI WorkBuddy

Sakura Bonsai by Hy4 Preview developed using their WorkBuddy client. Prompt is below (big one) I think is from Majid Manzarpour 👇 Thanks for the early access 🙏🏻 Tencent Hy Tencent AI WorkBuddy

Ivan Fioravanti

40,712 views • 2 months ago

A gallery is more than a collection of images. It’s a space for people to explore ideas and experience them in a new way. I created this gallery demo with Hy4 in WorkBuddy to explore how an idea can take shape through code. Hy4 keeps its pricing unchanged at $0.834 per million input tokens, $2.501 per million output tokens and $0.042 per million tokens on cache hits. For this project, I wanted to see how Hy4 could help turn a creative direction into an on-screen experience—from the initial concept to the finished result. Here’s how it turned out. What kind of gallery would you create? Build your own with WorkBuddy: Tencent Hy Tencent AI WorkBuddy

A gallery is more than a collection of images. It’s a space for people to explore ideas and experience them in a new way. I created this gallery demo with Hy4 in WorkBuddy to explore how an idea can take shape through code. Hy4 keeps its pricing unchanged at $0.834 per million input tokens, $2.501 per million output tokens and $0.042 per million tokens on cache hits. For this project, I wanted to see how Hy4 could help turn a creative direction into an on-screen experience—from the initial concept to the finished result. Here’s how it turned out. What kind of gallery would you create? Build your own with WorkBuddy: Tencent Hy Tencent AI WorkBuddy

Navid Tasnim

14,313 views • 1 day ago

🚨 Tencent just dropped a serious open-source AI contender. Meet Hy4 Preview built for productivity, coding & agentic workflows. 770B total parameters. 49B active. 1M+ token context. But the numbers aren’t the most interesting part. Hy4 Preview is designed to handle what actually matters: planning, tool use, coding, research, document workflows and complex multi-step tasks. In Tencent’s internal blind evaluation across 203 engineering tasks, it scored 2.99/4, edging out GLM 5.3 (2.92) and Kimi K3 (2.94). From full-stack development and research to workplace automation and even game development, this looks less like “just another LLM” and more like a model built to get real work done. Worth watching 👀 🔗 Try it with WorkBuddy: Tencent Hy Tencent AI WorkBuddy

🚨 Tencent just dropped a serious open-source AI contender. Meet Hy4 Preview built for productivity, coding & agentic workflows. 770B total parameters. 49B active. 1M+ token context. But the numbers aren’t the most interesting part. Hy4 Preview is designed to handle what actually matters: planning, tool use, coding, research, document workflows and complex multi-step tasks. In Tencent’s internal blind evaluation across 203 engineering tasks, it scored 2.99/4, edging out GLM 5.3 (2.92) and Kimi K3 (2.94). From full-stack development and research to workplace automation and even game development, this looks less like “just another LLM” and more like a model built to get real work done. Worth watching 👀 🔗 Try it with WorkBuddy: Tencent Hy Tencent AI WorkBuddy

RAVI KUMAR SAHU

63,568 views • 2 months ago

A transit map can show you where to go. But what if it could also show you how the network moves? I created this transit demo with Hy4 in WorkBuddy, exploring how a fictional subway map can become a dynamic visualization. Hy4 adds visual understanding compared with Hy4 preview, combining it with reasoning and tool use to support complex chart analysis and other visual tasks. From station names and color-coded lines to transfer points and train movement, the challenge was to bring the network to life while keeping it easy to follow. Hy4 keeps its pricing unchanged at $0.834 per million input tokens, $2.501 per million output tokens and $0.042 per million tokens on cache hits. Here’s how it turned out. What kind of transit system would you like to see visualized? Explore WorkBuddy: Tencent Hy Tencent AI WorkBuddy

A transit map can show you where to go. But what if it could also show you how the network moves? I created this transit demo with Hy4 in WorkBuddy, exploring how a fictional subway map can become a dynamic visualization. Hy4 adds visual understanding compared with Hy4 preview, combining it with reasoning and tool use to support complex chart analysis and other visual tasks. From station names and color-coded lines to transfer points and train movement, the challenge was to bring the network to life while keeping it easy to follow. Hy4 keeps its pricing unchanged at $0.834 per million input tokens, $2.501 per million output tokens and $0.042 per million tokens on cache hits. Here’s how it turned out. What kind of transit system would you like to see visualized? Explore WorkBuddy: Tencent Hy Tencent AI WorkBuddy

Jami

31,079 views • 1 day ago

Before anyone steps on stage, the lighting sets the mood. I created this stage lighting demo with Hy4 in WorkBuddy, exploring how a theatrical concept can take shape through code. Tencent worked with professional game developers at Tencent IEG to refine Hy4’s front-end and game development capabilities, including feature implementation and asset handling. Lighting can draw your attention to a focal point, define a space, and give a scene its atmosphere. That makes stage design a creative challenge where composition and technical execution need to work together. Hy4 keeps its pricing unchanged at $0.834 per million input tokens, $2.501 per million output tokens and $0.042 per million tokens on cache hits. For this project, I wanted to see how Hy4 would translate that visual direction into an on-screen experience. Here’s how it turned out. What kind of performance would you design the lighting for? Tencent Hy Tencent AI WorkBuddy

Before anyone steps on stage, the lighting sets the mood. I created this stage lighting demo with Hy4 in WorkBuddy, exploring how a theatrical concept can take shape through code. Tencent worked with professional game developers at Tencent IEG to refine Hy4’s front-end and game development capabilities, including feature implementation and asset handling. Lighting can draw your attention to a focal point, define a space, and give a scene its atmosphere. That makes stage design a creative challenge where composition and technical execution need to work together. Hy4 keeps its pricing unchanged at $0.834 per million input tokens, $2.501 per million output tokens and $0.042 per million tokens on cache hits. For this project, I wanted to see how Hy4 would translate that visual direction into an on-screen experience. Here’s how it turned out. What kind of performance would you design the lighting for? Tencent Hy Tencent AI WorkBuddy

Ted Cruz

16,423 views • 1 day ago

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI

I gave an AI one instruction: “Build me a playable 3D game from scratch.” Then I let it cook. 👀 I tested Tencent Hy4 preview inside WorkBuddy, and it went way beyond just generating a few snippets of code. It could: → Plan the game structure → Generate the code across files → Create the UI and interactions → Debug problems along the way → Iterate on the project while keeping context That last part is what caught my attention. Hy4 preview is built for these long-horizon tasks, with 770B total parameters, 49B active parameters, and a 1M-token context window. It’s designed for coding agents, game development, tool use, research, and other workflows where the model has to actually do the work, not just answer a prompt. And right now, you can try Hy4 preview for free on WorkBuddy until September 10. If you want to see how far an AI agent can take a real project, try it yourself: See what you can build with it. Tencent AI

Toha Khan

66,214 views • 2 months ago

Hy4 preview powers dynamic builds for a 770B open model. 770B total parameters, 49B active per token, native 1M context, Apache 2.0, direct vLLM and SGLang support, plus official FP8 weights. In this demo, Hy4 creates a colorful, playable 2D space shooter game directly from a prompt, featuring active controls, enemies, visual particle effects, plus score tracking. It is a preview. Test it, measure tokens/s, compare it with BF16 or FP8, and see what it builds. Try it in WorkBuddy: Tencent Hy WorkBuddy #Hy4Preview #OpenSourceAI #GameDev #AI

Hy4 preview powers dynamic builds for a 770B open model. 770B total parameters, 49B active per token, native 1M context, Apache 2.0, direct vLLM and SGLang support, plus official FP8 weights. In this demo, Hy4 creates a colorful, playable 2D space shooter game directly from a prompt, featuring active controls, enemies, visual particle effects, plus score tracking. It is a preview. Test it, measure tokens/s, compare it with BF16 or FP8, and see what it builds. Try it in WorkBuddy: Tencent Hy WorkBuddy #Hy4Preview #OpenSourceAI #GameDev #AI

Tyler Wayne

78,060 views • 1 month ago

Introducing Higgsfield 3D Jutsu, powered by GPT-6 Astra. Turn a single prompt into a fully editable, interactive 3D world. > Generate complex 3D scenes from text > Control geometry, layout, and details > Refine environment instantly with simple prompts Now live on Higgsfield.

Introducing Higgsfield 3D Jutsu, powered by GPT-6 Astra. Turn a single prompt into a fully editable, interactive 3D world. > Generate complex 3D scenes from text > Control geometry, layout, and details > Refine environment instantly with simple prompts Now live on Higgsfield.

Higgsfield AI 🧩

100,929 views • 2 months ago

Tried Hy4 preview through WorkBuddy and gave it a pretty vague prompt for a first person roller coaster ride, front row seat, make it feel fast, that was basically it. No detailed spec, no reference video, just a rough idea in a sentence. What came back actually held up. Steep drop that felt like the bottom dropping out, banked turns that leaned the right way, scenery rushing by close enough that you register the speed instead of just watching it happen. For something built off a loose prompt like that, I did not expect it to nail the feel this well. Coding and 3D rendering have clearly gotten a real upgrade here, and this took one pass to look this good. Free to try in WorkBuddy for the next two weeks if you want to mess with it yourself. Tencent Hy Tencent AI

Tried Hy4 preview through WorkBuddy and gave it a pretty vague prompt for a first person roller coaster ride, front row seat, make it feel fast, that was basically it. No detailed spec, no reference video, just a rough idea in a sentence. What came back actually held up. Steep drop that felt like the bottom dropping out, banked turns that leaned the right way, scenery rushing by close enough that you register the speed instead of just watching it happen. For something built off a loose prompt like that, I did not expect it to nail the feel this well. Coding and 3D rendering have clearly gotten a real upgrade here, and this took one pass to look this good. Free to try in WorkBuddy for the next two weeks if you want to mess with it yourself. Tencent Hy Tencent AI

Chubby♨️

27,793 views • 2 months ago

I gave WorkBuddy one prompt: build a campaign dashboard I could actually use. It planned the app, created CreatorFlow, ran it locally, and tested it on my computer. The result is a working system for campaigns, approvals, deliverables, and payments. Built with Hy4 Preview.

I gave WorkBuddy one prompt: build a campaign dashboard I could actually use. It planned the app, created CreatorFlow, ran it locally, and tested it on my computer. The result is a working system for campaigns, approvals, deliverables, and payments. Built with Hy4 Preview.

Kaitee

57,125 views • 2 months ago

🚨 I just built a game with an open-source AI model. And honestly… I didn’t expect it to be this capable. Tencent Hunyuan just released Hy4 preview, and it’s already pushing into the top tier of open-source models. Three major releases in six months. That pace is crazy. Here’s what Hy4 preview brings: → 770B total parameters → 49B active parameters → 1M+ token context window → Fully open-source But the numbers aren’t even the most interesting part. Hy4 preview was built around one goal: real-world productivity. Coding. Engineering. Office work. Science. Gaming. Finance. Security. And Tencent didn’t build it in isolation. Hy4 preview was co-designed alongside real products like WorkBuddy, using expertise and real-world data from across Tencent’s ecosystem. So I decided to test it the way I actually like testing AI models: I gave it a game idea and let WorkBuddy help turn it into a playable experience. 🎮 From the initial concept to the actual game logic, it was surprisingly smooth. And the benchmark results back up the hype: 163 internal experts 203 engineering tasks Hy4 preview — 2.99/4 Kimi K3 — 2.94/4 GLM 5.3 — 2.92/4 It also beats GLM 5.2 on benchmarks and comes remarkably close to GLM 5.3. Then comes the part I really like: 💰 ¥6/M input tokens 💰 ¥18/M output tokens 💰 ¥0.30/M cache hits Flagship-level capability without the flagship-level price. And right now, you can try Hy4 preview FREE through WorkBuddy for the next two weeks. If you’re curious what it can actually do, don’t just read the benchmarks. Build something with it. 🔗 Tencent Hy Tencent AI

🚨 I just built a game with an open-source AI model. And honestly… I didn’t expect it to be this capable. Tencent Hunyuan just released Hy4 preview, and it’s already pushing into the top tier of open-source models. Three major releases in six months. That pace is crazy. Here’s what Hy4 preview brings: → 770B total parameters → 49B active parameters → 1M+ token context window → Fully open-source But the numbers aren’t even the most interesting part. Hy4 preview was built around one goal: real-world productivity. Coding. Engineering. Office work. Science. Gaming. Finance. Security. And Tencent didn’t build it in isolation. Hy4 preview was co-designed alongside real products like WorkBuddy, using expertise and real-world data from across Tencent’s ecosystem. So I decided to test it the way I actually like testing AI models: I gave it a game idea and let WorkBuddy help turn it into a playable experience. 🎮 From the initial concept to the actual game logic, it was surprisingly smooth. And the benchmark results back up the hype: 163 internal experts 203 engineering tasks Hy4 preview — 2.99/4 Kimi K3 — 2.94/4 GLM 5.3 — 2.92/4 It also beats GLM 5.2 on benchmarks and comes remarkably close to GLM 5.3. Then comes the part I really like: 💰 ¥6/M input tokens 💰 ¥18/M output tokens 💰 ¥0.30/M cache hits Flagship-level capability without the flagship-level price. And right now, you can try Hy4 preview FREE through WorkBuddy for the next two weeks. If you’re curious what it can actually do, don’t just read the benchmarks. Build something with it. 🔗 Tencent Hy Tencent AI

Aryan Rakib

63,296 views • 1 month ago

🚨 Tencent Hunyuan just dropped Hy4 preview—and it’s already making its way into the open-source big leagues. Three major releases in six months. That’s seriously fast. Hy4 preview comes with: 770B total parameters 49B active parameters A 1M+ token context window And it’s built with one clear focus: productivity. We’re talking coding, office work, science, software engineering, gaming, finance, security, and more. But here’s the part that really caught my attention: Hy4 preview wasn’t developed in isolation. It was co-designed with real products like WorkBuddy. Tencent worked with experts from across its ecosystem to build the training data, then tested the model on real-world tasks. In a blind test involving 163 internal experts and 203 engineering tasks, the scores were: Hy4 preview: 2.99/4 Kimi K3: 2.94/4 GLM 5.3: 2.92/4 And performance isn’t the only impressive part. On benchmarks, Hy4 preview clearly outperforms GLM 5.2 and is basically neck-and-neck with GLM 5.3. Then there’s the pricing: $6/M input tokens $18/M output tokens $0.30/M cache hits That’s flagship-level performance without the flagship-level price. You can try Hy4 preview for FREE through WorkBuddy over the next two weeks: Tencent Hy @TencentAl_News

🚨 Tencent Hunyuan just dropped Hy4 preview—and it’s already making its way into the open-source big leagues. Three major releases in six months. That’s seriously fast. Hy4 preview comes with: 770B total parameters 49B active parameters A 1M+ token context window And it’s built with one clear focus: productivity. We’re talking coding, office work, science, software engineering, gaming, finance, security, and more. But here’s the part that really caught my attention: Hy4 preview wasn’t developed in isolation. It was co-designed with real products like WorkBuddy. Tencent worked with experts from across its ecosystem to build the training data, then tested the model on real-world tasks. In a blind test involving 163 internal experts and 203 engineering tasks, the scores were: Hy4 preview: 2.99/4 Kimi K3: 2.94/4 GLM 5.3: 2.92/4 And performance isn’t the only impressive part. On benchmarks, Hy4 preview clearly outperforms GLM 5.2 and is basically neck-and-neck with GLM 5.3. Then there’s the pricing: $6/M input tokens $18/M output tokens $0.30/M cache hits That’s flagship-level performance without the flagship-level price. You can try Hy4 preview for FREE through WorkBuddy over the next two weeks: Tencent Hy @TencentAl_News

AGAFE

131,568 views • 2 months ago

I’ve been testing Hy4 preview in WorkBuddy, and the most interesting part is not simply the model size, it’s how much practical work it can handle with a relatively focused active parameter count. Hy4 preview brings together stronger code understanding, generation, and editing; improved document and information processing; workflow automation; web and game development; cross-tool collaboration; and more reliable completion of complex, multi-step tasks. In other words, it is designed for work that requires planning, tool use, iteration, and follow-through, not just a quick answer in a chat window. Compared with its initial release, the current Hy4 preview is noticeably faster and better-performing in practical workflows. Following an upgrade released yesterday, it can complete tasks with fewer conversation rounds and lower token usage, while reasoning more quickly and making the overall user experience feel smoother from the first instruction to the final result. For my test, I gave it a demanding Three.js game-prototyping task with a 770B-parameter model and 49B active parameters. The result was more revealing than a simple first-look demo: Hy4 preview handled the core logic, edge cases, and follow-up changes while maintaining the broader context of the project. That combination of capability, speed, context, and active compute is what makes its cost-effectiveness worth examining. A fair evaluation should use the same prompt and environment configuration across models, changing only the model itself. That makes it easier to assess task completion, planning quality, tool-calling stability, reasoning speed, token efficiency, and performance over longer workflows without confusing the result with different settings. If you want to test the model yourself, access Hy4 preview through WorkBuddy and see how it performs on a real coding, document, automation, or creative task: Tencent Hy Tencent AI WorkBuddy

I’ve been testing Hy4 preview in WorkBuddy, and the most interesting part is not simply the model size, it’s how much practical work it can handle with a relatively focused active parameter count. Hy4 preview brings together stronger code understanding, generation, and editing; improved document and information processing; workflow automation; web and game development; cross-tool collaboration; and more reliable completion of complex, multi-step tasks. In other words, it is designed for work that requires planning, tool use, iteration, and follow-through, not just a quick answer in a chat window. Compared with its initial release, the current Hy4 preview is noticeably faster and better-performing in practical workflows. Following an upgrade released yesterday, it can complete tasks with fewer conversation rounds and lower token usage, while reasoning more quickly and making the overall user experience feel smoother from the first instruction to the final result. For my test, I gave it a demanding Three.js game-prototyping task with a 770B-parameter model and 49B active parameters. The result was more revealing than a simple first-look demo: Hy4 preview handled the core logic, edge cases, and follow-up changes while maintaining the broader context of the project. That combination of capability, speed, context, and active compute is what makes its cost-effectiveness worth examining. A fair evaluation should use the same prompt and environment configuration across models, changing only the model itself. That makes it easier to assess task completion, planning quality, tool-calling stability, reasoning speed, token efficiency, and performance over longer workflows without confusing the result with different settings. If you want to test the model yourself, access Hy4 preview through WorkBuddy and see how it performs on a real coding, document, automation, or creative task: Tencent Hy Tencent AI WorkBuddy

Tyler Wayne

56,152 views • 1 month ago

Once you have built one 3D world, coding a new one with AI using Three.js becomes much easier. Feed the existing code to AI, ask for variation ideas, then generate a prompt and refine the result through iterations. AI is also now quite capable of working with TSL.

Once you have built one 3D world, coding a new one with AI using Three.js becomes much easier. Feed the existing code to AI, ask for variation ideas, then generate a prompt and refine the result through iterations. AI is also now quite capable of working with TSL.

Techartist

21,331 views • 3 months ago

I wanted to see where Hy4 preview would stop, so I gave it a deliberately demanding prompt: “Build a working Cyber Incident Command Center.” Not a mockup. A real, responsive app with a live threat map, animated attack routes, incident simulation, filters, investigation panels, event logs, ownership controls, and working isolate/resolve actions. Hy4 preview planned the build, wrote the application, ran it locally, tested the interactions, checked the mobile layout, fixed issues, and opened the finished product for review. Then I clicked “Simulate.” A new incident appeared, the dashboard updated, I filtered it by severity, opened the evidence trail, isolated the affected system, and resolved it. The KPI counters changed with the action. That’s a much more useful coding demo to me than watching code appear in an editor. Hy4 preview is Hunyuan’s third major release in six months. It’s fully open-sourced, with 770B total parameters, 49B activated, and a 1M+ token context window. Tencent built it around productivity scenarios through close work with experts in software engineering, gaming, finance, and security, plus direct co-design with tools like WorkBuddy. In an internal blind test covering 203 engineering tasks and 163 Tencent experts, it scored 2.99/4—slightly ahead of Kimi K3 at 2.94 and GLM 5.3 at 2.92. And the pricing stays practical: $0.834/M input $2.501/M output $0.042/M cache hits If you want to test it yourself, Hy4 preview is free inside WorkBuddy for the next two weeks, for a limited time. Tencent Hy Tencent AI WorkBuddy

I wanted to see where Hy4 preview would stop, so I gave it a deliberately demanding prompt: “Build a working Cyber Incident Command Center.” Not a mockup. A real, responsive app with a live threat map, animated attack routes, incident simulation, filters, investigation panels, event logs, ownership controls, and working isolate/resolve actions. Hy4 preview planned the build, wrote the application, ran it locally, tested the interactions, checked the mobile layout, fixed issues, and opened the finished product for review. Then I clicked “Simulate.” A new incident appeared, the dashboard updated, I filtered it by severity, opened the evidence trail, isolated the affected system, and resolved it. The KPI counters changed with the action. That’s a much more useful coding demo to me than watching code appear in an editor. Hy4 preview is Hunyuan’s third major release in six months. It’s fully open-sourced, with 770B total parameters, 49B activated, and a 1M+ token context window. Tencent built it around productivity scenarios through close work with experts in software engineering, gaming, finance, and security, plus direct co-design with tools like WorkBuddy. In an internal blind test covering 203 engineering tasks and 163 Tencent experts, it scored 2.99/4—slightly ahead of Kimi K3 at 2.94 and GLM 5.3 at 2.92. And the pricing stays practical: $0.834/M input $2.501/M output $0.042/M cache hits If you want to test it yourself, Hy4 preview is free inside WorkBuddy for the next two weeks, for a limited time. Tencent Hy Tencent AI WorkBuddy

Clara Bennett

12,864 views • 2 months ago

I tested Tencent’s Hy4 preview model in WorkBuddy on a real frontend build, not a benchmark screenshot. I gave it one practical brief: create an original neon courier game in a single HTML file, with Canvas rendering, keyboard controls, collision detection, scoring, a countdown timer, a boost mechanic, sound effects, and reliable restart logic. The point was not to see whether it could describe a game. I wanted to see whether it could turn a creative idea into a coherent, playable result while handling the details that often break a quick prototype: state changes, movement, collisions, feedback, layout, and interaction flow. Tencent’s Hy4 preview is designed for stronger code understanding, generation, and editing, together with document and information processing, workflow automation, web and game development, cross-tool collaboration, and complex multi-step task completion. That makes it relevant not only for answering questions, but also for taking a task from brief to working output. The current preview version is faster and more effective than the first release. After the latest upgrade, the workflow takes fewer conversation rounds, uses fewer tokens, and reaches useful results more quickly. The difference is most noticeable in the handoff between idea, implementation, revision, and final testing: there is less waiting and less back-and-forth before the result becomes usable. For context, the reference materials describe Tencent’s Hy4 preview as a 770B-parameter model with 49B active parameters, a 1M-token context window, and Apache 2.0 weights. The practical question is how those capabilities translate into real work. In this case, I’m testing whether the model can produce a finished, playable game rather than just a promising code fragment. The one-minute video shows the complete process: selecting Tencent’s Hy4 preview model in WorkBuddy, submitting the build prompt, reviewing the generated result, playing the game, and checking the controls, collisions, score, timer, boost effect, sound, and restart flow. Try your own coding, frontend, document, or automation task in WorkBuddy: Tencent Hy Workbuddy Tencent AI

I tested Tencent’s Hy4 preview model in WorkBuddy on a real frontend build, not a benchmark screenshot. I gave it one practical brief: create an original neon courier game in a single HTML file, with Canvas rendering, keyboard controls, collision detection, scoring, a countdown timer, a boost mechanic, sound effects, and reliable restart logic. The point was not to see whether it could describe a game. I wanted to see whether it could turn a creative idea into a coherent, playable result while handling the details that often break a quick prototype: state changes, movement, collisions, feedback, layout, and interaction flow. Tencent’s Hy4 preview is designed for stronger code understanding, generation, and editing, together with document and information processing, workflow automation, web and game development, cross-tool collaboration, and complex multi-step task completion. That makes it relevant not only for answering questions, but also for taking a task from brief to working output. The current preview version is faster and more effective than the first release. After the latest upgrade, the workflow takes fewer conversation rounds, uses fewer tokens, and reaches useful results more quickly. The difference is most noticeable in the handoff between idea, implementation, revision, and final testing: there is less waiting and less back-and-forth before the result becomes usable. For context, the reference materials describe Tencent’s Hy4 preview as a 770B-parameter model with 49B active parameters, a 1M-token context window, and Apache 2.0 weights. The practical question is how those capabilities translate into real work. In this case, I’m testing whether the model can produce a finished, playable game rather than just a promising code fragment. The one-minute video shows the complete process: selecting Tencent’s Hy4 preview model in WorkBuddy, submitting the build prompt, reviewing the generated result, playing the game, and checking the controls, collisions, score, timer, boost effect, sound, and restart flow. Try your own coding, frontend, document, or automation task in WorkBuddy: Tencent Hy Workbuddy Tencent AI

Rebecca Adson

61,820 views • 1 month ago

What can a 770B model actually build? Hy4 preview is making that question more practical. 770B total / 49B active Native 1M context Apache 2.0 Day-0 vLLM + SGLang Official FP8 ~1.5TB → ~214GiB with mixed per-layer quant The interesting part: reported accuracy barely moves vs BF16. Here’s Hy4 turning a simple prompt into a playable game. A 770B-class model with a much lower deployment barrier. Tencent Hy

What can a 770B model actually build? Hy4 preview is making that question more practical. 770B total / 49B active Native 1M context Apache 2.0 Day-0 vLLM + SGLang Official FP8 ~1.5TB → ~214GiB with mixed per-layer quant The interesting part: reported accuracy barely moves vs BF16. Here’s Hy4 turning a simple prompt into a playable game. A 770B-class model with a much lower deployment barrier. Tencent Hy

Charles Roman

12,251 views • 2 months ago

EL MEJOR MODELO PARA PROGRAMAR DE ESTE MES ES GRATIS, ES OPEN SOURCE Y CASI NADIE LO ESTÁ MIRANDO. Hy4 preview de Tencent. Lo he estado usando en WorkBuddy y estas son las cosas que me han sorprendido: → Le pedí una ciudad isométrica 3D en Three.js y salió con coches, animales, shaders de agua y ciclo día/noche → Aguanta más de 1M de tokens sin perder el hilo → 770B parámetros totales, 49B activos, open source → Gratis en WorkBuddy dos semanas desde el lanzamiento Todas las capturas son mías, hechas mientras lo probaba. Link abajo :) Tencent Hy Tencent AI WorkBuddy

EL MEJOR MODELO PARA PROGRAMAR DE ESTE MES ES GRATIS, ES OPEN SOURCE Y CASI NADIE LO ESTÁ MIRANDO. Hy4 preview de Tencent. Lo he estado usando en WorkBuddy y estas son las cosas que me han sorprendido: → Le pedí una ciudad isométrica 3D en Three.js y salió con coches, animales, shaders de agua y ciclo día/noche → Aguanta más de 1M de tokens sin perder el hilo → 770B parámetros totales, 49B activos, open source → Gratis en WorkBuddy dos semanas desde el lanzamiento Todas las capturas son mías, hechas mientras lo probaba. Link abajo :) Tencent Hy Tencent AI WorkBuddy

marcus

38,964 views • 2 months ago

Tencent just dropped Hy4 preview, and it's officially open source now. 770B total params, 49B active, 1M+ token context. three major releases in six months, and this one just landed in the top tier of open source models. → Built through Tencent's co-design loop: training data shaped with experts across software engineering, gaming, finance, and security, then built directly alongside products like WorkBuddy → In a blind test with 163 internal experts across 203 engineering tasks, it scored 2.99/4, ahead of GLM 5.3 at 2.92 and Kimi K3 at 2.94 → Benchmarks put it clearly past GLM 5.2 and neck and neck with GLM 5.3 → Pricing stayed low: $0.834/M input, $2.501/M output, $0.042/M cache hits I asked it to write a weekly status update email template for a team lead, then generate a filled-out example with placeholder projects, and export both as Word docs. one prompt, no follow-up, and it handed back both files clean and ready to send. free to try for the next two weeks through WorkBuddy: Tencent Hy Tencent AI WorkBuddy

Tencent just dropped Hy4 preview, and it's officially open source now. 770B total params, 49B active, 1M+ token context. three major releases in six months, and this one just landed in the top tier of open source models. → Built through Tencent's co-design loop: training data shaped with experts across software engineering, gaming, finance, and security, then built directly alongside products like WorkBuddy → In a blind test with 163 internal experts across 203 engineering tasks, it scored 2.99/4, ahead of GLM 5.3 at 2.92 and Kimi K3 at 2.94 → Benchmarks put it clearly past GLM 5.2 and neck and neck with GLM 5.3 → Pricing stayed low: $0.834/M input, $2.501/M output, $0.042/M cache hits I asked it to write a weekly status update email template for a team lead, then generate a filled-out example with placeholder projects, and export both as Word docs. one prompt, no follow-up, and it handed back both files clean and ready to send. free to try for the next two weeks through WorkBuddy: Tencent Hy Tencent AI WorkBuddy

D-Coder

109,317 views • 2 months ago

AI 3D is getting much better at turning ideas into complete scenes. I’ve been checking out SEELE AI’s 3D Agent, and the part I found most interesting is how quickly it can turn a prompt or creative idea into a detailed 3D scene. Instead of generating a single isolated object, SeeleAgent can build out the broader environment and 3D models while keeping the result closely aligned with the original concept. That makes it much more useful for quickly turning an idea into a high-quality 3D scene without building everything manually. Try SeeleAgent here 👇 #seele #seeleai #3d

AI 3D is getting much better at turning ideas into complete scenes. I’ve been checking out SEELE AI’s 3D Agent, and the part I found most interesting is how quickly it can turn a prompt or creative idea into a detailed 3D scene. Instead of generating a single isolated object, SeeleAgent can build out the broader environment and 3D models while keeping the result closely aligned with the original concept. That makes it much more useful for quickly turning an idea into a high-quality 3D scene without building everything manually. Try SeeleAgent here 👇 #seele #seeleai #3d

Liam | AI Tools & News

14,722 views • 2 months ago