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.

Asked MiniMax M3 for a playable 3D game. No engine, no assets, one HTML file. It built the endless neon tunnel, the scoring rings, a 3-life system, and an autopilot mode that flies the ship on its own. It didn't land first try. I told it what looked wrong... show more

Leo

47,834 subscribers

14,730 views • 3 months ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

I gave EvoX Agent one prompt and asked it to build me a game. This is what came out 👇🏼 A playable browser game called Neon Dodge: built from scratch in Code Mode with movement, obstacles, scoring, increasing difficulty, and a full restart loop. Here’s how it happened.

I gave EvoX Agent one prompt and asked it to build me a game. This is what came out 👇🏼 A playable browser game called Neon Dodge: built from scratch in Code Mode with movement, obstacles, scoring, increasing difficulty, and a full restart loop. Here’s how it happened.

marcus

34,239 views • 2 months ago

This might be the craziest way I’ve ever used AI Agents. I gave MiniMax Design 2 iconic meme references and asked its AI Agent to connect them with one seamless cinematic FPV move. It analyzed the idea, broke down the sequence and built the MiniMax H3 prompt for me. The result is absolutely ridiculous. 🔥 I’m dropping the exact MiniMax Design prompt in the thread so you can try it yourself 👇 #MiniMaxH3 on #MiniMaxDesign

This might be the craziest way I’ve ever used AI Agents. I gave MiniMax Design 2 iconic meme references and asked its AI Agent to connect them with one seamless cinematic FPV move. It analyzed the idea, broke down the sequence and built the MiniMax H3 prompt for me. The result is absolutely ridiculous. 🔥 I’m dropping the exact MiniMax Design prompt in the thread so you can try it yourself 👇 #MiniMaxH3 on #MiniMaxDesign

Pierrick Chevallier | IA

52,774 views • 2 months ago

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

MiniMax is the James Bond of AI agents. It uses the world's first open-weight model (MiniMax-M1), and it squeezes every bit of power from it. The agent takes a prompt and does more than any other agent in the market right now: 1. It can do Deep Research 2. It can write code 3. It can design web pages 4. It can build 3D models I built 5 different experiences using MiniMax and recorded them for you:

Santiago

45,328 views • 1 year ago

MOONSHOT JUST CLONED CLAUDE CODE AND MADE IT FREE. It's called Kimi Code CLI. Open source, MIT license, maintained by the lab that shipped K3 yesterday. And it does things Claude Code doesn't: → drop a screen recording into the chat as input → built-in coder, explore, and plan subagents, each in its own context → plan mode before it touches a single file → MCP servers configured by the agent itself via /mcp-config → plugs into Zed, JetBrains, and VS Code → one binary, no Node setup, starts in milliseconds The CLI costs $0. K3 behind it starts at $3 per million tokens. Grab it for free👇

MOONSHOT JUST CLONED CLAUDE CODE AND MADE IT FREE. It's called Kimi Code CLI. Open source, MIT license, maintained by the lab that shipped K3 yesterday. And it does things Claude Code doesn't: → drop a screen recording into the chat as input → built-in coder, explore, and plan subagents, each in its own context → plan mode before it touches a single file → MCP servers configured by the agent itself via /mcp-config → plugs into Zed, JetBrains, and VS Code → one binary, no Node setup, starts in milliseconds The CLI costs $0. K3 behind it starts at $3 per million tokens. Grab it for free👇

darkzodchi

408,234 views • 3 months ago

🚨 one person can now do the work of an entire creative team. i just tested it on a real one. a friend needed an ad for his brand, so I opened the new Runway Agent 2.0 to try it out. here's how it went: → it generated the music and the key image first, so I could approve the direction → once I gave the ok, it built the full video around it → and when something was off, i changed just that one piece, without redoing the rest one prompt, and I had the ad we needed, work that used to take weeks. this is what it made 👇 if you want to try it → · 30% off 3 months with code RUNWAYAGENT — made with Runway · #MadeWithRunway · #ad

brenz.

28,770 views • 4 months ago

truly impressed by MiniMax (official) m3's visual coding Nous Research Hermes Desktop Agent + Minimax M3 built the whole thing 🌺 I didn't open a single TouchDesigner node for this

truly impressed by MiniMax (official) m3's visual coding Nous Research Hermes Desktop Agent + Minimax M3 built the whole thing 🌺 I didn't open a single TouchDesigner node for this

Amber Shen

16,242 views • 5 months ago

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.

You've probably scrolled past a dozen posts about Jev this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.

John Turner

21,029 views • 1 month ago

THE DESK RAN SIX DAYS FOR FREE AND CLOSED 96% OF 400 CALLS BEFORE IT HAD A TICKER -> TODAY IT GETS ONE $NYSE IS LIVE ON ROBINHOOD CHAIN, BUILT WITH MINARA AI AND GPT-6 ASTRA, AND THE SCORECARD IS OLDER THAN THE CHART CA: 0x3cedefe814e47b297743c82c20f947053ee667dd Every other ticker on this chain launches with a promise. This one launches with 400 receipts. What is already running while you read this: > An agent reading all 24 Robinhood Stock Tokens against the real share price every 20 seconds. > A line at 1.0% while the real NYSE is open, 1.5% the moment the bell rings and the oracle stops moving. > A scorecard with 386 hits, 14 misses and 2 calls open right now, nothing deleted, nothing hidden. The real NYSE opens in thirty minutes. The desk tightens its own line the second it does. Every call lands in Telegram before it lands anywhere else, the board is public and free, and the code is open with no wallet in it. There is a room on Wall Street that does this with forty people and a data bill with a comma in it. Mine is one agent, one laptop and now one ticker. Holders get the faster board, the earlier alerts and the agent's own stops, in that order. $NYSE SEE YOU AFTER THE BELL ↓

THE DESK RAN SIX DAYS FOR FREE AND CLOSED 96% OF 400 CALLS BEFORE IT HAD A TICKER -> TODAY IT GETS ONE $NYSE IS LIVE ON ROBINHOOD CHAIN, BUILT WITH MINARA AI AND GPT-6 ASTRA, AND THE SCORECARD IS OLDER THAN THE CHART CA: 0x3cedefe814e47b297743c82c20f947053ee667dd Every other ticker on this chain launches with a promise. This one launches with 400 receipts. What is already running while you read this: > An agent reading all 24 Robinhood Stock Tokens against the real share price every 20 seconds. > A line at 1.0% while the real NYSE is open, 1.5% the moment the bell rings and the oracle stops moving. > A scorecard with 386 hits, 14 misses and 2 calls open right now, nothing deleted, nothing hidden. The real NYSE opens in thirty minutes. The desk tightens its own line the second it does. Every call lands in Telegram before it lands anywhere else, the board is public and free, and the code is open with no wallet in it. There is a room on Wall Street that does this with forty people and a data bill with a comma in it. Mine is one agent, one laptop and now one ticker. Holders get the faster board, the earlier alerts and the agent's own stops, in that order. $NYSE SEE YOU AFTER THE BELL ↓

slash1s

59,833 views • 1 month ago

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Cognition

15,146,269 views • 6 months ago

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Devin for Terminal is the first CLI agent with its own dedicated virtual machine. You can start a project locally and hand it off to Devin to test it end-to-end. Devin for Terminal is super performant, and it works with all frontier models. Try it out today.

Cognition

24,723,355 views • 6 months ago

MiniMax H3 Fit Check You can try it with your own character. There's also a normal version in the replies. You can find the prompts in the replies.

MiniMax H3 Fit Check You can try it with your own character. There's also a normal version in the replies. You can find the prompts in the replies.

Kōda

15,993 views • 1 month ago

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just built a Meta Ads diagnostic in Claude Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

12,918 views • 5 months ago

If you could describe ANY game in plain English… and watch AI build it for you — what would you make? 👀 That’s exactly what I tried with Gear Zero. No engine. No coding. No files. No installation. Just describe the game → AI plans it, codes it, creates the art, builds the levels → and you’re playing it in your browser. And it gets crazier: ⚡ First version in ~20 minutes 🤝 Build & shape games together 🧠 Deep Mode can work on one game for up to 10 hours 🎮 Play instantly on desktop or phone 🆓 Free to start This isn’t just AI generating a game. It’s AI helping you actually BUILD one. Describe your game. Watch it become real. Try Gear Zero 👇 Gear Zero

If you could describe ANY game in plain English… and watch AI build it for you — what would you make? 👀 That’s exactly what I tried with Gear Zero. No engine. No coding. No files. No installation. Just describe the game → AI plans it, codes it, creates the art, builds the levels → and you’re playing it in your browser. And it gets crazier: ⚡ First version in ~20 minutes 🤝 Build & shape games together 🧠 Deep Mode can work on one game for up to 10 hours 🎮 Play instantly on desktop or phone 🆓 Free to start This isn’t just AI generating a game. It’s AI helping you actually BUILD one. Describe your game. Watch it become real. Try Gear Zero 👇 Gear Zero

Succeeded Mind

22,880 views • 2 months ago

MiniMax H3 Character Fast Cut Montage I loved how this style turned out! Feel free to try it with your own characters. You can find the prompt in the replies.

MiniMax H3 Character Fast Cut Montage I loved how this style turned out! Feel free to try it with your own characters. You can find the prompt in the replies.

Kōda

26,417 views • 1 month ago

I built an AI agent in 15 minutes. Gave it a name, a purpose. And started charging $9/month for access. Now it handles 500+ conversations a week. Let me show you the process (no coding): 👇

I built an AI agent in 15 minutes. Gave it a name, a purpose. And started charging $9/month for access. Now it handles 500+ conversations a week. Let me show you the process (no coding): 👇

EyeingAI

266,070 views • 1 year ago

Someone gave Claude Code the raw machine code of Minecraft for the 3DS, with no source code, and it found a 3D renderer that Mojang switched off after the first frame and later deleted. It then rebuilt the 3D for the current version of the game. He also used it to give Terraria 3DS real depth per layer, which the game never had. This is the poster's own account, it's homebrew on copyrighted games, and I couldn't check the claims independently. What other lost features do you think AI could find?

Someone gave Claude Code the raw machine code of Minecraft for the 3DS, with no source code, and it found a 3D renderer that Mojang switched off after the first frame and later deleted. It then rebuilt the 3D for the current version of the game. He also used it to give Terraria 3DS real depth per layer, which the game never had. This is the poster's own account, it's homebrew on copyrighted games, and I couldn't check the claims independently. What other lost features do you think AI could find?

0xMarioNawfal

42,521 views • 9 days ago

What Caffeine actually spits out when it builds you an app You describe the app in plain English. It writes the code, deploys it, and keeps updating it, with nobody touching the codebase. It writes Motoko, DFINITY Foundation's own language, and ships straight to canisters on $ICP. dom | icp's bet is that coders will ship straight on chain, growing the ecosystem.

What Caffeine actually spits out when it builds you an app You describe the app in plain English. It writes the code, deploys it, and keeps updating it, with nobody touching the codebase. It writes Motoko, DFINITY Foundation's own language, and ships straight to canisters on $ICP. dom | icp's bet is that coders will ship straight on chain, growing the ecosystem.

BSCN

41,153 views • 3 months ago

I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.

I explored a further possibility with local models: Qwen3.6 35B A3B + NVIDIA LocateAnything-3B as a local Computer Use agent (proof of concept). In the demo, I asked it to switch my Mac to light mode. It did. Then back to dark. Did that too — finding the right toggle in System Settings, clicking it, and verifying the change itself. It's fully screenshot-based, so no Accessibility API needed. If it's on screen, the agent can see it and act on it. This runs entirely on your own hardware — private, local, built from two small open models.

stevibe

44,330 views • 5 months ago

Announcing 100% free MiniMax M3 with a blazing fast provider. - Up to 200 tokens/sec 🔥 - It's so good we had to crown it "RECOMMENDED"! Try now, it's free: npm i -g freebuff

Announcing 100% free MiniMax M3 with a blazing fast provider. - Up to 200 tokens/sec 🔥 - It's so good we had to crown it "RECOMMENDED"! Try now, it's free: npm i -g freebuff

James Grugett

44,530 views • 4 months ago