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。

🔫 Badass! A team at the Mistral AI hackathon in SF trained the 7B open-source model to play DOOM, based on an ASCII representation of the current frame in the game. 🤯 John Carmack

👩‍💻 Paige Bailey

74,306 subscribers

857,627 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

James Cham 的头像

James Cham2 年前

@MistralAI @ID_AA_Carmack Is this text representation basically the equivalent of the matrix?

joe Sabado 的头像

joe Sabado2 年前

@MistralAI @ID_AA_Carmack Anyone still has a copy of Zork? How would that convert to interactive video game?

👩‍💻 Paige Bailey 的头像

👩‍💻 Paige Bailey2 年前

@MistralAI @ID_AA_Carmack SUPER WELL 😁

Adrian Dittmann 的头像

Adrian Dittmann2 年前

@MistralAI @ID_AA_Carmack It can play doom! 🔥

Pim de Witte 的头像

Pim de Witte2 年前

@MistralAI @ID_AA_Carmack If anyone on this team wants a job send me a dm lol

Simon 的头像

Simon2 年前

@MistralAI @ID_AA_Carmack To be clear, we could do this with a vision model, with a powerful enough model that could take a screenshot every every one second or something something I would imagine could also output the commands to play doom well enough

Hax⚡️ 的头像

Hax⚡️2 年前

@MistralAI @ID_AA_Carmack

Sasha Sheng 🫶🏼 的头像

Sasha Sheng 🫶🏼2 年前

@MistralAI @ID_AA_Carmack WOW

stijn sagaert 的头像

stijn sagaert2 年前

@MistralAI @ID_AA_Carmack Giving a whole new meaning to "can it run doom?"

beowulf 的头像

beowulf2 年前

@MistralAI @ID_AA_Carmack amazing

相关视频

This may look like a game of Counterstrike running slowly, but it actually extraordinary. The entire game is created, frame-by-frame, on my *home computer* by an AI diffusion model in response to my actions. There is no game engine, just a "world model" trained on Counterstrike

This may look like a game of Counterstrike running slowly, but it actually extraordinary. The entire game is created, frame-by-frame, on my home computer by an AI diffusion model in response to my actions. There is no game engine, just a "world model" trained on Counterstrike

Ethan Mollick

376,399 次观看 • 1 年前

Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and kyutai, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.

Introducing MIRA. A playable, multiplayer world model. A dream of Rocket League. Trained on 10k hours of data collected with publicly available bots, MIRA learns the dynamics of a four-player game. The model runs in real time at 20 fps, based on the keys you and the other players press. Built by General Intuition and kyutai, in collaboration with Epic Games. Not used to develop Rocket League. ▶️ Play the demo, read the technical report, and explore the open-source code at At ICML? Find us at Booth 111 to try it yourself and dig into the results with the team.

General Intuition

455,671 次观看 • 19 天前

So grateful to have won second place at the Mistral AI SHACK15 Cerebral Valley hackathon with AI Pacman (watch an AI agent play Pacman fully autonomously from an image per frame). Thanks so all the organizer and sponsors - esp Fireworks AI and Dmytro Dzhulgakov

So grateful to have won second place at the Mistral AI SHACK15 Cerebral Valley hackathon with AI Pacman (watch an AI agent play Pacman fully autonomously from an image per frame). Thanks so all the organizer and sponsors - esp Fireworks AI and Dmytro Dzhulgakov

Peggy Wang

33,324 次观看 • 2 年前

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

Simplifying AI

278,796 次观看 • 6 个月前

Mad times! ASCII Doom. Jeffrey Emanuel got a swarm of AI agents to build a new highly-optimised Terminal UI engine from scratch in a few days called FrankenTUI. So I hooked up Doom to see if it would work with terminal half-block rendering.. and it does. 🤯 cc John Carmack

Mad times! ASCII Doom. Jeffrey Emanuel got a swarm of AI agents to build a new highly-optimised Terminal UI engine from scratch in a few days called FrankenTUI. So I hooked up Doom to see if it would work with terminal half-block rendering.. and it does. 🤯 cc John Carmack

Mike Kelly

17,473 次观看 • 5 个月前

Turns out when you’re cracked at math, you can make a text-based ASCII Doom in C that runs in the terminal.

Turns out when you’re cracked at math, you can make a text-based ASCII Doom in C that runs in the terminal.

tetsuo

2,982,465 次观看 • 1 年前

the legendary John Carmack on the love of the craft in programming:

the legendary John Carmack on the love of the craft in programming:

ℏεsam

51,145 次观看 • 4 个月前

Wow, diffusion models (used in AI image generation) are also game engines - a type of world simulation. By predicting the next frame of the classic shooter DOOM, you get a playable game at 20 fps without any underlying real game engine. This video is from the diffusion model.

Wow, diffusion models (used in AI image generation) are also game engines - a type of world simulation. By predicting the next frame of the classic shooter DOOM, you get a playable game at 20 fps without any underlying real game engine. This video is from the diffusion model.

Ethan Mollick

1,768,873 次观看 • 1 年前

Open-source AI is changing the game, and we're here for it! 🚀 From launching Qwen-7B in 2023, we’re empowering creators and innovators everywhere to shape the future of AI. 💡🌍 #Opensource #AlibabaAI #Qwen

Open-source AI is changing the game, and we're here for it! 🚀 From launching Qwen-7B in 2023, we’re empowering creators and innovators everywhere to shape the future of AI. 💡🌍 #Opensource #AlibabaAI #Qwen

Alibaba Group

402,487 次观看 • 1 年前

Today I saw the launch of another "open-source" AI wearable that has not published anything just to charge you 5x the cost At Mistral AI x Cerebral Valley hackathon in SHACK15 we built FRIEND - an AI Wearable that: - Works 24+ hours on a single charge - Costs ~$20 - Remembers what you say, gives you feedback - Understands you via voice or chat - Has 2 apps (one for device and one standalone) Give us 24 hours to finish the hackathon and publish the GitHub repo

Today I saw the launch of another "open-source" AI wearable that has not published anything just to charge you 5x the cost At Mistral AI x Cerebral Valley hackathon in SHACK15 we built FRIEND - an AI Wearable that: - Works 24+ hours on a single charge - Costs ~$20 - Remembers what you say, gives you feedback - Understands you via voice or chat - Has 2 apps (one for device and one standalone) Give us 24 hours to finish the hackathon and publish the GitHub repo

Nik Shevchenko

509,183 次观看 • 2 年前

Microsoft has created an AI-generated replica of Quake II that you can play in browser. "Every frame is created on the fly by an AI world model." Play it here:

Microsoft has created an AI-generated replica of Quake II that you can play in browser. "Every frame is created on the fly by an AI world model." Play it here:

Geoff Keighley

3,877,326 次观看 • 1 年前

We just released the world's first open-source humanoid physical strike AI! The AI is trained with large-scale self-play RL with a pre-trained ASE model from Jason Peng. Thank ZiyiBird for this amazing work.

We just released the world's first open-source humanoid physical strike AI! The AI is trained with large-scale self-play RL with a pre-trained ASE model from Jason Peng. Thank ZiyiBird for this amazing work.

Flood Sung

101,777 次观看 • 3 年前

🚨 BREAKING: NVIDIA just removed the biggest friction point in Voice AI They open-sourced PersonaPlex 7B, a real-time conversational model. It listens and speaks simultaneously to handle natural interruptions and overlaps. 100% Open Source.

🚨 BREAKING: NVIDIA just removed the biggest friction point in Voice AI They open-sourced PersonaPlex 7B, a real-time conversational model. It listens and speaks simultaneously to handle natural interruptions and overlaps. 100% Open Source.

How To Prompt

702,251 次观看 • 3 个月前

French President Macron: France is the only country in Europe to have an LLM model capable of competing with the great Americans and the great Chinese with Mistral AI.

French President Macron: France is the only country in Europe to have an LLM model capable of competing with the great Americans and the great Chinese with Mistral AI.

Clash Report

1,052,246 次观看 • 1 个月前

Sunday: hundreds of developers in SF are committed to AI growth at the hackathon with GPT plugins hosted by OpenAI Cerebral Valley and SHACK15 jorn lyseggen #ai

Sunday: hundreds of developers in SF are committed to AI growth at the hackathon with GPT plugins hosted by OpenAI Cerebral Valley and SHACK15 jorn lyseggen #ai

Jeremiah Owyang

34,245 次观看 • 3 年前

Google researchers just developed GameNGen, an AI that can simulate DOOM at over 20 fps It works by predicting each frame in real time with a diffusion model At scale this could mean AI will be able to create games on the fly, personalized to each player

Google researchers just developed GameNGen, an AI that can simulate DOOM at over 20 fps It works by predicting each frame in real time with a diffusion model At scale this could mean AI will be able to create games on the fly, personalized to each player

Rowan Cheung

880,346 次观看 • 1 年前

Throwback to the time Kobe Bryant put on a SHOOTING CLINIC against Team LeBron in a 2007 Team USA scrimmage. Not only did Kobe take the last shot but he stepped up to guard LeBron at the end of the game. 👀 More competitive than an All-Star game in today's current NBA. 🔥

Throwback to the time Kobe Bryant put on a SHOOTING CLINIC against Team LeBron in a 2007 Team USA scrimmage. Not only did Kobe take the last shot but he stepped up to guard LeBron at the end of the game. 👀 More competitive than an All-Star game in today's current NBA. 🔥

NBA Strife ツ

112,948 次观看 • 2 年前

Just a month later and the first AI model that can generate live and interactive playable dynamic worlds is here It's called GameNGen and is trained on the classic game DOOM

Just a month later and the first AI model that can generate live and interactive playable dynamic worlds is here It's called GameNGen and is trained on the classic game DOOM

@levelsio

519,186 次观看 • 1 年前

Vibe video: 400 AI developers are building at the Cerebral Valley Hackaton with Mistral AI in SF at SHACK15 —I’m one of the first round judges. There’s no other city that is building as quickly in AI as San Francisco.

Vibe video: 400 AI developers are building at the Cerebral Valley Hackaton with Mistral AI in SF at SHACK15 —I’m one of the first round judges. There’s no other city that is building as quickly in AI as San Francisco.

Jeremiah Owyang

28,128 次观看 • 2 年前