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。

Today, we’re releasing SpeedrunBench: the first benchmark that measures how fast agents can beat video games. We asked frontier models not to simply complete video games, but to speedrun them - across 10 titles like Mario Kart and Pokemon. On simpler games, agents get close to the human world... show more

Anand Kannappan

1,760 subscribers

142,594 次观看 • 1 个月前 •via X (Twitter)

科学技术游戏

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Today we’re releasing APK Arena: a frontier benchmark for evaluating AI agents on phone-use. We ran GPT 5.6 for a side by side comparison where it outperformed other models across the board and is currently leading on APK Arena. 50+ levels: taps, vision, memory, games, real tasks. Here's how it did vs every other frontier model 🧵

Today we’re releasing APK Arena: a frontier benchmark for evaluating AI agents on phone-use. We ran GPT 5.6 for a side by side comparison where it outperformed other models across the board and is currently leading on APK Arena. 50+ levels: taps, vision, memory, games, real tasks. Here's how it did vs every other frontier model 🧵

Jan Schnyder

10,143 次观看 • 3 个月前

The world is severely underestimating the value of AI Gaming Agents in Web3 games Imagine you're playing The Sandbox Attack on Titan and you're playing with AI Agents that navigate like real humans Metaverse games are going to COOK!

The world is severely underestimating the value of AI Gaming Agents in Web3 games Imagine you're playing The Sandbox Attack on Titan and you're playing with AI Agents that navigate like real humans Metaverse games are going to COOK!

Brycent

22,217 次观看 • 1 年前

Can GPT, Claude, and Gemini play video games like Zelda, Civ, and Doom II? 𝗩𝗶𝗱𝗲𝗼𝗚𝗮𝗺𝗲𝗕𝗲𝗻𝗰𝗵 evaluates VLMs on Game Boy & MS-DOS games given only raw screen input, just like how a human would play. The best model (Gemini) completes just 0.48% of the benchmark! 🧵👇

Can GPT, Claude, and Gemini play video games like Zelda, Civ, and Doom II? 𝗩𝗶𝗱𝗲𝗼𝗚𝗮𝗺𝗲𝗕𝗲𝗻𝗰𝗵 evaluates VLMs on Game Boy & MS-DOS games given only raw screen input, just like how a human would play. The best model (Gemini) completes just 0.48% of the benchmark! 🧵👇

alex zhang

134,163 次观看 • 1 年前

Today we announced the Kaggle Game Arena, a new benchmarking platform where AI models and agents can compete head-to-head in strategic games, starting with chess ♟️. Why games, you ask? 🤔 Games are perfect for AI evaluation because they help us understand how models tackle complex reasoning tasks. Many games are a proxy for real-world skills and can test a model's ability in areas like strategic planning, adaptation, and memory. To inaugurate the Game Arena, we're launching an AI chess exhibition tournament. The world’s leading AI models will battle in head-to-head games in a multi-day event running from August 5-7 with streamed games happening daily. Tune-in to root for your favorites at

Today we announced the Kaggle Game Arena, a new benchmarking platform where AI models and agents can compete head-to-head in strategic games, starting with chess ♟️. Why games, you ask? 🤔 Games are perfect for AI evaluation because they help us understand how models tackle complex reasoning tasks. Many games are a proxy for real-world skills and can test a model's ability in areas like strategic planning, adaptation, and memory. To inaugurate the Game Arena, we're launching an AI chess exhibition tournament. The world’s leading AI models will battle in head-to-head games in a multi-day event running from August 5-7 with streamed games happening daily. Tune-in to root for your favorites at

Google AI

132,302 次观看 • 1 年前

What is the best LLM for agentic software engineering? Today, we're releasing The OpenHands Index to answer this question. It's the first broad-coverage benchmark for AI coding agents, comparing them on accuracy, cost, and runtime across 5 task domains.

What is the best LLM for agentic software engineering? Today, we're releasing The OpenHands Index to answer this question. It's the first broad-coverage benchmark for AI coding agents, comparing them on accuracy, cost, and runtime across 5 task domains.

OpenHands

31,924 次观看 • 8 个月前

This is the moment robots crash yet again on the closing day of the Humanoid Robot Games in Beijing, after Chinese robot Tian Jiao shattered the 100 metre sprint record in 8.64 seconds. But whilst robots are able to beat the human record, they seem to find stopping after the race significantly more difficult, often crashing into padded barriers and sometimes catching fire throughout the games. The second World Humanoid Robot Games brought together more than 2000 robots for 51 sporting and scenario-based events.

This is the moment robots crash yet again on the closing day of the Humanoid Robot Games in Beijing, after Chinese robot Tian Jiao shattered the 100 metre sprint record in 8.64 seconds. But whilst robots are able to beat the human record, they seem to find stopping after the race significantly more difficult, often crashing into padded barriers and sometimes catching fire throughout the games. The second World Humanoid Robot Games brought together more than 2000 robots for 51 sporting and scenario-based events.

Channel 4 News

39,232 次观看 • 1 个月前

New Kimi K3 beat Opus 4.8 at making retro games for 2x cheaper! We gave three models the same task: make three old arcade games that play by themselves. Each game is one HTML file with a bot that plays it Prompts: – Road Fighter – Battle City – Q*bert Outputs: Kimi K3: 18.4K tokens, $0.28 GPT-5.6: 18.1K tokens, $0.28 Opus 4.8: 21.3K tokens, $0.54 Kimi K3 made the best games. Its Q*bert is the best of all three. The player jumps on the cubes, paints them and runs from the purple snake. Its Battle City looks just like the real game and plays right. The tanks move, aim, shoot and break the walls. GPT-5.6 could not handle the cars. Its Battle City broke too. The tank died on its own and the base got hit. But GPT had the nicest textures of the three

New Kimi K3 beat Opus 4.8 at making retro games for 2x cheaper! We gave three models the same task: make three old arcade games that play by themselves. Each game is one HTML file with a bot that plays it Prompts: – Road Fighter – Battle City – Qbert Outputs: Kimi K3: 18.4K tokens, $0.28 GPT-5.6: 18.1K tokens, $0.28 Opus 4.8: 21.3K tokens, $0.54 Kimi K3 made the best games. Its Qbert is the best of all three. The player jumps on the cubes, paints them and runs from the purple snake. Its Battle City looks just like the real game and plays right. The tanks move, aim, shoot and break the walls. GPT-5.6 could not handle the cars. Its Battle City broke too. The tank died on its own and the base got hit. But GPT had the nicest textures of the three

atomic.chat

100,437 次观看 • 2 个月前

today, we’re partnering with Natural to let users send money to agents, all over text. at linq, we believe agents should talk to us like we talk to each other. we give agents phones, so they can call, text, FaceTime, play games, and do work for millions of people. Natural lets agents move money through the world just like people would. now, all that can happen over text. the future is bright!

today, we’re partnering with Natural to let users send money to agents, all over text. at linq, we believe agents should talk to us like we talk to each other. we give agents phones, so they can call, text, FaceTime, play games, and do work for millions of people. Natural lets agents move money through the world just like people would. now, all that can happen over text. the future is bright!

Elliott Potter

30,203 次观看 • 2 个月前

Eigent day 0 supports MiniMax (official) M2.5! Try M2.5 on your open source cowork! With Chinese New Year (Horse) coming, we asked Eigent to generate 10 complete HTML/CSS/JS games (no libraries) across arcade, puzzle, runner, strategy, memory, idle and more. The Developer Agent called the Terminal Toolkit, generated all 10 games, and saved them locally. Games are insanely fun and you can play them directly inside Eigent. Try it out today!

Eigent day 0 supports MiniMax (official) M2.5! Try M2.5 on your open source cowork! With Chinese New Year (Horse) coming, we asked Eigent to generate 10 complete HTML/CSS/JS games (no libraries) across arcade, puzzle, runner, strategy, memory, idle and more. The Developer Agent called the Terminal Toolkit, generated all 10 games, and saved them locally. Games are insanely fun and you can play them directly inside Eigent. Try it out today!

Eigent AI

13,816 次观看 • 8 个月前

Mobile games are a $157B industry and nobody is shipping them. Multi-millionaire Game studios have ran a monopoly for decades on all the top mobile games.. but now they are scared. Because the playing field has evened I just made this mobile game the same one you see on the fake ads. with $100k/mo in meta spend in literally 1 prompt to Claude opus 5, higgsfield mcp made all the assets and textures. There are simple games like these making $200,000/mo + with over 50% profit margins. people that play video games are not thinking about vibe coding their own game they just want to play something fun. im bullish on video games during the AI race. I made an article on how I use claude to get insane results like this link below:

Mobile games are a $157B industry and nobody is shipping them. Multi-millionaire Game studios have ran a monopoly for decades on all the top mobile games.. but now they are scared. Because the playing field has evened I just made this mobile game the same one you see on the fake ads. with $100k/mo in meta spend in literally 1 prompt to Claude opus 5, higgsfield mcp made all the assets and textures. There are simple games like these making $200,000/mo + with over 50% profit margins. people that play video games are not thinking about vibe coding their own game they just want to play something fun. im bullish on video games during the AI race. I made an article on how I use claude to get insane results like this link below:

Ernesto Lopez

217,230 次观看 • 2 个月前

We’re unveiling a new look for Artificial Analysis! We’ve come a long way since launching Artificial Analysis over 2 years ago. Today, we benchmark 400+ models, 50+ inference providers, and benchmark not only language models but also image, video, speech, music, hardware, and agents. Our mission to support the AI ecosystem with independent benchmarking remains the same, but our brand and website refresh is designed to better reflect how much we’ve grown and how much further we plan to go. A huge thank you to everyone who has been part of the Artificial Analysis community along the way: from developers choosing models and building agents, to labs, inference and hardware providers, and fellow independent researchers.

Artificial Analysis

18,208 次观看 • 6 个月前

ELON MUSK: Video games will be indistinguishable from reality "If you look at the evolution of video games, in my lifetime it's gone from very simple video games, like Pong, where you've got two rectangles in a square just batting it back and forth, to photorealistic, real-time games with millions of people playing simultaneously. That's happened just in the span of 50 years So if that trend continues, video games will be indistinguishable from reality We're also going to have very intelligent characters, like non-player characters, in these video games. Think of how sophisticated the conversations are you can have with an AI today, and that's only going to get more sophisticated. You'll be able to have conversations that are more complex and sophisticated than almost any human conversation So then the future, if civilization continues, will be millions, maybe billions, of photorealistic, indistinguishable-from-reality video games. With characters in those video games that are very deep, and where the dialogue is not pre-programmed. That's for sure what's going to happen in this level of the simulation, if you could call it So then, what are the odds that we are in base reality and that this has not happened before?"

ELON MUSK: Video games will be indistinguishable from reality "If you look at the evolution of video games, in my lifetime it's gone from very simple video games, like Pong, where you've got two rectangles in a square just batting it back and forth, to photorealistic, real-time games with millions of people playing simultaneously. That's happened just in the span of 50 years So if that trend continues, video games will be indistinguishable from reality We're also going to have very intelligent characters, like non-player characters, in these video games. Think of how sophisticated the conversations are you can have with an AI today, and that's only going to get more sophisticated. You'll be able to have conversations that are more complex and sophisticated than almost any human conversation So then the future, if civilization continues, will be millions, maybe billions, of photorealistic, indistinguishable-from-reality video games. With characters in those video games that are very deep, and where the dialogue is not pre-programmed. That's for sure what's going to happen in this level of the simulation, if you could call it So then, what are the odds that we are in base reality and that this has not happened before?"

X Freeze

30,787 次观看 • 10 个月前

Thrilled to be at The Pear Tree in Edinburgh today. Pubs and your local sports clubs should get late-night licences to air Scotland games during the World Cup. That’s how we can come together to celebrate and show Scotland we’re behind them!

Thrilled to be at The Pear Tree in Edinburgh today. Pubs and your local sports clubs should get late-night licences to air Scotland games during the World Cup. That’s how we can come together to celebrate and show Scotland we’re behind them!

Alex Cole-Hamilton🔶🇺🇦

314,797 次观看 • 10 个月前

AI only has pre-schooler level capabilities for visual tasks. "The frontier models—the best of them—still reason around the age of a preschooler, and any elementary school kid in that benchmark was able to beat all the frontier models on these visual tasks." "These are tasks that are not just object recognition. It's about spatial reasoning... tasks like navigating through the maze…” — Andrew M. Dai, CEO of Elorian

AI only has pre-schooler level capabilities for visual tasks. "The frontier models—the best of them—still reason around the age of a preschooler, and any elementary school kid in that benchmark was able to beat all the frontier models on these visual tasks." "These are tasks that are not just object recognition. It's about spatial reasoning... tasks like navigating through the maze…” — Andrew M. Dai, CEO of Elorian

The Information

26,229 次观看 • 3 个月前

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Earlier this week at GTC, we announced our partnership with Nvidia. We will work with Nvidia to build strong, American open-source models that are at the frontier of scientific reasoning. These models will be essential for the US to compete with China on science in the coming decades. Jensen is committing to spend tens of billions of dollars developing open-source models, and we are excited to be a partner with them in figuring out how to benchmark, train and use those agents to accelerate scientific research. We have already open-sourced some of the work we have done with them, and are looking forward to open-sourcing more. There are few things today that are more important. See our blog post below, and watch the video to learn more, narrated by the man himself.

Sam Rodriques

24,421 次观看 • 6 个月前

Excited to show some surprising inventions on generative multiplayer games we made at Google with Stanford. We call the work MultiGen. I've always been inspired by early studios like id Software with Doom or Blizzard with Warcraft bringing networked video games to the next level. We are at the point in history where we can make strides like them, but for generative games. It's a strange feeling to be in the age of generative video games while still discovering how exactly to train the models and design the tools that make them useful. All of the tools that have been invented for classic game engines need to be redesigned for generative games. For example level and world design is not entirely possible with existing technology. We introduce editable memory to diffusion game engines that allow for design of new levels via a minimap. But we can easily imagine how this can be expanded with different creation tools. The end goal of this research direction is to allow game designers to be able to guide the generation process of their world, at the granularity that they prefer. Editable memory also allows us to add multiplayer to Generative Doom. We were amazed when we saw GameNGen some years ago, and now you can play it live with friends in real-time, on your couch or even online. Shared representations like our editable memory seem like the future for this type of experience. Models are, in some cases, expensive and approximate encoders but great interpolators and extrapolators. Leveraging their strengths lets you have completely new experiences that can be realized now and not in the distant future. This work was started at my previous team and continued in collaboration with Stanford. Congratulations to all for the discoveries.

Excited to show some surprising inventions on generative multiplayer games we made at Google with Stanford. We call the work MultiGen. I've always been inspired by early studios like id Software with Doom or Blizzard with Warcraft bringing networked video games to the next level. We are at the point in history where we can make strides like them, but for generative games. It's a strange feeling to be in the age of generative video games while still discovering how exactly to train the models and design the tools that make them useful. All of the tools that have been invented for classic game engines need to be redesigned for generative games. For example level and world design is not entirely possible with existing technology. We introduce editable memory to diffusion game engines that allow for design of new levels via a minimap. But we can easily imagine how this can be expanded with different creation tools. The end goal of this research direction is to allow game designers to be able to guide the generation process of their world, at the granularity that they prefer. Editable memory also allows us to add multiplayer to Generative Doom. We were amazed when we saw GameNGen some years ago, and now you can play it live with friends in real-time, on your couch or even online. Shared representations like our editable memory seem like the future for this type of experience. Models are, in some cases, expensive and approximate encoders but great interpolators and extrapolators. Leveraging their strengths lets you have completely new experiences that can be realized now and not in the distant future. This work was started at my previous team and continued in collaboration with Stanford. Congratulations to all for the discoveries.

Nataniel Ruiz

104,972 次观看 • 7 个月前

Elon Musk: My hobby is video games and it's on the list of things that turn women off the most😂😂 “My hobbies, love sort of spending time with friends and family, and video games. And then that's probably not like the sexiest thing to say, you know? In fact, I was looking at some list of things that turn women off the most, and one is if your hobby is video games.”

Elon Musk: My hobby is video games and it's on the list of things that turn women off the most😂😂 “My hobbies, love sort of spending time with friends and family, and video games. And then that's probably not like the sexiest thing to say, you know? In fact, I was looking at some list of things that turn women off the most, and one is if your hobby is video games.”

Eva Fo𝕏 🦊 Claudius Nero's Legion

143,698 次观看 • 9 个月前

Agents are getting complex to manage: models, skills, automations, permissions, cloud environments, orchestration patterns... So, we built the Terraform for agents: one repository that configures all of your agents as code. The Warp Factories configuration spec defines: - Agents and orchestration: how work gets routed and which models agents use - Automations: the events and schedules that kick off work - Access and environments: repositories, secrets, MCP servers, and runners - Measurement: scorers and benchmarks for understanding and improving performance Because it’s all code, both engineers and agents can propose changes to the factory itself. That makes it possible to test new configurations, benchmark them, and even have your factory propose improvements as PRs.

Agents are getting complex to manage: models, skills, automations, permissions, cloud environments, orchestration patterns... So, we built the Terraform for agents: one repository that configures all of your agents as code. The Warp Factories configuration spec defines: - Agents and orchestration: how work gets routed and which models agents use - Automations: the events and schedules that kick off work - Access and environments: repositories, secrets, MCP servers, and runners - Measurement: scorers and benchmarks for understanding and improving performance Because it’s all code, both engineers and agents can propose changes to the factory itself. That makes it possible to test new configurations, benchmark them, and even have your factory propose improvements as PRs.

Warp

248,660 次观看 • 10 天前