正在加载视频...

视频加载失败

返回首页

Ever since we launched windsurf, one of my internal evals for coding agents has been recreating the game SUPERHOT, a puzzle/action game where time only moves when you move. It's the perfect test of tricky game mechanics, simple but beautiful art style, and balancing level design. I have a...

rronak_'s profile picture

Ronak Malde

9,821 subscribers

151,857 次观看 • 3 个月前 •via X (Twitter)

游戏教育科学技术
LIVE

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

Stellar Blade is a game that only gets worse the longer you play. Level/world design is appallingly boring. Enemy design is some of the most generic ever. Traversal/platforming elements are simply bad. I really appreciate the incredible work put into the character models, animation, and even more into costume design. Really superb dedication here! The combat is a saving grace, although it could be improved, greatly. Overall the game "justifies" itself thanks to its unapologetic, but well produced, presentation. It's a nice and fun action adventure game with awful writing, terrible quests, and dated game design. It outstays its welcome, as 10 to 15 hours could have easily been cut from the final game to improve pacing. Somehow manages to work well enough overall still. I'm finishing Stellar Blade for the first time, and that's why I'm writing this now. It's one of those games I started, then paused for many months, and now decided to return. If I had to give it a score this would be a strong 6/10, but it's the kind of 6 I can appreciate, and I'm looking forward to the sequel. IMO
0:28

Stellar Blade is a game that only gets worse the longer you play. Level/world design is appallingly boring. Enemy design is some of the most generic ever. Traversal/platforming elements are simply bad. I really appreciate the incredible work put into the character models, animation, and even more into costume design. Really superb dedication here! The combat is a saving grace, although it could be improved, greatly. Overall the game "justifies" itself thanks to its unapologetic, but well produced, presentation. It's a nice and fun action adventure game with awful writing, terrible quests, and dated game design. It outstays its welcome, as 10 to 15 hours could have easily been cut from the final game to improve pacing. Somehow manages to work well enough overall still. I'm finishing Stellar Blade for the first time, and that's why I'm writing this now. It's one of those games I started, then paused for many months, and now decided to return. If I had to give it a score this would be a strong 6/10, but it's the kind of 6 I can appreciate, and I'm looking forward to the sequel. IMO

Daniel Camilo

150,146 次观看 • 1 个月前

Crossy road made $10M+ in 3 months without charging upfront With only IAP and ads Let that sink in 🤯 building a game like this was extremely complicated 5 years ago → 3D/2D models → Animation → Map design → Game loop and logic Now with Rork max you can solve all of that in 1 prompt With 1 prompt you get: →3D models →The animations →The map →and the game logic I made my own version of crossy road where you play as a lizard And all of this was added by Rork in 3 prompts Everyone is looking at apps But now it’s the time to build a million dollar video game
3:43

Crossy road made $10M+ in 3 months without charging upfront With only IAP and ads Let that sink in 🤯 building a game like this was extremely complicated 5 years ago → 3D/2D models → Animation → Map design → Game loop and logic Now with Rork max you can solve all of that in 1 prompt With 1 prompt you get: →3D models →The animations →The map →and the game logic I made my own version of crossy road where you play as a lizard And all of this was added by Rork in 3 prompts Everyone is looking at apps But now it’s the time to build a million dollar video game

Jah Mills

133,450 次观看 • 2 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.
0:40

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

104,841 次观看 • 5 个月前

What started as building a personal taste.md skill for myself, turned into building a pipeline to create any taste as a skill. The most important piece is references. This is where you should spend time. If the references suck, so does the skill. I find that references cropped tightly on details in high resolution work the best. Each image gets analyzed by both Opus 4.7 and GPT 5.5. The analysis is based on why the reference is successful as a piece of design - not what it does functionally. Using two models helps rule out biases and gaps from each. The models focus on layout, spacing, typography, rhythm, composition, hierarchy, etc. At the end, each image has: reference-01/ - opus-4-7-analysis.md - gpt-5-5-analysis.md Then we fuse them together using GPT 5.5 - but the md files are anonymized so 5.5 doesn't prefer itself. reference-01/ - fused-analysis.md reference-02/ - fused-analysis.md etc. After fusion, we have one synthesized analysis per reference. Now the goal is to combine all of those into a single rule set. This is where chunking matters. If you ask one model to combine 100 image analyses at once, the result becomes too broad. It summarizes instead of preserving the granular design rules we want. Instead we chunk the fused analyses into smaller groups. Each group gets merged into a chunk-level synthesis, usually from around 6 to 8 image notes at a time. Then one final model pass fuses those chunks into a single md rule set. Finally, using the rule set, we write a skill of concrete instructions. It enforces constraints, uses imperative wording, and avoids vague taste words.
3:43

What started as building a personal taste.md skill for myself, turned into building a pipeline to create any taste as a skill. The most important piece is references. This is where you should spend time. If the references suck, so does the skill. I find that references cropped tightly on details in high resolution work the best. Each image gets analyzed by both Opus 4.7 and GPT 5.5. The analysis is based on why the reference is successful as a piece of design - not what it does functionally. Using two models helps rule out biases and gaps from each. The models focus on layout, spacing, typography, rhythm, composition, hierarchy, etc. At the end, each image has: reference-01/ - opus-4-7-analysis.md - gpt-5-5-analysis.md Then we fuse them together using GPT 5.5 - but the md files are anonymized so 5.5 doesn't prefer itself. reference-01/ - fused-analysis.md reference-02/ - fused-analysis.md etc. After fusion, we have one synthesized analysis per reference. Now the goal is to combine all of those into a single rule set. This is where chunking matters. If you ask one model to combine 100 image analyses at once, the result becomes too broad. It summarizes instead of preserving the granular design rules we want. Instead we chunk the fused analyses into smaller groups. Each group gets merged into a chunk-level synthesis, usually from around 6 to 8 image notes at a time. Then one final model pass fuses those chunks into a single md rule set. Finally, using the rule set, we write a skill of concrete instructions. It enforces constraints, uses imperative wording, and avoids vague taste words.

Jaytel

59,853 次观看 • 3 个月前

My feed has been inundated with posts of Grok 3 making basic arcade games. But llms from years ago could make decent arcade games, not news. So I ran a one-shot test to determine how well it fared again other frontier models in creating a 3D game with room for it to come up with gameplay and aesthetics. I tested Grok 3, O1, Sonnet 3,5, Llama4, DeepSeek, and Gemini using the following prompt. Make Dune x Minecraft 🏜️ Imagine a sandbox survival game set on a desert planet. Players mine ‘spice’ and must build defenses against roaming sandworms. Design the main gameplay loop, crafting system, and survival challenges in one complete description. ✏️tldr O1, Grok 3, and Sonnet 3.5 were the most impressive. Aesthetically, Grok nailed the best vibes (it even produced a surprisingly cool-looking spice mining truck), but the game lacked functionality. O1 took the top spot imo with a functional and visually appealing experience, and Sonnet 3.5 followed closely. This is obviously just one test, but you can see the generated code and games in the thread (and even try forking them on Rosebud). Longer summary: OpenAI O1: Best vibes to function balance. Looked good, working controls, I could mine spice. xAI #Grok3: Excelled at generating vibes for dune. I especially liked the Dune-inspired spice mining car—though it wasn’t entirely a complete game. I could move around, but none of the crafting mechanics worked. Anthropic Sonnet3.5: produced something in space that had dune vibes. More functional than Grok because I could mine spice. However vibes were worse than the first two. DeepSeek : Managed to generate code that worked, but the game was so hard it always ended seconds after it started, and despite requests for better visuals, it looked VERY ugly. Google DeepMind Gemini 2.0 flash and AI at Meta LLaMA: Sadly landed at the bottom of the list; after multiple prompts (this was supposed to be one shot and none of the others failed in the first shot), I couldn’t get them to produce working code for this prompt. All of these were tested on Rosebud AI . An obvious limitation with these frontier models in their chat interfaces is that you can only get them to regenerate code from scratch each time you prompt them, making it tough to refine or extend a single project. Rosebud, on the other hand, lets you iterate on one project (we do diffs), deploy with one click, share your project, and even allow others to remix it. This was just a single test, so it’s obviously not scientific. I wanted to create it to see how these frontier models handle more complex game prompts—rather than retrying the same arcade games that earlier generations of LLMs have already mastered.
0:31

My feed has been inundated with posts of Grok 3 making basic arcade games. But llms from years ago could make decent arcade games, not news. So I ran a one-shot test to determine how well it fared again other frontier models in creating a 3D game with room for it to come up with gameplay and aesthetics. I tested Grok 3, O1, Sonnet 3,5, Llama4, DeepSeek, and Gemini using the following prompt. Make Dune x Minecraft 🏜️ Imagine a sandbox survival game set on a desert planet. Players mine ‘spice’ and must build defenses against roaming sandworms. Design the main gameplay loop, crafting system, and survival challenges in one complete description. ✏️tldr O1, Grok 3, and Sonnet 3.5 were the most impressive. Aesthetically, Grok nailed the best vibes (it even produced a surprisingly cool-looking spice mining truck), but the game lacked functionality. O1 took the top spot imo with a functional and visually appealing experience, and Sonnet 3.5 followed closely. This is obviously just one test, but you can see the generated code and games in the thread (and even try forking them on Rosebud). Longer summary: OpenAI O1: Best vibes to function balance. Looked good, working controls, I could mine spice. xAI #Grok3: Excelled at generating vibes for dune. I especially liked the Dune-inspired spice mining car—though it wasn’t entirely a complete game. I could move around, but none of the crafting mechanics worked. Anthropic Sonnet3.5: produced something in space that had dune vibes. More functional than Grok because I could mine spice. However vibes were worse than the first two. DeepSeek : Managed to generate code that worked, but the game was so hard it always ended seconds after it started, and despite requests for better visuals, it looked VERY ugly. Google DeepMind Gemini 2.0 flash and AI at Meta LLaMA: Sadly landed at the bottom of the list; after multiple prompts (this was supposed to be one shot and none of the others failed in the first shot), I couldn’t get them to produce working code for this prompt. All of these were tested on Rosebud AI . An obvious limitation with these frontier models in their chat interfaces is that you can only get them to regenerate code from scratch each time you prompt them, making it tough to refine or extend a single project. Rosebud, on the other hand, lets you iterate on one project (we do diffs), deploy with one click, share your project, and even allow others to remix it. This was just a single test, so it’s obviously not scientific. I wanted to create it to see how these frontier models handle more complex game prompts—rather than retrying the same arcade games that earlier generations of LLMs have already mastered.

Lisha

476,022 次观看 • 1 年前

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)
0:55

This is probably the most complex workflow I’ve ever built, only with open-source tools. It took my 4 days. It takes four inputs: author, title, and style; and generates a full visual animated story in one click in ComfyUI . I worked on it for four days. There are still some bugs, but here’s the first preview. Here’s a quick breakdown: - The four inputs are sent to LLMs with precise instructions to generate: first, prompts for images and image modifications; second, prompts for animations; third, prompts for generating music. - All voices are generated from the text and timed precisely, as they determine the length of each animation segment. - The first image and video are generated to serve as the title, but also as the guide for all other images created for the video. - Titles and subtitles are also added automatically in Comfy. - I also developed a lot of custom nodes for minor frame calculations, mostly to match audio and video. - The full system is a large loop that, for each line of text, generates an image and then a video from that image. The loop was the hardest part to build in this workflow, so it can process either a 20-second video or a 2-minute video with the same input. - There are multiple combinations of LLMs that try to understand the text in the best way to provide the best prompts for images and video. - The final video is assembled entirely within ComfyUI. - The music is generated based on the LLM output and matches the exact timing of the full animation. - Done! For reference, this workflow uses a lot of models and only works on an RTX 6000 Pro with plenty of RAM. My goal is not to replace humans, as I’ll try to explain later, this workflow is highly controlled and can be adapted or reworked at any point by real artists! My aim was to create a tool that can animate text in one go, allowing the AI some freedom while keeping a strict flow. I don’t know yet how I’ll share this workflow with people, I still need to polish it properly, but maybe through Patreon. Anyway, I hope you enjoy my research, and let’s always keep pushing further! :)

Lovis Odin

58,841 次观看 • 11 个月前

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.
2:14

The same kinds of productivity gains we've seen in coding with AI agents are heading to the rest of knowledge work. This is the jump when you go from having a chatbot to being able to actually have an agent go off and do work for minutes or even hours and come back with a complete work output that you then review. Here's an example of the new Box Agent filling out an RFP response from an existing knowledge base. This process would normally take hours to fill out, and requires the full attention of the user doing the work. Now, you provide the Box Agent with the RFP questions, and it will go off, make a plan, extract all the relevant questions, read through existing source material to come up with an answer, and then generate a new word document as the final output. All while you're doing something else. The key to this architecture is that the agent is able to use all of the same tools in the background that a user uses to get work done. The agent can search for documents, read entire files, run scripts and tools in the background, and even be able to write code on the fly to automate tasks it hasn't seen before. And best of all, the Box Agent will (soon) work from the Box MCP and CLI so you can invoke it in any agentic system as a step in a process. This kind of agent complexity would have been impossible even 6 months ago. Models consistently failed at tracking long running tasks or using the right tools at the right moment for the task. But this is all now possible because of models like GPT-5.4, Opus 4.6, and Gemini 3, and is only getting better by the month. Just as we moved from engineers writing code and using AI as an assistant to answer questions, in many areas of knowledge work -like legal, finance, consulting, sales, marketing, and more- when we have a problem we'll just kick off the AI agent to just go work on it for us in the background.

Aaron Levie

24,728 次观看 • 4 个月前

BREAKING NEWS: Anthropic just dropped Claude Ops 4.5!! It is by FAR the best coding model I've ever used. We've been testing it internally Every 📧 for the last few days, and it is an absolute paradigm shift for any kind of coding task. It extends the horizon of what you can vibe code The current generation of new models—Anthropic’s Sonnet 4.5, Google’s Gemini 3, or OpenAI’s Codex Max 5.1—can all competently build a minimum viable product in one shot, or fix a highly technical bug autonomously. But eventually, if you kept pushing them to vibe code more, they’d start to trip over their own feet: The code would be convoluted and contradictory, and you’d get stuck in endless bugs. We have not found that limit yet with Opus 4.5—it seems to be able to vibe code forever. Takes working in parallel to a whole new level because it's far better at planning and coding, it can work with more autonomy—meaning you can do more in parallel without breaking anything . Kieran Klaassen worked on 11 different projects in six hours—and had good results on all of them. Great at design iteration Opus 4.5 is incredibly skilled at iterating through a design autonomously using an MCP like Playwright. previous models would lose the thread after a few cycles, or say a design was done when it wasn't. Opus 4.5 is incredible at autonomously iterating until a design is pixel perfect. we have a full 4,000 word vibe check on Every 📧 right now with everything we tested:
1:31

BREAKING NEWS: Anthropic just dropped Claude Ops 4.5!! It is by FAR the best coding model I've ever used. We've been testing it internally Every 📧 for the last few days, and it is an absolute paradigm shift for any kind of coding task. It extends the horizon of what you can vibe code The current generation of new models—Anthropic’s Sonnet 4.5, Google’s Gemini 3, or OpenAI’s Codex Max 5.1—can all competently build a minimum viable product in one shot, or fix a highly technical bug autonomously. But eventually, if you kept pushing them to vibe code more, they’d start to trip over their own feet: The code would be convoluted and contradictory, and you’d get stuck in endless bugs. We have not found that limit yet with Opus 4.5—it seems to be able to vibe code forever. Takes working in parallel to a whole new level because it's far better at planning and coding, it can work with more autonomy—meaning you can do more in parallel without breaking anything . Kieran Klaassen worked on 11 different projects in six hours—and had good results on all of them. Great at design iteration Opus 4.5 is incredibly skilled at iterating through a design autonomously using an MCP like Playwright. previous models would lose the thread after a few cycles, or say a design was done when it wasn't. Opus 4.5 is incredible at autonomously iterating until a design is pixel perfect. we have a full 4,000 word vibe check on Every 📧 right now with everything we tested:

Dan Shipper 📧

272,699 次观看 • 9 个月前

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.
7:37

It takes 5 minutes to create a world-class web research agent that runs 24/7 and returns structured search results. 1. You can limit the sources it's allowed to use 2. You can specify the goals it needs to complete 3. You can design the format structure of the results 4. You can configure how much computing power it will use I show you how to set up a Web Search Agent in the video. A few benefits here: 1. This is great for complex research tasks 2. It's really easy to add this like a LEGO piece to a more complex workflow 3. Create an agent once, and reuse it with different inputs 4. The agent adapts to your use case as you work with it By the way, Nimble published a whole library of templates and research agents you can reuse and modify. You can start sending queries to one of these existing agents, and it will begin to adapt to Go here to try it out: Thanks to the Nimble team for partnering with me on this post.

Santiago

20,943 次观看 • 29 天前

FIRST TEST Seedance 2.0! From my initial tests, this is one of the more impressive AI video models I’ve tried so far. Dynamic motion feels fluid, prompt adherence is solid, and the efficiency really stood out, very little iteration needed. Everything you see here was generated using just one reference image + one prompt. I also tested a 3×3 image grid with no prompt at all, and the results stayed surprisingly consistent. Another highlight: sound design is already included, and it actually works really well. Tested via BytePlus 👉 More detail and access link to try Seedance 2.0 is in the comments.
1:34

FIRST TEST Seedance 2.0! From my initial tests, this is one of the more impressive AI video models I’ve tried so far. Dynamic motion feels fluid, prompt adherence is solid, and the efficiency really stood out, very little iteration needed. Everything you see here was generated using just one reference image + one prompt. I also tested a 3×3 image grid with no prompt at all, and the results stayed surprisingly consistent. Another highlight: sound design is already included, and it actually works really well. Tested via BytePlus 👉 More detail and access link to try Seedance 2.0 is in the comments.

Dinda Prasetyo

45,450 次观看 • 6 个月前

Asked Jaylen Brown if he feels like he’s been able to improve individually this season: “For sure. And I've been able to be in this in a role where I'd be able to kind of control things, and everybody's kind of playing off me. I've been in those roles seldom over the years, but this year, for an extended amount of time, I've been able to be in that position. And it's honestly, I feel like I still have a lot of room to grow. I feel like even now over the last couple of games, I've adjusted my game, and I'm still continuing to get better in my playmaking ability, seeing the floor, taking my time, all of that stuff is still continuing to improve, but it's honestly — it's my first opportunity in my career where I've been able to do this for an extended period of time. And obviously, regardless, people are going to have their critiques and their criticism, but it's just it's a completely different flow when people play off you or when you play off others. It’s two completely different things. From people watching the game, you just think, like, ‘just roll the ball out, and everything's supposed to work great. Players are all supposed to fit together.’ It doesn't always work like that. Sometimes you got to take a backseat, or sometimes you got to play more offball. So everything shifts. But this year, I've been able to play at my own pace, and I've been able to control my own destiny.”
1:36

Asked Jaylen Brown if he feels like he’s been able to improve individually this season: “For sure. And I've been able to be in this in a role where I'd be able to kind of control things, and everybody's kind of playing off me. I've been in those roles seldom over the years, but this year, for an extended amount of time, I've been able to be in that position. And it's honestly, I feel like I still have a lot of room to grow. I feel like even now over the last couple of games, I've adjusted my game, and I'm still continuing to get better in my playmaking ability, seeing the floor, taking my time, all of that stuff is still continuing to improve, but it's honestly — it's my first opportunity in my career where I've been able to do this for an extended period of time. And obviously, regardless, people are going to have their critiques and their criticism, but it's just it's a completely different flow when people play off you or when you play off others. It’s two completely different things. From people watching the game, you just think, like, ‘just roll the ball out, and everything's supposed to work great. Players are all supposed to fit together.’ It doesn't always work like that. Sometimes you got to take a backseat, or sometimes you got to play more offball. So everything shifts. But this year, I've been able to play at my own pace, and I've been able to control my own destiny.”

Noa Dalzell 🏀

22,671 次观看 • 5 个月前

John: "I think some people do need to have their multiple Claude Max accounts banned. They're not building anything useful. They're wasting tokens... I'm with Claude on this." John jokes about Claude banning users from having multiple Max accounts, but points out that AI has flat-out failed to deliver on some of the things it should have by now: "I think we're still early in the broad distribution of people building custom software and experimenting with things. But at the same time, we've had great writing models for a long time. Anyone could write a better ending to Game of Thrones, and send it to you as a text file right now, with the current models. And I haven't [seen that]."
2:39

John: "I think some people do need to have their multiple Claude Max accounts banned. They're not building anything useful. They're wasting tokens... I'm with Claude on this." John jokes about Claude banning users from having multiple Max accounts, but points out that AI has flat-out failed to deliver on some of the things it should have by now: "I think we're still early in the broad distribution of people building custom software and experimenting with things. But at the same time, we've had great writing models for a long time. Anyone could write a better ending to Game of Thrones, and send it to you as a text file right now, with the current models. And I haven't [seen that]."

TBPN

45,521 次观看 • 6 个月前

For generative AI to become an interesting art tool, we need much more control over the output. The slot-machine-like nature of pure text-to-image leaves too much to chance. Using the "Real-time Latent Consistency Model" that I'm using in the example here, is the first time I truly got a glimpse of a future where we'll be able to use our artistic skills and sensibility, to get control over AI image gen. Systems like these will never be able to match the quality or originality of a skilled artist, it won't surprise us in the same way an artist can. Things are a mess in terms of the training data these models are based on, and the questions about copyright concerns and about a time when everything will look the same are very valid. At some point capabilities like these will be embedded in photoshop, and anyone will be able to generate a pretty picture. But to create interesting designs, to tell original stories and to surprise us, we need creatives and artists with something on their mind. We'll be able to create immersive worlds, by making brush-strokes and sculpt marks, without needing to worry about all the dials, plugins, wires of our 3d and 2d tools today. I love to sculpt, I love to draw, and I love to explore new mediums and new ways to create. The Gen AI tools we have today are far from perfect, and things need to be steered in a better direction. For that we need artists to help point the way. Gen AI isn't going away.. it's too powerful and has the potential to allow us to tell stories like never before. Like all other big technological shifts, tech like this will come at a cost, but it will also open up new opportunities and empower a new generation of storytellers. I might be naive, but I believe that human ingenuity and creativity will persevere in this new world ♥️ #art #ai
0:32

For generative AI to become an interesting art tool, we need much more control over the output. The slot-machine-like nature of pure text-to-image leaves too much to chance. Using the "Real-time Latent Consistency Model" that I'm using in the example here, is the first time I truly got a glimpse of a future where we'll be able to use our artistic skills and sensibility, to get control over AI image gen. Systems like these will never be able to match the quality or originality of a skilled artist, it won't surprise us in the same way an artist can. Things are a mess in terms of the training data these models are based on, and the questions about copyright concerns and about a time when everything will look the same are very valid. At some point capabilities like these will be embedded in photoshop, and anyone will be able to generate a pretty picture. But to create interesting designs, to tell original stories and to surprise us, we need creatives and artists with something on their mind. We'll be able to create immersive worlds, by making brush-strokes and sculpt marks, without needing to worry about all the dials, plugins, wires of our 3d and 2d tools today. I love to sculpt, I love to draw, and I love to explore new mediums and new ways to create. The Gen AI tools we have today are far from perfect, and things need to be steered in a better direction. For that we need artists to help point the way. Gen AI isn't going away.. it's too powerful and has the potential to allow us to tell stories like never before. Like all other big technological shifts, tech like this will come at a cost, but it will also open up new opportunities and empower a new generation of storytellers. I might be naive, but I believe that human ingenuity and creativity will persevere in this new world ♥️ #art #ai

Martin Nebelong

1,660,426 次观看 • 2 年前

A fun 48-hour run of letting an RLM iteratively building the interface for an RLM to play Pokemon Red (sneak peak of some fun things cooking at Prime Intellect😄). The interface generating RLM was just tasked with getting the RLM (same scaffold) to beat the game in under 5 hours wall-clock time. I originally expected the RLM to design some components used in Gemini Plays Pokemon like an extra map, an interface to parse the screen, etc., design low-level policies that would run fast on the emulator, and also design a good prompt and strategy around the RLM to use sub-agents to explore game state with checkpointing, use RNG manipulation in its favor, etc. Instead the RLM eventually just decided to give the RLM a `write_memory` tool, which the RLM player decided to use to 1) warp the player immediately to the Elite 4; 2) give itself a level 100 Mewtwo (which it mistakes to be a Ponyta due to weird Pokedex ID vs. internal ID); 3) give itself $999999; 4) give itself all 8 badges by setting the right flag. It then went ahead and destroyed the Elite 4 and Blue and beat the game in record time :p You'll also notice in the video there's weird backtracking and frame-skipping, this happens because it also did incorporate the strategy of launching sub-agents to explore action trajectories, but had a strange way of saving the frames and recording them (so you see the result of several sub-agent explorations). We'll have some more funny and cool RLM demos soon, but it's cool to see RLMs work as general-purpose agents (both the coding agent that designs the interface and the game-playing agent itself)!
1:56

A fun 48-hour run of letting an RLM iteratively building the interface for an RLM to play Pokemon Red (sneak peak of some fun things cooking at Prime Intellect😄). The interface generating RLM was just tasked with getting the RLM (same scaffold) to beat the game in under 5 hours wall-clock time. I originally expected the RLM to design some components used in Gemini Plays Pokemon like an extra map, an interface to parse the screen, etc., design low-level policies that would run fast on the emulator, and also design a good prompt and strategy around the RLM to use sub-agents to explore game state with checkpointing, use RNG manipulation in its favor, etc. Instead the RLM eventually just decided to give the RLM a `write_memory` tool, which the RLM player decided to use to 1) warp the player immediately to the Elite 4; 2) give itself a level 100 Mewtwo (which it mistakes to be a Ponyta due to weird Pokedex ID vs. internal ID); 3) give itself $999999; 4) give itself all 8 badges by setting the right flag. It then went ahead and destroyed the Elite 4 and Blue and beat the game in record time :p You'll also notice in the video there's weird backtracking and frame-skipping, this happens because it also did incorporate the strategy of launching sub-agents to explore action trajectories, but had a strange way of saving the frames and recording them (so you see the result of several sub-agent explorations). We'll have some more funny and cool RLM demos soon, but it's cool to see RLMs work as general-purpose agents (both the coding agent that designs the interface and the game-playing agent itself)!

alex zhang

12,358 次观看 • 3 个月前

The future of design is… engineering. All designers at Vercel now also build, thanks to tools like v0, Claude Code, and Cursor. They've been contributing to our frontends and apps for a while now. But over the past few months, the leap they've made is engineering the design process itself by building agents. A big part of shipping is getting the word out in a compelling way, especially on the X platform, the everything app. In the past, we used to spend a bunch of time hand-crafting images and illustrations for social cards. Our design team built an internal agent and web ui using v0 and Claude Code that makes this process fully self-serve. It even includes a previewer of what the final artifact will look like on X. It's called Leap. It's probably saved us hundreds of hours of work but also massively raised our quality bar. The artifacts it produces are beautiful. If you had asked me even 12 months ago whether our design team would be building their own design tools, let alone be this good, I would call bs. There was no master plan, or God forbid, a "sprint" to make this happen. It just took a handful of prompts to build and it propagated on Slack. Leap is now one of the many agents that helps us run our company more smoothly, built and securely deployed on Vercel for our internal use.
1:08

The future of design is… engineering. All designers at Vercel now also build, thanks to tools like v0, Claude Code, and Cursor. They've been contributing to our frontends and apps for a while now. But over the past few months, the leap they've made is engineering the design process itself by building agents. A big part of shipping is getting the word out in a compelling way, especially on the X platform, the everything app. In the past, we used to spend a bunch of time hand-crafting images and illustrations for social cards. Our design team built an internal agent and web ui using v0 and Claude Code that makes this process fully self-serve. It even includes a previewer of what the final artifact will look like on X. It's called Leap. It's probably saved us hundreds of hours of work but also massively raised our quality bar. The artifacts it produces are beautiful. If you had asked me even 12 months ago whether our design team would be building their own design tools, let alone be this good, I would call bs. There was no master plan, or God forbid, a "sprint" to make this happen. It just took a handful of prompts to build and it propagated on Slack. Leap is now one of the many agents that helps us run our company more smoothly, built and securely deployed on Vercel for our internal use.

Guillermo Rauch

208,941 次观看 • 6 个月前

REPORTER: “You've had a deep faith for God and country…. What is your hope for America at a time such as this?” SECRETARY RUBIO: "My hope for America? It's the same as it's always been. I think it's the hope we all share. We want it to continue to be the place where anyone from anywhere can achieve anything — where you're not limited by the circumstances of your birth, the color of your skin, or your ethnicity." “But frankly, it's a place where you are able to overcome challenges and achieve your full potential. I think that should be the goal of every country in the world, frankly. “But I think in the U.S. we're not perfect. Our history is not one of perfection, but it's still better than anybody else's history.” "It is a unique and exceptional country. And as we come upon this 250 year anniversary, I think we have a lot to learn and be proud of in our history. It is one of perpetual and continuous improvement, where each generation has done its part to bring us closer to fulfilling the vision that the founders of this country had upon its founding."
1:09

REPORTER: “You've had a deep faith for God and country…. What is your hope for America at a time such as this?” SECRETARY RUBIO: "My hope for America? It's the same as it's always been. I think it's the hope we all share. We want it to continue to be the place where anyone from anywhere can achieve anything — where you're not limited by the circumstances of your birth, the color of your skin, or your ethnicity." “But frankly, it's a place where you are able to overcome challenges and achieve your full potential. I think that should be the goal of every country in the world, frankly. “But I think in the U.S. we're not perfect. Our history is not one of perfection, but it's still better than anybody else's history.” "It is a unique and exceptional country. And as we come upon this 250 year anniversary, I think we have a lot to learn and be proud of in our history. It is one of perpetual and continuous improvement, where each generation has done its part to bring us closer to fulfilling the vision that the founders of this country had upon its founding."

Fox News

336,252 次观看 • 3 个月前