Loading video...

Video Failed to Load

Go Home

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 views • 1 month ago •via X (Twitter)

GamingEducationScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

As a motion graphics designer, your main objective is with whatever still image design you create, you should always be cognisant of how to make elements of your designs move! DUST Visual Arts the best in the digital marketing and visual arts game!
0:29

As a motion graphics designer, your main objective is with whatever still image design you create, you should always be cognisant of how to make elements of your designs move! DUST Visual Arts the best in the digital marketing and visual arts game!

PAIN

16,446 views • 2 years ago

Inspiration is everywhere. Creation should be just as easy. Drop in a reference, a video, or a scene you like, and Hedra Agent understands the character, the mood, and the visual style. Generate variations. Change the aesthetic. Turn a single image into a fully animated video. No complex prompts. Just describe what you want to create. Agent builds the visuals. The era of vibe creation is here. Try it now:
0:42

Inspiration is everywhere. Creation should be just as easy. Drop in a reference, a video, or a scene you like, and Hedra Agent understands the character, the mood, and the visual style. Generate variations. Change the aesthetic. Turn a single image into a fully animated video. No complex prompts. Just describe what you want to create. Agent builds the visuals. The era of vibe creation is here. Try it now:

Hedra

12,112 views • 3 months ago

AI is coming for taste and judgment Claude Code's Boris Cherny: "We have this tendency to think....here's a thing the agent can't do yet, this must be a thing it can never do. But the rate of progress is so quick that something like taste, the agent will be able to do quite soon" co-lead cat says you can see the jump in the models directly. The front-end apps Claude builds have gotten visibly nicer between Sonnet 3.5 and Opus 4.7, and you no longer need to handhold the agent.
0:55

AI is coming for taste and judgment Claude Code's Boris Cherny: "We have this tendency to think....here's a thing the agent can't do yet, this must be a thing it can never do. But the rate of progress is so quick that something like taste, the agent will be able to do quite soon" co-lead cat says you can see the jump in the models directly. The front-end apps Claude builds have gotten visibly nicer between Sonnet 3.5 and Opus 4.7, and you no longer need to handhold the agent.

Deirdre Bosa

21,115 views • 2 months ago

As Simple As That, Simple should never be confused with Easy. Because a lot of Players and Teams want to win, But very few want to prepare at the level it takes to be a Champion. Both Donegal and Armagh prepared in the way needed To Be Champions and we got a brilliant game, where only a penalty shootout could separate them.
0:23

As Simple As That, Simple should never be confused with Easy. Because a lot of Players and Teams want to win, But very few want to prepare at the level it takes to be a Champion. Both Donegal and Armagh prepared in the way needed To Be Champions and we got a brilliant game, where only a penalty shootout could separate them.

Ray Boyne

87,836 views • 2 years ago

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 views • 21 days ago

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.
0:37

GPT Image 2 + Codex: or how to make Codex not suck at UI. Step 1: Generate a UI image (native in Codex) Step 2: Get Codex to implement the UI based on it Step 3: Get Codex to iterate until it aligns with the image as much as possible Codex is bad at initial UI, but very good at implementing a reference design, so this is your way out - iterate with the image model first and then Codex will do a good job.

Peter Gostev

66,675 views • 2 months ago

Claude Fable 5 has been out for a day. I already one-shotted a voxel spaceship racer with it. I fed it a reference image of a track layout and told it to build a full game around that shape. Missiles, boost zones, 3 AI opponents, 3 laps, a HUD with speed and health. Fable 5 read the image, traced the track geometry, and built the entire thing. One prompt. This is what Mythos-class models do to the build cycle.
1:21

Claude Fable 5 has been out for a day. I already one-shotted a voxel spaceship racer with it. I fed it a reference image of a track layout and told it to build a full game around that shape. Missiles, boost zones, 3 AI opponents, 3 laps, a HUD with speed and health. Fable 5 read the image, traced the track geometry, and built the entire thing. One prompt. This is what Mythos-class models do to the build cycle.

God of Prompt

27,386 views • 28 days ago

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

104,492 views • 4 months ago

Aigents! 🤖 Have you ever imagined a world where technology could not only see, but also understand and advise you? 🤔 Imagine playing a game of chess, strategizing each move, and then, with the help of AigentX, discovering the next winning move. This is not just a possibility anymore, it's reality! 🚀 Introducing AigentX's Image Processing feature! This isn't just about analysing and processing images; it's about bringing them to life with insights and guidance that we once thought could never become a reality and merely a figment of our imagination! 🤯 Picture this: You're deeply engrossed in a chess match, contemplating your next move. You snap a picture of the board and send it to AigentX. In moments, you're not just seeing the pieces – you're understanding the potential for your next move! 📸 AigentX doesn't just view the image; it interprets it, offering you useful insights and it isn't just chess! This feature can be taken straight to the real world with features like chart analysis and more! 📈 But that's just the beginning. AigentX is ready to transform how you interact with any image. From art analysis to real-world problem-solving, the possibilities are endless 📈 Check out our latest video below to see AigentX in action. This is more than an update; it's a leap into a future where your interaction with images is redefined 📻 Test out AigentX for yourself and witness how it's changing the game, one image at a time. Stay tuned for more – the journey with AigentX has just begun!
1:21

Aigents! 🤖 Have you ever imagined a world where technology could not only see, but also understand and advise you? 🤔 Imagine playing a game of chess, strategizing each move, and then, with the help of AigentX, discovering the next winning move. This is not just a possibility anymore, it's reality! 🚀 Introducing AigentX's Image Processing feature! This isn't just about analysing and processing images; it's about bringing them to life with insights and guidance that we once thought could never become a reality and merely a figment of our imagination! 🤯 Picture this: You're deeply engrossed in a chess match, contemplating your next move. You snap a picture of the board and send it to AigentX. In moments, you're not just seeing the pieces – you're understanding the potential for your next move! 📸 AigentX doesn't just view the image; it interprets it, offering you useful insights and it isn't just chess! This feature can be taken straight to the real world with features like chart analysis and more! 📈 But that's just the beginning. AigentX is ready to transform how you interact with any image. From art analysis to real-world problem-solving, the possibilities are endless 📈 Check out our latest video below to see AigentX in action. This is more than an update; it's a leap into a future where your interaction with images is redefined 📻 Test out AigentX for yourself and witness how it's changing the game, one image at a time. Stay tuned for more – the journey with AigentX has just begun!

AGIX | $AGX

22,621 views • 2 years ago

Claude Design is incredible It allows ANYONE to design BEAUTIFUL apps and websites But here's the thing, when combined with ChatGPT's new image model it's 10x better In this video I cover how to use Claude Design and ChatGPT Image 2 together to design BEAUTIFUL apps:
23:47

Claude Design is incredible It allows ANYONE to design BEAUTIFUL apps and websites But here's the thing, when combined with ChatGPT's new image model it's 10x better In this video I cover how to use Claude Design and ChatGPT Image 2 together to design BEAUTIFUL apps:

Alex Finn

206,636 views • 2 months ago

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

55,377 views • 1 month ago

Stairs and ladders are fine, but the proper adventurer should be able to overcome any obstacle! Game has a climbing mechanic just like in Dragon's Dogma or Thief. Hopefully this will allow me to add a lot of verticality to the level design! #indiedev #indiegame
0:24

Stairs and ladders are fine, but the proper adventurer should be able to overcome any obstacle! Game has a climbing mechanic just like in Dragon's Dogma or Thief. Hopefully this will allow me to add a lot of verticality to the level design! #indiedev #indiegame

Tinto

39,542 views • 7 months ago

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 views • 1 year ago

This is the future of web design. Gamma 3.0 has just been released, and I used it to create a complete website from a URL in seconds. No prompts. No code. No input. Their new AI agent will design, review, fix, and iterate on your content. The best part: you can watch it in real-time as it builds your website! This is pretty amazing! There are many AI design agents out there, but this one is one of the most hands-off tools I've seen. This is incredible.
1:11

This is the future of web design. Gamma 3.0 has just been released, and I used it to create a complete website from a URL in seconds. No prompts. No code. No input. Their new AI agent will design, review, fix, and iterate on your content. The best part: you can watch it in real-time as it builds your website! This is pretty amazing! There are many AI design agents out there, but this one is one of the most hands-off tools I've seen. This is incredible.

Santiago

39,140 views • 9 months ago

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

58,571 views • 9 months ago

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

24,618 views • 3 months ago

reKILL is not just the game itself. I also built a set of tools to be able to create the game and iterate faster. And one of the biggest is MapEditor. And it made it possible to design such big map.
1:09

reKILL is not just the game itself. I also built a set of tools to be able to create the game and iterate faster. And one of the biggest is MapEditor. And it made it possible to design such big map.

TheoTheDev

10,983 views • 5 months ago

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 views • 7 months ago

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 views • 4 months ago