Загрузка видео...

Не удалось загрузить видео

На главную

Astra (GPT-6) is here!!! I've had early access and tested it like crazy with things like games, code, writing, browser control, presentations and general knowledge work. This is the best model I've ever used. Period. (Incredible demos below in this thread ⬇️) Here's my take on Astra: > It's...

MatthewBerman's profile picture

Matthew Berman

134,984 subscribers

406,848 просмотров • 5 часов назад •via X (Twitter)

Наука и технологииОбразованиеИгры
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 🪨 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 🪨:
0:11

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 🪨 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 🪨:

Dan Shipper 📧

354,559 просмотров • 3 месяцев назад

AI video is waaaaay better than most people realize. I came with this stupid idea for a terrible PS1 game with hideous textures and a jumping catfish... 30 minutes later, I had this. It's almost exactly what I had in my head. Between Nano Banana, GPT Image 2 and Seedance 2 you can pretty much create anything you can think of, with more granular control than people realize. It's not perfect but it's VERY good and I'm really excited to see the wild shit that new creators do with it!
0:10

AI video is waaaaay better than most people realize. I came with this stupid idea for a terrible PS1 game with hideous textures and a jumping catfish... 30 minutes later, I had this. It's almost exactly what I had in my head. Between Nano Banana, GPT Image 2 and Seedance 2 you can pretty much create anything you can think of, with more granular control than people realize. It's not perfect but it's VERY good and I'm really excited to see the wild shit that new creators do with it!

Finn McKenty

10,979 просмотров • 3 месяцев назад

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:
0:16

HTML Artifacts are a big part of how I work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:

elvis

18,374 просмотров • 3 месяцев назад

AM2R is a triumph. The original Metroid 2 on Game Boy was my first Metroid game, back when I was about 7. I've since played it about ten times. Over the years I've played all the 2D Metroids over and over, 5 to 20 times each. I don't usually play fan games, but this week I decided to finally give AM2R a shot (on Hard with an Xbox controller), and I gotta say... it's fantastic. It's simultaneously a more faithful remake than Samus Returns, and more satisfying to play and 100% complete. I like Samus Returns alright -- it's probably my least favorite 2D Metroid, still a good game though. But I think AM2R is even better.
0:12

AM2R is a triumph. The original Metroid 2 on Game Boy was my first Metroid game, back when I was about 7. I've since played it about ten times. Over the years I've played all the 2D Metroids over and over, 5 to 20 times each. I don't usually play fan games, but this week I decided to finally give AM2R a shot (on Hard with an Xbox controller), and I gotta say... it's fantastic. It's simultaneously a more faithful remake than Samus Returns, and more satisfying to play and 100% complete. I like Samus Returns alright -- it's probably my least favorite 2D Metroid, still a good game though. But I think AM2R is even better.

DidYouKnowGaming

101,196 просмотров • 2 лет назад

People still don't understand how good Codex has become 👀 I asked it to build this Starbucks website and within some 30 minutes it generated this without me touching a single line of code or spending time looking for assets either. Imagen generated every visual and GPT hooked everything into the codebase. After a couple of small tweaks it all just worked. It didn't even use half of my Codex session. It's super surprising to see quality of the assets. Was way better than I expected. That made me think about what AI is actually changing. Being a developer or a designer was never just about doing the work, writing code or designing it using some kind of tool. It was about knowing what to build in the first place. AI is getting incredibly good at the doing. The hard part is still having good ideas, making the right decisions, and knowing when something feels right. That is only getting more valuable. The people who win won't be the ones writing the most code. They'll be the ones with the best ideas who know how to turn them into reality with AI. Live: Code:
0:17

People still don't understand how good Codex has become 👀 I asked it to build this Starbucks website and within some 30 minutes it generated this without me touching a single line of code or spending time looking for assets either. Imagen generated every visual and GPT hooked everything into the codebase. After a couple of small tweaks it all just worked. It didn't even use half of my Codex session. It's super surprising to see quality of the assets. Was way better than I expected. That made me think about what AI is actually changing. Being a developer or a designer was never just about doing the work, writing code or designing it using some kind of tool. It was about knowing what to build in the first place. AI is getting incredibly good at the doing. The hard part is still having good ideas, making the right decisions, and knowing when something feels right. That is only getting more valuable. The people who win won't be the ones writing the most code. They'll be the ones with the best ideas who know how to turn them into reality with AI. Live: Code:

The Bugged Dev

60,699 просмотров • 1 месяц назад

I've used ghee a fair bit in my animal-based life but I was never able to tolerate the taste of it straight from the jar. This Great Ghee product is different. It tastes more like butter than any ghee I have ever used plus it's lab tested for glyphosate, grass fed and made from A2 cows. Ghee is clarified butter with the water and milk solids removed, leaving it almost pure fat. It is a low omega 6 concentration of saturated and monounsaturated fats and has little lactose and casein, which is why many people tolerate it better than butter and it's why it has a very high smoke point. Highly recommend this ghee and it's made by a small business in Virginia.
0:19

I've used ghee a fair bit in my animal-based life but I was never able to tolerate the taste of it straight from the jar. This Great Ghee product is different. It tastes more like butter than any ghee I have ever used plus it's lab tested for glyphosate, grass fed and made from A2 cows. Ghee is clarified butter with the water and milk solids removed, leaving it almost pure fat. It is a low omega 6 concentration of saturated and monounsaturated fats and has little lactose and casein, which is why many people tolerate it better than butter and it's why it has a very high smoke point. Highly recommend this ghee and it's made by a small business in Virginia.

Cary Kelly

25,775 просмотров • 6 месяцев назад

I'm still playing with 3D storyboards for Seedance 2.0. Even when I ask for a 2D video, using a 3D storyboard often pushes the model toward a 3D look. I haven't tested it extensively yet but there definitely seems to be a bias. So 2D storyboards work better for 2D videos, while 3D storyboards are better suited for 3D or photorealistic outputs. Another thing I found is that my video prompt is already very detailed. If I remove the storyboard section and generate the video without attaching a storyboard, the model still follows the same beats. The main difference is the environment. With a storyboard, it tends to recreate an environment that closely matches the storyboard. I also think storyboards help with certain poses and compositions. If you're curious about the prompts, I've included them below.
0:15

I'm still playing with 3D storyboards for Seedance 2.0. Even when I ask for a 2D video, using a 3D storyboard often pushes the model toward a 3D look. I haven't tested it extensively yet but there definitely seems to be a bias. So 2D storyboards work better for 2D videos, while 3D storyboards are better suited for 3D or photorealistic outputs. Another thing I found is that my video prompt is already very detailed. If I remove the storyboard section and generate the video without attaching a storyboard, the model still follows the same beats. The main difference is the environment. With a storyboard, it tends to recreate an environment that closely matches the storyboard. I also think storyboards help with certain poses and compositions. If you're curious about the prompts, I've included them below.

Kōda

43,256 просмотров • 2 месяцев назад

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.
0:15

After a few more hours, I think I've figured out Opus 5. Opus 5 is trained to be more agentic than anything I've used. All Claude 5 models are like that. So what changes? The way to interact with Opus 5 or contextualize it won't work the same way as with other models. It loves exploring, so it doesn't need much guidance for it. Unique preferences, artifacts, and references compliment it well and enable cleaner and more effective exploration and execution. Now that it can explore more effectively on its own and understand intent better, the best thing to do is to get out of its way (e.g., it doesn't need examples of your preferences; a clear high-level description of it works best). It's truly agentic in that sense. A good first step to provide better context for Opus 5 is to distinguish between what's situational and what needs persistence. Regardless, persistent system prompts and CLAUDE.MD needs to stay lightweight. Remove memories and tool descriptions from these. CLAUDE.MD is also a great place to tap into progressive disclosure by linking command/skills to it. On the situational side, agent skills and auto-memory can leverage progressive disclosure and the improved ability of the model to use its external context/knowledge. Conflicting and unnecessary instructions, which are common at this layer (mainly to ensure reliability), are going to throw off this model easily. That's the biggest change I had to make. Simple, clean, and clear prompts and skills work best. I had to clean a lot of my skills and system prompts. The way I prompt remains the same (usually clear and well-scoped). MCP tool descriptions are also more descriptive and have been deduped from the system prompt. Anthropic released a guide on the new rules for context engineering, which was helpful here. I started to test the recommendations and created a little artifact with the things that worked along the way. This might feel like a lot of work. Believe me, it has been frustrating. But I think we can expect future frontier models to become more agentic and smarter at figuring out the right context/gaps. The best thing to do is to prepare for that now. Boris Cherny mentioned that Opus 5 is their least prompt-injectable model yet. I am not sure if that was something they intentionally trained for or if it emerged based on how it was trained, which is to be extremely agentic in nature and more direct in execution.

elvis

37,685 просмотров • 1 месяц назад

Okay yall. I did it. Textured + Holographic Gold art pieces are working out. I've always wanted to do Gold ones but I knew I wanted to make it holographic (at least). Well this is textured too. It's a pain in the butt to make. But it's beautiful. Because it's a lot more work, I'm charging $5 more than the regular ones. Only 1 design available now - the Mega Charizard X EX one, 10 in stock for now. It's hard! I'm a dad. I'll try to do more after. There will be more don't worry. Link below! Also this one is not waterproof and scratched resistant, please treat it with care! What's next? Gold, BWRs, Rainbows? Gotta make em all
0:11

Okay yall. I did it. Textured + Holographic Gold art pieces are working out. I've always wanted to do Gold ones but I knew I wanted to make it holographic (at least). Well this is textured too. It's a pain in the butt to make. But it's beautiful. Because it's a lot more work, I'm charging $5 more than the regular ones. Only 1 design available now - the Mega Charizard X EX one, 10 in stock for now. It's hard! I'm a dad. I'll try to do more after. There will be more don't worry. Link below! Also this one is not waterproof and scratched resistant, please treat it with care! What's next? Gold, BWRs, Rainbows? Gotta make em all

PokeMinh

11,222 просмотров • 2 месяцев назад

I know a lot of people hate on AI. I get it. Be creative. But for those of use who can't draw or animate, this is more of a quick and cheap fix. and there's nothing wrong with that. I wish others were more open about sharing what they've learned using AI and not hoard their knowledge like it's worth gold. The only way we can learn and improve is if others share what they've learned. I understand people are protective of what prompts they use. Ok fine, don't share them. But you can't even give a tip? Like "add this phrase to the prompt for better [fill in the blank]" or "use [blank] for a more realistic atmosphere]. Just pisses me off. I'm happy to share all I've learned with anyone who askes. Same happened in the 3d printing community with crushable printed houses. No one wanted to share anything. So I gave up on that. #sizetwitter #giantess #AIart #giantessai #Sora2 #soraArt
0:10

I know a lot of people hate on AI. I get it. Be creative. But for those of use who can't draw or animate, this is more of a quick and cheap fix. and there's nothing wrong with that. I wish others were more open about sharing what they've learned using AI and not hoard their knowledge like it's worth gold. The only way we can learn and improve is if others share what they've learned. I understand people are protective of what prompts they use. Ok fine, don't share them. But you can't even give a tip? Like "add this phrase to the prompt for better [fill in the blank]" or "use [blank] for a more realistic atmosphere]. Just pisses me off. I'm happy to share all I've learned with anyone who askes. Same happened in the 3d printing community with crushable printed houses. No one wanted to share anything. So I gave up on that. #sizetwitter #giantess #AIart #giantessai #Sora2 #soraArt

Carly {Amazingly Unavoidable}

14,459 просмотров • 11 месяцев назад

I spent a day playing with GPT-5.6-Sol, and I can now say with much more confidence that it hasn’t improved at design tasks. I haven’t noticed any meaningful improvement in its coding capabilities, either. Maybe it's just in the tasks I gave it. However, I finished an app we started building on a stream yesterday and brought it close to the original idea I had in mind. It’s incredibly easy to build tools like this these days. I basically gave Codex a batch of editorial grid examples, then combined those layouts with formula-based pattern generation. A few prompts and some polishing, and you have something that can serve as a basic brand identity system.
0:15

I spent a day playing with GPT-5.6-Sol, and I can now say with much more confidence that it hasn’t improved at design tasks. I haven’t noticed any meaningful improvement in its coding capabilities, either. Maybe it's just in the tasks I gave it. However, I finished an app we started building on a stream yesterday and brought it close to the original idea I had in mind. It’s incredibly easy to build tools like this these days. I basically gave Codex a batch of editorial grid examples, then combined those layouts with formula-based pattern generation. A few prompts and some polishing, and you have something that can serve as a basic brand identity system.

Alex Barashkov

17,792 просмотров • 1 месяц назад

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.
0:15

GPT-5.5 is MUCH more reliable on longer running tasks - for the first time with any model. As we speak I have a migration running for over 7+ hours - this literally never happened before, the models would maybe run for 30 mins or of you really shout at them for 2-3 hours. Last night I went to sleep, set a long running task, then queued up 10 prompts to 'keep it going'. It did not stop after the first prompt and kept going for 8+ hours and I woke up to all the same prompts still queued up. The ability to run for a long time, in combination with ability to validate with computer use & other tools, makes it much more useful for building real applications.

Peter Gostev

105,642 просмотров • 4 месяцев назад

Made this commercial demo entirely with Seedance 2.0 via Yapper Everything you see here is done by one single prompt shot, from the cuts, edits, graphic effects, to the voice over. Basically within the prompt I gave detailed instructions on how many shots I wanted, the timestamps, the copywriting, visual and graphic effects, etc. The full prompt sample is available for my subscribers only in the comment section below ⏬ + + + There are so many use cases for Seedance 2.0 instead of just recreating existing IP. I think for me as a copywriter, what I like about it is that I can create a pre-visualization of an ad we're about to make, with its specific tone and style. Like I said before, the AI generated content here wasn't meant to be the final product, but rather a starting point for our creative direction regarding the potential style that will go into our ads. It's just that it's now so much faster to iterate ideas, and to test many different concepts with Gen-AI. Like I've always said, the technology is here, and it's up to you how you want to use it.
0:15

Made this commercial demo entirely with Seedance 2.0 via Yapper Everything you see here is done by one single prompt shot, from the cuts, edits, graphic effects, to the voice over. Basically within the prompt I gave detailed instructions on how many shots I wanted, the timestamps, the copywriting, visual and graphic effects, etc. The full prompt sample is available for my subscribers only in the comment section below ⏬ + + + There are so many use cases for Seedance 2.0 instead of just recreating existing IP. I think for me as a copywriter, what I like about it is that I can create a pre-visualization of an ad we're about to make, with its specific tone and style. Like I said before, the AI generated content here wasn't meant to be the final product, but rather a starting point for our creative direction regarding the potential style that will go into our ads. It's just that it's now so much faster to iterate ideas, and to test many different concepts with Gen-AI. Like I've always said, the technology is here, and it's up to you how you want to use it.

MXVDXN // DAN

17,791 просмотров • 5 месяцев назад

introducing a new, very fun, LLM benchmark- the Game-of-Life Bench! the rules are simple: given an 8x8 grid following Conway's game of life rules, the goal is to create an initial pattern with at most 32 cells that can last the longest number of turns before dying/repeating. some results to highlight (with caveats detailed below): - gpt 5.1 lasts the longest with a 106 step run - claude models are really bad at this! they refuse to reason about this task and score < 25 points - deepseek r1 is the best open model with 102 steps. why? because i wanted to create a benchmark that has (i think) no practicality, but is still fun to look at, cheap, and still measures something interesting. i also am a big fan of the game of life. its absurdly simple rules leading to intractability is extremely cool to me. also, i saw a lot of work with LLMs trying to "predict" the next state in Conway's game of life, I think game-of-life bench is more fun because it's pretty open ended and only asks the LLM for the initial state. I also think this could be an RL env? but idk why you would ever train on this task haha i don't think this is a "serious" benchmark because it doesnt measure anything practical, but i still think it's a hard benchmark exactly because you can't predict what happens with your initial state many turns into the future; this is why i was initially expecting all LLMs to be bad at it, but turns out, some are clearly better than the others (the ordering may surprise you!) reminder: this is still a work-in-progress; (1) i am gpu-poor so could only do 10 runs for each model, even though total running cost is relatively low. maybe with some more credits i can run more seeds for each model. (2) i handpicked models which i think are at the frontier right now, plus some others that were on my mind. so, if you'd like to see a model on here, let me know. (3) i currently only do an 8x8 grid because i thought that by itself would be pretty hard for current LLMs, but of course we can increase grid sizes! (4) the coolest thing is, i dont think we can calculate the max possible number of states (yay undecidability!) you can go without repeating, so this is essentially a no-ceiling task, which is pretty cool! again, i did this mostly out of a desire to make LLMs do something fun. if this keeps me entertained for a few more days, i'd likely release a blog post on it. if it keeps me entertained for a week (and someone sponsors me), i'll put more work into it :P lastly, this is fully open sourced, so feel free to run this on your own!
0:19

introducing a new, very fun, LLM benchmark- the Game-of-Life Bench! the rules are simple: given an 8x8 grid following Conway's game of life rules, the goal is to create an initial pattern with at most 32 cells that can last the longest number of turns before dying/repeating. some results to highlight (with caveats detailed below): - gpt 5.1 lasts the longest with a 106 step run - claude models are really bad at this! they refuse to reason about this task and score < 25 points - deepseek r1 is the best open model with 102 steps. why? because i wanted to create a benchmark that has (i think) no practicality, but is still fun to look at, cheap, and still measures something interesting. i also am a big fan of the game of life. its absurdly simple rules leading to intractability is extremely cool to me. also, i saw a lot of work with LLMs trying to "predict" the next state in Conway's game of life, I think game-of-life bench is more fun because it's pretty open ended and only asks the LLM for the initial state. I also think this could be an RL env? but idk why you would ever train on this task haha i don't think this is a "serious" benchmark because it doesnt measure anything practical, but i still think it's a hard benchmark exactly because you can't predict what happens with your initial state many turns into the future; this is why i was initially expecting all LLMs to be bad at it, but turns out, some are clearly better than the others (the ordering may surprise you!) reminder: this is still a work-in-progress; (1) i am gpu-poor so could only do 10 runs for each model, even though total running cost is relatively low. maybe with some more credits i can run more seeds for each model. (2) i handpicked models which i think are at the frontier right now, plus some others that were on my mind. so, if you'd like to see a model on here, let me know. (3) i currently only do an 8x8 grid because i thought that by itself would be pretty hard for current LLMs, but of course we can increase grid sizes! (4) the coolest thing is, i dont think we can calculate the max possible number of states (yay undecidability!) you can go without repeating, so this is essentially a no-ceiling task, which is pretty cool! again, i did this mostly out of a desire to make LLMs do something fun. if this keeps me entertained for a few more days, i'd likely release a blog post on it. if it keeps me entertained for a week (and someone sponsors me), i'll put more work into it :P lastly, this is fully open sourced, so feel free to run this on your own!

Akshit

13,775 просмотров • 6 месяцев назад

【🌷 3D REVEAL~! 🌷】 It was a dream (of spring hehe) come true to join some of my most precious friends to celebrate Nimi's 1-year #nimiversary at her 3D concert and to sing and dance together~! 🎶 This is actually both my new 3D model and was my first time doing mocap. 💖 It means a lot to me, and I'm so happy it got to be with friends!!! I love love love how Ayn @ VGEN was able to bring my wonderful mama さえきやひろ💀's art to life so skillfully and beautifully. 🎨 This is the reveal of my proper main hairstyle too~! I'm able to express myself so well with it, from every soft and silly expression, so the way the flowy dress moves like petals in the wind, to the bounce and flutter of my wings! 🎀 And this model actually was made possible BECAUSE of Nimi 💚 I didn't have a 3D model at all at the time, but I'm happy that she wanted me to be able to stand by her side and dance together and hug her ;////; I will treasure this model always. It's another important addition to the fairytale we've been writing together! I'll keep putting all of my heart into blooming more and more as an idol, and making happy memories with you all like we did today!
0:12

【🌷 3D REVEAL~! 🌷】 It was a dream (of spring hehe) come true to join some of my most precious friends to celebrate Nimi's 1-year #nimiversary at her 3D concert and to sing and dance together~! 🎶 This is actually both my new 3D model and was my first time doing mocap. 💖 It means a lot to me, and I'm so happy it got to be with friends!!! I love love love how Ayn @ VGEN was able to bring my wonderful mama さえきやひろ💀's art to life so skillfully and beautifully. 🎨 This is the reveal of my proper main hairstyle too~! I'm able to express myself so well with it, from every soft and silly expression, so the way the flowy dress moves like petals in the wind, to the bounce and flutter of my wings! 🎀 And this model actually was made possible BECAUSE of Nimi 💚 I didn't have a 3D model at all at the time, but I'm happy that she wanted me to be able to stand by her side and dance together and hug her ;////; I will treasure this model always. It's another important addition to the fairytale we've been writing together! I'll keep putting all of my heart into blooming more and more as an idol, and making happy memories with you all like we did today!

Phoebe Chan 🐝🌸 Densetsu.EXE 🔜 Skyline Serenade

63,861 просмотров • 6 месяцев назад

In the past week, I was able to build the following games: - An endless runner - A tower defense - A Mario Party-like mini-game - An arena-based shooter The key unlock here was the ThreeJS skill With Opus 4.5 & GPT 5.2 - Claude Code / Codex CLI have much better end results now. With each game, I continued to update the skill based on bugs and issues faced - so it progressively got better and better at building the gameplay I was looking for. I've been doing this for a while now - and I can say that the leap in building games with vibe coding is real.
0:12

In the past week, I was able to build the following games: - An endless runner - A tower defense - A Mario Party-like mini-game - An arena-based shooter The key unlock here was the ThreeJS skill With Opus 4.5 & GPT 5.2 - Claude Code / Codex CLI have much better end results now. With each game, I continued to update the skill based on bugs and issues faced - so it progressively got better and better at building the gameplay I was looking for. I've been doing this for a while now - and I can say that the leap in building games with vibe coding is real.

Chong-U

266,787 просмотров • 8 месяцев назад

I never thought I would ever say this, but I have truly lost all my confidence today. A part of me still believes in my work and knows the value of what I have built here over the past five years. At the same time, I just feel faded. The people I associated with closely haven't supported me, and the majority of my collector base has left the space. I still took it on the chin and continued to show up because I blindly believed in what I do and I know what it has done for me. I never had a Plan B. There was never a backup plan, and that is exactly why I even got here in the first place. I was good for nothing but art, and that is the reason I have always said that art saved my life. But lately, it feels like it is the very thing that is going to kill me. I really don't know how I feel about everything anymore. I just don't know. But I am not going anywhere. This is my home, so I still gonna continue to show up! I just needed to get this off my chest.
0:12

I never thought I would ever say this, but I have truly lost all my confidence today. A part of me still believes in my work and knows the value of what I have built here over the past five years. At the same time, I just feel faded. The people I associated with closely haven't supported me, and the majority of my collector base has left the space. I still took it on the chin and continued to show up because I blindly believed in what I do and I know what it has done for me. I never had a Plan B. There was never a backup plan, and that is exactly why I even got here in the first place. I was good for nothing but art, and that is the reason I have always said that art saved my life. But lately, it feels like it is the very thing that is going to kill me. I really don't know how I feel about everything anymore. I just don't know. But I am not going anywhere. This is my home, so I still gonna continue to show up! I just needed to get this off my chest.

Graffiti On Grave

12,965 просмотров • 4 месяцев назад

Building a personal knowledge base for my agents is increasingly where I spend my time these days. Like Andrej Karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers. I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal. You all get to benefit from that with the papers I feature in my timeline and on DAIR.AI. The papers are indexed using tobi lutke qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there. I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip. 100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation. But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close. The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to. Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them. Work in progress. More updates soon. Back to building.
0:18

Building a personal knowledge base for my agents is increasingly where I spend my time these days. Like Andrej Karpathy, I also use Obsidian for my MD vaults. What's different in my approach is that I curate research papers on a daily basis and have actually tuned a Skill for months to find high-signal, relevant papers. I was reviewing and curating papers manually for some time, but now it's all automated as it has gotten so good at capturing what I consider the best of the best. There are so many papers these days, so this is a big deal. You all get to benefit from that with the papers I feature in my timeline and on DAIR.AI. The papers are indexed using tobi lutke qmd cli tool (all of it in markdown files along with useful metadata). So good for semantic search and surfacing insights, unlike anything out there. I am a visual person, so I then started to experiment with how to leverage this personal knowledge base of research papers inside my new interactive artifact generator (mcp tools inside my agent orchestrator system). The result is what you see in the clip. 100s of papers with all sorts of insights visualized. I keep track of research papers daily, so believe me when I tell you that this system is absolutely insane at surfacing insights. This is the result of months of tinkering on how to index research and leverage agent automations for wikification and robust documentation. But this is just the beginning. The visual artifact (which is interactive too) can be changed dynamically as I please. I can prompt my agent to throw any data at it. I can add different views to the data. Different interactions. I feel like this is the most personalized research system I have ever built and used, and it's not even close. The knowledge that the agents are able to surface from this basic setup is already extremely useful as I experiment with new agentic engineering concepts. I feel like this knowledge layer and the higher-level ones I am working on will allow me to maximize other automation tools like autoresearch. The research is only as good as the research questions. And the research questions are only as good as the insights the agents have access to. Where I am spending time now is on how to make this more actionable. I am obsessed about the search problem here. The automations, autoresearch, ralph research loop (I built one months ago) are easier to build but are only as good as what you feed them. Work in progress. More updates soon. Back to building.

elvis

466,109 просмотров • 5 месяцев назад