Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Can computer-use models play games now, one-shot? I gave Claude Opus 4.5 a simple prompt like "play league of legends" and it starts clicking and typing around my computer pretty effectively even though it doesn't win due to latency More interestingly between Minecraft, finding car insurance, and booking flights... show more

Surya

15,887 subscribers

411,793 görüntüleme • 9 ay önce •via X (Twitter)

Oyun Bilim & Teknoloji

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

Anthropic computer use API + iPhone mirroring to a Mac = AI controlled phone. Watch Claude control my phone and successfully look up stats in my Sports app. I even got it to play a game in the Chess app against another AI - pretty crazy. And this is the worst it’ll ever be.

Anthropic computer use API + iPhone mirroring to a Mac = AI controlled phone. Watch Claude control my phone and successfully look up stats in my Sports app. I even got it to play a game in the Chess app against another AI - pretty crazy. And this is the worst it’ll ever be.

Mckay Wrigley

607,955 görüntüleme • 1 yıl önce

Kimi K3 makes me feel like one prompt is enough to build a game. You can build a game console, plug in a cartridge, and play a game on it. I just played one of my fav game "Ace Attorney" on my computer!

Kimi K3 makes me feel like one prompt is enough to build a game. You can build a game console, plug in a cartridge, and play a game on it. I just played one of my fav game "Ace Attorney" on my computer!

Crystal

14,334 görüntüleme • 1 ay önce

Back in the late 1980s, a friend gave me a single floppy disk as a birthday present. He told me it was something you could put games on and actually play, and I remember staring at it all day, wondering if something that magical could really be possible. I followed him to a computer academy, and that was the first time I had ever seen a computer in my life. As a reward for bringing me in, he even got a whole box of floppy disks. That was the moment I first stepped into a completely new world. And when I saw, just like in the video, games being copied onto a disk, inserted into a computer, and actually running… the shock I felt easily ranks in my top five moments of my life.

Back in the late 1980s, a friend gave me a single floppy disk as a birthday present. He told me it was something you could put games on and actually play, and I remember staring at it all day, wondering if something that magical could really be possible. I followed him to a computer academy, and that was the first time I had ever seen a computer in my life. As a reward for bringing me in, he even got a whole box of floppy disks. That was the moment I first stepped into a completely new world. And when I saw, just like in the video, games being copied onto a disk, inserted into a computer, and actually running… the shock I felt easily ranks in my top five moments of my life.

Gamer_lafan

84,180 görüntüleme • 4 ay önce

Asmongold says game developers who put masculine female characters in video games make it harder for him to support and play their games 👀😳 "You're not gonna play Halo? I'm not really that excited about it anymore. I saw some of the stuff about the game, and it felt like another one of those. I don't know why a developer would put weird, masculine female characters in there. There's a part of me that doesn't even want to play or support the game”

Asmongold says game developers who put masculine female characters in video games make it harder for him to support and play their games 👀😳 "You're not gonna play Halo? I'm not really that excited about it anymore. I saw some of the stuff about the game, and it felt like another one of those. I don't know why a developer would put weird, masculine female characters in there. There's a part of me that doesn't even want to play or support the game”

Prism

37,201 görüntüleme • 28 gün önce

🧸 you’re asking if it was hard when i worked part-time at the kids cafe? of course 🙂‍↕️ the thing that really shocked me back then was…even when we play simple games we play a lot of tricks and joke around a lot but these innocent babies can’t tolerate that 🧸 you can’t play tricks and if we have rules set from 1 to 10, these babies can only enjoy if you play within those rules but if i make my own rule #11 outside these rules and do that, they’ll be like “hyung, that doesn’t exist…why are you doing that?” “why are you playing foul?” so if i want to play with them, i need to think like a child and play & enjoy within their set rules 🧸 it was really fascinating to me…it made me think “these babies are really that innocent, huh?”

🧸 you’re asking if it was hard when i worked part-time at the kids cafe? of course 🙂‍↕️ the thing that really shocked me back then was…even when we play simple games we play a lot of tricks and joke around a lot but these innocent babies can’t tolerate that 🧸 you can’t play tricks and if we have rules set from 1 to 10, these babies can only enjoy if you play within those rules but if i make my own rule #11 outside these rules and do that, they’ll be like “hyung, that doesn’t exist…why are you doing that?” “why are you playing foul?” so if i want to play with them, i need to think like a child and play & enjoy within their set rules 🧸 it was really fascinating to me…it made me think “these babies are really that innocent, huh?”

💬

35,845 görüntüleme • 5 ay önce

Introducing World-Builder. A game that lets you prompt anything in to existance. You can make vehicles (anything that traverses air, land, or sea), you can build buildings, or weapons. Literally anything you can imagine. I saw people like Matt Shumer one-shotting games, but I don't think that's the future of games. I think the future of gaming is true world-building. BUT, the one-shotted games showed me that I think technology is finally at a place where we can experiment with what the UX of world-building games actually is. I've been building it between meetings, but its actually pretty fun and everyone at tenex is testing it out! If you want to play it, test it out with me, and maybe even contribute to it, let me know!

Introducing World-Builder. A game that lets you prompt anything in to existance. You can make vehicles (anything that traverses air, land, or sea), you can build buildings, or weapons. Literally anything you can imagine. I saw people like Matt Shumer one-shotting games, but I don't think that's the future of games. I think the future of gaming is true world-building. BUT, the one-shotted games showed me that I think technology is finally at a place where we can experiment with what the UX of world-building games actually is. I've been building it between meetings, but its actually pretty fun and everyone at tenex is testing it out! If you want to play it, test it out with me, and maybe even contribute to it, let me know!

Arman Hezarkhani

23,056 görüntüleme • 23 gün önce

I built a form-filling agent that anyone can use 💫 This is an extremely simple but useful (I hope) app. Upload a fillable form 📋, some context files, and chat with the agent to fill the form out automatically ✍️ 1️⃣ Yes it is a Claude Code SDK wrapper 2️⃣ It is better and faster than ChatGPT/Claude UI out of the box 3️⃣ We use LlamaParse to parse the context files, so you can have more trust that we are able to read context without hallucinations (e.g. messy scanned handwriting, drivers license photo, and more). This was one of my holiday Claude Code vibe-coding projects. Built with Opus 4.5, and also powered by Opus 4.5. Feeling the AGI 🫡 App is here: Repo is open-source:

I built a form-filling agent that anyone can use 💫 This is an extremely simple but useful (I hope) app. Upload a fillable form 📋, some context files, and chat with the agent to fill the form out automatically ✍️ 1️⃣ Yes it is a Claude Code SDK wrapper 2️⃣ It is better and faster than ChatGPT/Claude UI out of the box 3️⃣ We use LlamaParse to parse the context files, so you can have more trust that we are able to read context without hallucinations (e.g. messy scanned handwriting, drivers license photo, and more). This was one of my holiday Claude Code vibe-coding projects. Built with Opus 4.5, and also powered by Opus 4.5. Feeling the AGI 🫡 App is here: Repo is open-source:

Jerry Liu

48,431 görüntüleme • 7 ay önce

Rekkles: "—and Keria really wanted to play AD against me, so I was just honestly proud to be even thought of, if that makes sense, that they really wanted to make a specific role swap style versus me... And even though he kinda won the lane against me, I feel like it was really fun to play an ADC game. I did it last year as well, and it's something that, of course, I hold dearly in my heart after all these years, so whenever I get the chance, I always take it."

Rekkles: "—and Keria really wanted to play AD against me, so I was just honestly proud to be even thought of, if that makes sense, that they really wanted to make a specific role swap style versus me... And even though he kinda won the lane against me, I feel like it was really fun to play an ADC game. I did it last year as well, and it's something that, of course, I hold dearly in my heart after all these years, so whenever I get the chance, I always take it."

yo

376,215 görüntüleme • 9 ay önce

WOW! I'm so excited about this. OpenAI Developers said Codex was good at Computer Use, but I wasn't prepared for this. For the last two weeks I've been working on a Computer Use skill to work with Linux. And while I had some success, it was a pretty frustrating experience. That is...until the breakthrough. Using accessibility tools, Codex can now control my entire computer, not just the browser. There are limits to this, of course, but what a time to be alive. This Computer Use skill will unlock and entirely new set of automations, all powered by Codex. Demonstration below 👇

WOW! I'm so excited about this. OpenAI Developers said Codex was good at Computer Use, but I wasn't prepared for this. For the last two weeks I've been working on a Computer Use skill to work with Linux. And while I had some success, it was a pretty frustrating experience. That is...until the breakthrough. Using accessibility tools, Codex can now control my entire computer, not just the browser. There are limits to this, of course, but what a time to be alive. This Computer Use skill will unlock and entirely new set of automations, all powered by Codex. Demonstration below 👇

am.will

79,698 görüntüleme • 5 ay önce

Our first short course with Anthropic! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let AI agents do many more tasks than were possible before, since it lets them interact with interfaces designed for humans to use, rather than only tools that provide explicit API access. I hope you will enjoy learning about it! This course is taught by Anthropic's Head of Curriculum, Colt_Steele. You'll learn to apply image reasoning and tool use to "use" a computer as follows: a model processes an image of the screen, analyzes it to understand what's going on, and navigates the computer via mouse clicks and keystrokes. This course goes through the key building blocks, and culminates in a demo of an AI assistant that uses a web browser to search for a research paper, downloads the PDF, and finally summarizes the paper for you. In detail, you’ll: - Learn about Anthropic's family of models, when to use which one, and make API requests to Claude - Use multi-modal prompts that combine text and image content blocks, and also work with streaming responses - Improve your prompting by using prompt templates, using XML to structure prompts, and providing examples - Implement prompt caching to reduce cost and latency - Apply tool-use to build a chatbot that can call different tools to respond to queries - See all these building blocks come together in Computer Use demo Please sign up here:

Our first short course with Anthropic! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let AI agents do many more tasks than were possible before, since it lets them interact with interfaces designed for humans to use, rather than only tools that provide explicit API access. I hope you will enjoy learning about it! This course is taught by Anthropic's Head of Curriculum, Colt_Steele. You'll learn to apply image reasoning and tool use to "use" a computer as follows: a model processes an image of the screen, analyzes it to understand what's going on, and navigates the computer via mouse clicks and keystrokes. This course goes through the key building blocks, and culminates in a demo of an AI assistant that uses a web browser to search for a research paper, downloads the PDF, and finally summarizes the paper for you. In detail, you’ll: - Learn about Anthropic's family of models, when to use which one, and make API requests to Claude - Use multi-modal prompts that combine text and image content blocks, and also work with streaming responses - Improve your prompting by using prompt templates, using XML to structure prompts, and providing examples - Implement prompt caching to reduce cost and latency - Apply tool-use to build a chatbot that can call different tools to respond to queries - See all these building blocks come together in Computer Use demo Please sign up here:

Andrew Ng

170,425 görüntüleme • 1 yıl önce

Garrett Wilson opens up on his feelings after the Jets traded away Sauce Gardner and Quinnen Williams: "I don't get paid to have a vision, [the Jets] do - and they've got one. I've got to trust it, man. I do. My emotions, that side of it...I hate it. I hate it. I play football, I play with my brothers, I get to know my brothers...I hate it. But I'm paid to play football. No one cares if I hate it, go catch the ball. That's how I see it. That's what I'm going to do - I'm going to do my job to the best of my abilities so that stuff like that, they feel like they can keep us all together. That's the reality - you don't win games, things change."

Garrett Wilson opens up on his feelings after the Jets traded away Sauce Gardner and Quinnen Williams: "I don't get paid to have a vision, [the Jets] do - and they've got one. I've got to trust it, man. I do. My emotions, that side of it...I hate it. I hate it. I play football, I play with my brothers, I get to know my brothers...I hate it. But I'm paid to play football. No one cares if I hate it, go catch the ball. That's how I see it. That's what I'm going to do - I'm going to do my job to the best of my abilities so that stuff like that, they feel like they can keep us all together. That's the reality - you don't win games, things change."

SNY Jets

2,524,214 görüntüleme • 9 ay önce

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself

OPUS 4.6 WAS NERFED DUE TO DEMAND BUT OPUS 4.5 DOES NOT SEEM TO BE HIT this guy ran the same test on both models. Opus 4.6 fails consistently but Opus 4.5 passes every time he switched back to Opus 4.5 on Claude Code and said "what a difference, feels like i got Opus back finally" he is now using this test as a "quantization canary" that runs it at the start of every session before doing real work. if it fails, the model is degraded. five Opus 4.6 windows in a row failed the untransparent nerfing is pushing people to cancel their Max plans if you've been feeling like Opus got dumber lately, you're not imagining it i'd suggest switching to Opus 4.5 to see the difference for yourself

Om Patel

696,175 görüntüleme • 4 ay önce

Block blast makes ~$1M/day from ads I play it everyday and my biggest gripe is there's no way to skip them So I vibe coded my own version - here's how: > Write prompt with gpt-5 > Build using opus 4.5 on rork > Done entirely on my phone I used to code games from scratch and it took months, now all it takes is a $25/month app and the quality feels unreal With 0.1% of block blast's market, you’ll have a $30k/month app If you’re waiting to start building - this is your sign

Block blast makes ~$1M/day from ads I play it everyday and my biggest gripe is there's no way to skip them So I vibe coded my own version - here's how: > Write prompt with gpt-5 > Build using opus 4.5 on rork > Done entirely on my phone I used to code games from scratch and it took months, now all it takes is a $25/month app and the quality feels unreal With 0.1% of block blast's market, you’ll have a $30k/month app If you’re waiting to start building - this is your sign

Avery

271,860 görüntüleme • 8 ay önce

I gave Claude Opus 5 the exact same extreme-ocean challenge I gave GPT-5.6 Sol. The result was honestly on another level. Visually, technically and in sheer ambition, Opus built a substantially better project. But it also spent almost 10x more and worked like a maniac, continuously expanding, refining and adding things even though I never asked it to enter any kind of /loop. That tradeoff is fascinating. Sol felt efficient and deliberate. Opus felt almost creatively unrestrained. And yet... I’m completely enchanted by what it built. The project is already ridiculously promising, and watching a coding model autonomously keep pushing a simulated world further than I asked for is one hell of a glimpse at where this is going.

I gave Claude Opus 5 the exact same extreme-ocean challenge I gave GPT-5.6 Sol. The result was honestly on another level. Visually, technically and in sheer ambition, Opus built a substantially better project. But it also spent almost 10x more and worked like a maniac, continuously expanding, refining and adding things even though I never asked it to enter any kind of /loop. That tradeoff is fascinating. Sol felt efficient and deliberate. Opus felt almost creatively unrestrained. And yet... I’m completely enchanted by what it built. The project is already ridiculously promising, and watching a coding model autonomously keep pushing a simulated world further than I asked for is one hell of a glimpse at where this is going.

Token Gremlin

12,496 görüntüleme • 4 gün önce

Sam Altman admits even he hasn't adopted his own product Codex as much as he should and still uses his computer the old way "The thing that feels most psychologically inconsistent about myself is that I have for 20 years been using computers the same way." "I now have a magic thing called Codex -- so do you, so does everybody. That means I should completely be using my computer in a different way." "I should not be clicking around, pasting from one messaging app to another. I should not be scrolling mindlessly through my emails trying to figure out which one is least painful to open. I should not be keeping a to-do list and doing these rote computer tasks the same way I have for so long." "And yet there's something in my mind that is encoded, that doing this kind of stuff is what it means to work and to be productive." "If you asked me, I would never say I like doing it that way -- in fact I'd say the opposite, and I'd mean it." "But by revealed preference, I have a better way to do it now, and I still do it the old way. It makes no sense, other than I must secretly like it or feel good about it."

Sam Altman admits even he hasn't adopted his own product Codex as much as he should and still uses his computer the old way "The thing that feels most psychologically inconsistent about myself is that I have for 20 years been using computers the same way." "I now have a magic thing called Codex -- so do you, so does everybody. That means I should completely be using my computer in a different way." "I should not be clicking around, pasting from one messaging app to another. I should not be scrolling mindlessly through my emails trying to figure out which one is least painful to open. I should not be keeping a to-do list and doing these rote computer tasks the same way I have for so long." "And yet there's something in my mind that is encoded, that doing this kind of stuff is what it means to work and to be productive." "If you asked me, I would never say I like doing it that way -- in fact I'd say the opposite, and I'd mean it." "But by revealed preference, I have a better way to do it now, and I still do it the old way. It makes no sense, other than I must secretly like it or feel good about it."

Fireside Alpha

43,710 görüntüleme • 5 gün önce

✨ Added a CRT curvature distortion to pieter™ now It takes the Em-DOSBox and processes it in WebGL and builds a new with the distortion of a classic CRT screen which had this convex curvature (like an old TV) even though the screen itself was square I had this working on DOSBox on MacOS and on Linux with CRT-Pi shader, but on web it doesn't support shaders so I had to build my own with Claude Code in JS, very easy I remember trying this a year ago and Claude Code fucked it up so bad that I gave up, so I think the models have improved a lot Tomorrow I'll try add some scanlines, it really helps make the simulation more passable (and nostalgic!) 😊👌

✨ Added a CRT curvature distortion to pieter™ now It takes the Em-DOSBox and processes it in WebGL and builds a new with the distortion of a classic CRT screen which had this convex curvature (like an old TV) even though the screen itself was square I had this working on DOSBox on MacOS and on Linux with CRT-Pi shader, but on web it doesn't support shaders so I had to build my own with Claude Code in JS, very easy I remember trying this a year ago and Claude Code fucked it up so bad that I gave up, so I think the models have improved a lot Tomorrow I'll try add some scanlines, it really helps make the simulation more passable (and nostalgic!) 😊👌

@levelsio

88,256 görüntüleme • 7 ay önce

I think one of the coolest things of being a Mariner is that I went from thinking Ichiro was larger than life and imitating his batting stance/swing in the backyard to one day I blinked and woke up to moments like this 😂 (I was perfectly fine) Now we all get to watch this man enter the HOF. Pretty awesome, even though I think he can still play today

I think one of the coolest things of being a Mariner is that I went from thinking Ichiro was larger than life and imitating his batting stance/swing in the backyard to one day I blinked and woke up to moments like this 😂 (I was perfectly fine) Now we all get to watch this man enter the HOF. Pretty awesome, even though I think he can still play today

Tayler Saucedo

531,523 görüntüleme • 1 yıl önce

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

I asked Garry Tan how to use meta prompting to get better at AI: "My partners at YC Jared Friedman and Pete Koomen showed me how to do this. You can take almost anything that you do all the time and just drop it into a context window. And then say, “Here’s a bunch of inputs and outputs." And maybe you also add a bunch of notes. And then you tell it, “Write me a prompt that can act as an agent that takes this input and makes this output over here.” You can do this for almost any type of knowledge work. And you can even introspect. "What are things you notice that I did to convert this from the input to the output?”. And then you can just start using the prompt. Initially, it’s going to suck. Because it’s just not that smart yet. But what’s funny is now, I also use it to Iterate my writing. You can be very direct, "I would never say that", "Don’t say it like this", or "Oh, you used the long word there, use the short word". Just speak to it conversationally. And then when you're happy with the output, you can use that new output to make a new prompt. "Based on this conversation, give me a better initial prompt that incorporates all the things we talked about." And you can do this with literally everything. And in theory, there’s so much it applies to that people do day-to-day. You could use it for tweets. You could use it for editing podcasts. You can use it for pretty much everything. I have a folder of prompts that I use all the time. My YouTube prompt is on v27 or something. I'll go through this process with all the different max models. I'll use GPT 5.2 Pro. I’ll use Grok. I'll use Claude. Then, I’ll take all the outputs from all the models and put them into Claude and say "Here’s my prompt, here’s the output from four LLMs, including yourself. Rate each response and tell me what the pros and cons of each approach are." And I usually say "give it to me in numbered form". And then you can agree with one, disagree with two, tell it three is this or that. And then after that, you say given all of this, synthesize it."

The Peel

51,632 görüntüleme • 6 ay önce

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)

Okay, I got Claude Code to actually fly my plane now It controls the keys via Chrome by running it with `claude --chrome` There is some issue with the lift vs gravity formula though so it takes a lot of speed to take off, but it's really cool to see it control and fly the plane This means it can code the game and then play it to check in a loop to theoretically improve it without my help (haven't gotten there though) I run it like this btw: `IS_SANDBOX=1 claude --dangerously-skip-permissions --chrome` (Run at your own risk)

@levelsio

143,316 görüntüleme • 7 ay önce

An emotional Brandt Snedeker: "To not have my card the last couple of years, to be struggling to do what I love, you know, to still have a passion to play this game the way I want to play it and to show people how I can still do it, especially not playing my best and struggling the way I did to come back and fight, claw my way back and play some great golf this year even though it hasn't seemed like it to people outside. "I knew I was playing well. I just hadn't been able to put it all together. Hopefully it shows my family, my kids something. Just, you know, ten wins out here is an accomplishment. Something I'm very proud of."

An emotional Brandt Snedeker: "To not have my card the last couple of years, to be struggling to do what I love, you know, to still have a passion to play this game the way I want to play it and to show people how I can still do it, especially not playing my best and struggling the way I did to come back and fight, claw my way back and play some great golf this year even though it hasn't seemed like it to people outside. "I knew I was playing well. I just hadn't been able to put it all together. Hopefully it shows my family, my kids something. Just, you know, ten wins out here is an accomplishment. Something I'm very proud of."

Cameron Jourdan

268,758 görüntüleme • 3 ay önce