正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Whoa, I just used Google's Bard AI to recreate a basic timer app for iPhone in under 4 minutes... just from a screenshot! 🤯 Did not give it hints as to what the app did, and it provided all of the code—it made some mistakes but nothing it couldn't... show more

Ammaar Reshi

92,693 subscribers

508,457 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Min Choi 的头像

Min Choi3 年前

@spacecasetay Pretty awesome! 🔥 And while Code Interpreter is disabled!

Ammaar Reshi 的头像

Ammaar Reshi3 年前

@spacecasetay Hahah perfect timing.

AP 的头像

AP3 年前

Google is cooking 🧑‍🍳

Ammaar Reshi 的头像

Ammaar Reshi3 年前

I feel like we’re sleeping on them!!

TechnoKing 的头像

TechnoKing3 年前

"do not make any mistakes" is my new favorite prompt

Ammaar Reshi 的头像

Ammaar Reshi3 年前

LOL it might have been too much pressure for it

Databas3 的头像

Databas33 年前

What do you use for these screen recordings? Looks great!

Ammaar Reshi 的头像

Ammaar Reshi3 年前

@databas3_io from @pie6k—easily one of my favorite mac apps!

Sam Sung 的头像

Sam Sung3 年前

This is awesome - we saw a demo like this when GPT-4 was released (i.e., drawing a UI of a website, and then AI coding it), but GPT-4 does not yet allow uploading of images. This should open up a lot of ideas for non-technical folks who want to build an app or website, but don't want to explain the entire UI (rather, just sketch it or create it in Figma)

Ammaar Reshi 的头像

Ammaar Reshi3 年前

Oh yeah!! I wonder when they’ll open up with that. Totally, just another great way for folks to get started on their ideas!

相关视频

The ChatGPT Mac app is the ultimate screenshot-to-code tool. Screenshot anything, paste it in the ChatGPT shortcut, and just tell GPT-4o to code it for you. Here's me taking a snapshot of Snake Game and getting fully working code in 90 seconds. Video is on 3x speed.

The ChatGPT Mac app is the ultimate screenshot-to-code tool. Screenshot anything, paste it in the ChatGPT shortcut, and just tell GPT-4o to code it for you. Here's me taking a snapshot of Snake Game and getting fully working code in 90 seconds. Video is on 3x speed.

Rowan Cheung

860,703 次观看 • 2 年前

Bolt built my entire mobile app from scratch 🤯 No Figma. No code. Just prompts. I used Bolt + UX Pilot + ChatGPT to go from raw idea to live preview in under 15 minutes. Here’s exactly how I did it:

Bolt built my entire mobile app from scratch 🤯 No Figma. No code. Just prompts. I used Bolt + UX Pilot + ChatGPT to go from raw idea to live preview in under 15 minutes. Here’s exactly how I did it:

Prajwal Tomar

163,948 次观看 • 1 年前

i asked an AI to break my app. it did. then fixed it. it was breaking the app on purpose and somehow made it better i used the new Replit ⠕ Agent 3 (anyone can try it right now ) i set it up to act like a QA tester told it to click through every page try every button and report anything weird it didn’t just test the app — it used an actual browser logged every step screenshot the UI and flagged two bugs i didn’t even know existed then it rewrote the code to fix them tested it again and sent me a summary like “fixed button logic on checkout flow — confirm working” all without me asking it ran for almost 2 hours autonomously while i did other work this is like a dev + tester rolled into one but without the back and forth i didn’t give it prompts i gave it a goal and that’s just one thing it can do it’s more like assigning work to a teammate not chatting with a bot we can now finally hand off part of our own work and products to AI without being nervous about the outcome you can try it here:

i asked an AI to break my app. it did. then fixed it. it was breaking the app on purpose and somehow made it better i used the new Replit ⠕ Agent 3 (anyone can try it right now ) i set it up to act like a QA tester told it to click through every page try every button and report anything weird it didn’t just test the app — it used an actual browser logged every step screenshot the UI and flagged two bugs i didn’t even know existed then it rewrote the code to fix them tested it again and sent me a summary like “fixed button logic on checkout flow — confirm working” all without me asking it ran for almost 2 hours autonomously while i did other work this is like a dev + tester rolled into one but without the back and forth i didn’t give it prompts i gave it a goal and that’s just one thing it can do it’s more like assigning work to a teammate not chatting with a bot we can now finally hand off part of our own work and products to AI without being nervous about the outcome you can try it here:

The SamurAI

40,030 次观看 • 9 个月前

This is wild. In just 25 seconds, Claude 3.5 Sonnet coded a fully functional Mancala web app for me 🕹️ I only provided ONE screenshot of the game's instructions. It did the rest: - Coded the entire game - Previewed it so I could test - Provided rules of play

This is wild. In just 25 seconds, Claude 3.5 Sonnet coded a fully functional Mancala web app for me 🕹️ I only provided ONE screenshot of the game's instructions. It did the rest: - Coded the entire game - Previewed it so I could test - Provided rules of play

Allie K. Miller

255,802 次观看 • 2 年前

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

The new Screenshot to Code from Vercel v0 is insane. I just took a screenshot of a pricing table and it was converted into code using AI in seconds! It even outputs the code and allows you to modify any specific parts.

Alvaro Cintas

378,005 次观看 • 2 年前

Just spent 20 minutes with v13.2.2 and I’m still trying to comprehend with what I just experienced. I took it to the tightest street I knew. Never in a million years did I think an autonomous car could get itself out of this situation. But it did 🤯 Tesla ai team solved it.

Just spent 20 minutes with v13.2.2 and I’m still trying to comprehend with what I just experienced. I took it to the tightest street I knew. Never in a million years did I think an autonomous car could get itself out of this situation. But it did 🤯 Tesla ai team solved it.

Pete Balls to the wall FSD 🤖🚕

45,059 次观看 • 1 年前

$I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)$

I just compared Claude Code vs Codex vs Cursor CLI The task was to build a Next.js app with Tailwind 4 and shadcn components to collect customer feedback and showcase it with a widget. I gave all three the same prompt and let them go for 30 minutes to see what they came up with. Claude Code with Opus 4.1 Even though I told it to set up the app in the existing project folder, it tried to create a directory for it. After I interrupted and told it not to do that, it built a demo form and landing page with no errors. I had to ask it to make the demo interactive so users could submit a testimonial and preview it. The landing page looked like AI and was pretty basic, but it worked and it was done in a fraction of the time of the others. Total tokens used: 33k Codex with GPT-5 At the end of the 30 minutes I just could not get Codex to produce a working app. It got stuck in a loop of not being able to set up Tailwind 4 and despite many, MANY, attempts, I ended up with a "failed to compile" error. Total tokens used: 102k Cursor Agent with GPT-5 This was the slowest agent by far and a couple of times I actually thought it got stuck in a loop and was close to Ctrl+C'ing to cancel it. The TUI is really nice though, especially how it shows diffs and it did eventually build a working app (after one or two slight errors that needed fixing) The demo was interactive and it had a very minimal design that looked bare but also a lot less like an "AI generated" app than the Opus 4.1 design. It also wasn't too chatty and just did what it needed to do! Code quality was on a par with Opus 4.1, but it did use 5.5x as many tokens to get there. Still cheaper than Opus on a direct comparison but not when you factor in a Claude Code Max subscription. Total tokens: 188k I'll be able to do a proper comparison and record some videos when I'm back from holiday but for now, Opus is still the more capable model out of the box and Claude Code is the more complete CLI product. It will be interesting to see how Cursor evolve their CLI though with commands and subagents because I think with GPT-5 they have a real shot at providing competition for Claude Code if they can optimise output to get similar quality with less tokens. Jump to 0:40 in the video to see the two apps. Which do you think is which? ;)

Ian Nuttall

194,949 次观看 • 11 个月前

Literally stole $12M worth of app ideas in minutes by just sending a few prompts from my phone I doubted it too, i don't blame you but AI is undeniable I did not want to admit that “ I wasted years learning code” all for a clanker to do it in 45 minutes So i’m done coping, and you should too I built 5 apps at the same time with just a few prompts it’s a blessing really, you can now fail faster. Master distribution and suddenly you're app is making $20k/mo

Literally stole $12M worth of app ideas in minutes by just sending a few prompts from my phone I doubted it too, i don't blame you but AI is undeniable I did not want to admit that “ I wasted years learning code” all for a clanker to do it in 45 minutes So i’m done coping, and you should too I built 5 apps at the same time with just a few prompts it’s a blessing really, you can now fail faster. Master distribution and suddenly you're app is making $20k/mo

Jah Jiren

27,965 次观看 • 6 个月前

🚀 OMG Windsurf’s newest App Deploys feature is awesome! I vibecoded a Pomodoro app (got the prompt from and deployed it using App Deploys... in just 4 minutes ⚡🤯

🚀 OMG Windsurf’s newest App Deploys feature is awesome! I vibecoded a Pomodoro app (got the prompt from and deployed it using App Deploys... in just 4 minutes ⚡🤯

fatih kadir akın

36,772 次观看 • 1 年前

I just designed a full food recipe app with dishes from all over the world… in under 10 minutes using Grok Build with the new Composer 2.5 model And the entire process was basically just 3 simple steps: → Gave the idea I had in my mind and asked it to plan everything → Told it to execute the plan → Made a few layout adjustments …and done This honestly feels like a cheat code for app development.... It even perfectly added the ingredient quantity adjustments and allergen ingredients to avoid check list The speed at which “Grok Build” can go from idea → design → launch now is absolutely insane

I just designed a full food recipe app with dishes from all over the world… in under 10 minutes using Grok Build with the new Composer 2.5 model And the entire process was basically just 3 simple steps: → Gave the idea I had in my mind and asked it to plan everything → Told it to execute the plan → Made a few layout adjustments …and done This honestly feels like a cheat code for app development.... It even perfectly added the ingredient quantity adjustments and allergen ingredients to avoid check list The speed at which “Grok Build” can go from idea → design → launch now is absolutely insane

X Freeze

13,066 次观看 • 1 个月前

I used AI to predict the correct score of a football game and it actually WORKED 😂. Here's how I did it.

I used AI to predict the correct score of a football game and it actually WORKED 😂. Here's how I did it.

Design Chief Priest

143,285 次观看 • 2 年前

another cal ai copycat just did 7.4M views from a single video it's a faceless slideshow of Pinterest images and this is not a cal ai thing, the same format works for almost any app, you just apply it to your niche so reverse engineer it back into your own app, the viral part is already proven

another cal ai copycat just did 7.4M views from a single video it's a faceless slideshow of Pinterest images and this is not a cal ai thing, the same format works for almost any app, you just apply it to your niche so reverse engineer it back into your own app, the viral part is already proven

Roman Khaves

53,073 次观看 • 24 天前

I asked o1 to help me code the wii menu it built a react app that renders in chatgpt canvas I fed it a screenshot and it one-shotted the basic layout—even the striped background—then I kept on prompting to add animations, etc

I asked o1 to help me code the wii menu it built a react app that renders in chatgpt canvas I fed it a screenshot and it one-shotted the basic layout—even the striped background—then I kept on prompting to add animations, etc

edwin

139,305 次观看 • 1 年前

This is insane Just built a fully working AI Room Designer in minutes, no coding, no API keys, just chatting with OnSpace AI. I use Nano Banana Pro for generation and handles UI, logic, and integration automatically. Not a demo. A real app: • No API setup required – Just told OnSpace to use Nano Banana Pro for content generation and it worked instantly • Full app, not a prototype – Complete UI, logic, and AI integration handled automatically • Actually works – Nails my tone every single time The whole thing came together through conversation. No design work. No wrestling with code. Just described the app and OnSpace made it real. This is what building with AI should feel like. Check my app link in the thread and try it yourself

This is insane Just built a fully working AI Room Designer in minutes, no coding, no API keys, just chatting with OnSpace AI. I use Nano Banana Pro for generation and handles UI, logic, and integration automatically. Not a demo. A real app: • No API setup required – Just told OnSpace to use Nano Banana Pro for content generation and it worked instantly • Full app, not a prototype – Complete UI, logic, and AI integration handled automatically • Actually works – Nails my tone every single time The whole thing came together through conversation. No design work. No wrestling with code. Just described the app and OnSpace made it real. This is what building with AI should feel like. Check my app link in the thread and try it yourself

AI Frontliner

70,013 次观看 • 7 个月前

Hacking the #EU #AgeVerification app in under 2 minutes. During setup, the app asks you to create a PIN. After entry, the app encrypts it and saves it in the shared_prefs directory. 1. It shouldn't be encrypted at all - that's a really poor design. 2. It's not cryptographically tied to the vault which contains the identity data. So, an attacker can simply remove the PinEnc/PinIV values from the shared_prefs file and restart the app. After choosing a different PIN, the app presents credentials created under the old profile and let's the attacker present them as valid. Other issues: 1. Rate limiting is an incrementing number in the same config file. Just reset it to 0 and keep trying. 2. "UseBiometricAuth" is a boolean, also in the same file. Set it to false and it just skips that step. Seriously Ursula von der Leyen - this product will be the catalyst for an enormous breach at some point. It's just a matter of time.

Paul Moore - Security Consultant 

3,395,866 次观看 • 2 个月前

I just vibe coded an app powered by an n8n agent, using the . The app will help me do research and prep for podcasts that I produce. Here's how the app works: - I type in the episode topic or topics - The App connects with my n8n agent that researches the topic, relevant news, and what people are saying about it - It also finds relevant links, and tweets - It sends the script / outline email to the team - And then it shows me what it did on the app

I just vibe coded an app powered by an n8n agent, using the . The app will help me do research and prep for podcasts that I produce. Here's how the app works: - I type in the episode topic or topics - The App connects with my n8n agent that researches the topic, relevant news, and what people are saying about it - It also finds relevant links, and tweets - It sends the script / outline email to the team - And then it shows me what it did on the app

Emily Lambert

57,603 次观看 • 1 年前

I just made an AI trading bot that executes Polymarket trades for me while I sleep! 📈 All it took was the new Bullpen CLI and a simple conversation with Claude Code ✏️ Here's exactly how I did it ⬇️

I just made an AI trading bot that executes Polymarket trades for me while I sleep! 📈 All it took was the new Bullpen CLI and a simple conversation with Claude Code ✏️ Here's exactly how I did it ⬇️

ItsRagnar

14,824 次观看 • 3 个月前

“I asked Allah to give me xyz but he didn’t give it to me and now I’m frustrated and sad” Did you ever think, my dear brother or sister, that Allah did not give you what or who you wished for, because He knew that if He did give it to you, it would destroy you? The money The person The job The house The car The holiday The opportunity The victory Whatever it was that you hoped and begged and worked and prayed for Think of a child who wants to pick something off the floor and put it in its mouth. The parent would take it away, no? Then the child would cry and scream “but I want it, I want it, I want it”, not knowing that the parent did not give the child what it wanted because if the parent did, it would harm the child As Allah says in the Quran, meaning, “But perhaps you hate a thing and it is good for you; and perhaps you love a thing and it is bad for you” (excerpt 2:216) (I’m not comparing Allah to His creation [I.e. a parent], it’s just an example to help frame the point I’m making more clearly)

“I asked Allah to give me xyz but he didn’t give it to me and now I’m frustrated and sad” Did you ever think, my dear brother or sister, that Allah did not give you what or who you wished for, because He knew that if He did give it to you, it would destroy you? The money The person The job The house The car The holiday The opportunity The victory Whatever it was that you hoped and begged and worked and prayed for Think of a child who wants to pick something off the floor and put it in its mouth. The parent would take it away, no? Then the child would cry and scream “but I want it, I want it, I want it”, not knowing that the parent did not give the child what it wanted because if the parent did, it would harm the child As Allah says in the Quran, meaning, “But perhaps you hate a thing and it is good for you; and perhaps you love a thing and it is bad for you” (excerpt 2:216) (I’m not comparing Allah to His creation [I.e. a parent], it’s just an example to help frame the point I’m making more clearly)

Xavier

49,373 次观看 • 4 个月前

There is fintech mobile app that allows one to send money to one or multiple people without the need to ask for their account details. You just send the beneficiary code and and cash it out on the App. The App is called “CHARITY AFRICA”, it makes give away much more easier, the founder have solved a major problem for Nigerians. Download the App now and deop screenshot in the comment section. I will be sending 5k( 50 codes) to 50 lucky winners! Then you can cash it on the APP.

There is fintech mobile app that allows one to send money to one or multiple people without the need to ask for their account details. You just send the beneficiary code and and cash it out on the App. The App is called “CHARITY AFRICA”, it makes give away much more easier, the founder have solved a major problem for Nigerians. Download the App now and deop screenshot in the comment section. I will be sending 5k( 50 codes) to 50 lucky winners! Then you can cash it on the APP.

Chude

14,024 次观看 • 6 个月前