Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Fascinating. GPT 4 Vision coupled with Iteration X automatically recommends improvements on Y Combinator's live website and adds comments as pins, directly on the html elements.

mehdidjabri's profile picture

Mehdi Djabri

1,948 subscribers

24,049 görüntüleme • 3 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

11 Yorum

Mehdi Djabri profil fotoğrafı
Mehdi Djabri3 yıl önce

@ycombinator With a screenshot + the page code GPT4V is able to associate each issue to the right XPath @gdb @OfficialLoganK

Safari Web Extensions profil fotoğrafı
Safari Web Extensions1 yıl önce

Discover the top Safari web extensions to boost productivity, enhance workflow, and customize your browsing experience on Mac, iOS, and iPadOS.

Produkthelt profil fotoğrafı
Produkthelt3 yıl önce

@iteration_x @ycombinator The action bar 🖤🖤🖤

Pratham profil fotoğrafı
Pratham3 yıl önce

@iteration_x @ycombinator This sounds interesting!

Poonam Soni profil fotoğrafı
Poonam Soni3 yıl önce

@iteration_x @ycombinator This is impressive.

Jan Mraz profil fotoğrafı
Jan Mraz3 yıl önce

@iteration_x @ycombinator 🚀🚀

Artem Gladkikh profil fotoğrafı
Artem Gladkikh2 yıl önce

@iteration_x @ycombinator Outstanding quality in this product

Mehdi Djabri profil fotoğrafı
Mehdi Djabri2 yıl önce

@iteration_x @ycombinator thank you Artem!

Csaba Kissi profil fotoğrafı
Csaba Kissi3 yıl önce

@iteration_x @ycombinator This is outstanding. I like Hackernews, and this takes it to another level!

Madni Aghadi profil fotoğrafı
Madni Aghadi3 yıl önce

@iteration_x @ycombinator Wow... that’s amazing!

Devxhub profil fotoğrafı
Devxhub2 yıl önce

@iteration_x @ycombinator Incredible collaboration! 🤖💻 At #DEVxHUB, we excel in integrating cutting-edge technologies. If you're exploring similar innovations or need assistance with web development, we've got you covered! 🌐 #TechInnovation #WebDevelopment

Benzer Videolar

BREAKING: ChatGPT GPT-4o was just announce by OpenAI. It improves on vision, audio and text. The ease of use is incredibly enhanced. It makes interaction with the GPT much more natural, especially with voice. GPT-4o reasons across voice, text and vision. GPT-4 wil be available to everyone.
0:42

BREAKING: ChatGPT GPT-4o was just announce by OpenAI. It improves on vision, audio and text. The ease of use is incredibly enhanced. It makes interaction with the GPT much more natural, especially with voice. GPT-4o reasons across voice, text and vision. GPT-4 wil be available to everyone.

Ed Krassenstein

21,605 görüntüleme • 2 yıl önce

From image to live website using GPT-4 vision and Replit ⠕ in less than a minute. Things are about to get so interesting. 🔥
0:33

From image to live website using GPT-4 vision and Replit ⠕ in less than a minute. Things are about to get so interesting. 🔥

Pietro Schirano

1,217,349 görüntüleme • 3 yıl önce

For the last couple months, our team has been working hard on a few paradigm-changing features for HTML Canvas. One of them is the ability to have HTML elements in a canvas. Here's a ThreeJS demo with a live HTML texture.
0:43

For the last couple months, our team has been working hard on a few paradigm-changing features for HTML Canvas. One of them is the ability to have HTML elements in a canvas. Here's a ThreeJS demo with a live HTML texture.

Fernando Serboncini

682,632 görüntüleme • 2 yıl önce

running gpt-oss:20b on ollama with Turbo and web search 🏎️ 💨 very happy with how the web search turned out :) and ofcourse – more improvements on the way!
0:28

running gpt-oss:20b on ollama with Turbo and web search 🏎️ 💨 very happy with how the web search turned out :) and ofcourse – more improvements on the way!

parth

54,124 görüntüleme • 1 yıl önce

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.
0:55

My favorite way of interacting with Claude Code is to have it generate static HTML files as outputs (reports, explorations, code structure, mockups etc.) I wanted to iterate on the file by commenting in browser and having Claude update the output live. So, I built this Claude Skill👇 How it works: - Install Claude Code skill (ask it to clone repo) - Build an HTML page for anything (e.g. research coding agents and generate HTML report) - Ask it to make the page interactive That's it. CC will launch a localhost server and allow you to then leave comments on the page itself and once it updates, will give you a tour of changes. It's like Google Docs kind of comments/iteration but for HTML pages.

Paras Chopra

216,705 görüntüleme • 5 ay önce

i recreated this with GPT 5.6 Sol & it costed me ~$5 only & 2 prompts >GPT 5.6 Sol Ultra as the main agent, admin & orchestrator >GPT 5.6 Luna Max as sub-agents >used the Codex app >used about 20% of my weekly limit on $100 plan ($100/4 * 20%) some bugs, and improvements would take another prompt but pretty good for $5!
1:00

i recreated this with GPT 5.6 Sol & it costed me ~$5 only & 2 prompts >GPT 5.6 Sol Ultra as the main agent, admin & orchestrator >GPT 5.6 Luna Max as sub-agents >used the Codex app >used about 20% of my weekly limit on $100 plan ($100/4 * 20%) some bugs, and improvements would take another prompt but pretty good for $5!

anul agarwal

16,542 görüntüleme • 2 ay önce

🚨 BREAKING: GPT-4 image recognition already has a new competitor. Open-sourced and completely free to use. Introducing LLaVA: Large Language and Vision Assistant. I compared the viral parking space photo on GPT-4 Vision to LLaVa, and it worked flawlessly (see video).
0:21

🚨 BREAKING: GPT-4 image recognition already has a new competitor. Open-sourced and completely free to use. Introducing LLaVA: Large Language and Vision Assistant. I compared the viral parking space photo on GPT-4 Vision to LLaVa, and it worked flawlessly (see video).

Rowan Cheung

681,670 görüntüleme • 3 yıl önce

Laika AI is officially live on the GPT Store! Access On-chain Information, Unparalleled DeFi insights, top-tier NFT monitoring, and smart contract security with our state-of-the-art AI tools directly at ChatGPT. Access our RAG directly from the GPT Store, featuring the most advanced and accurate data layers available. Explore now: $LKI
0:45

Laika AI is officially live on the GPT Store! Access On-chain Information, Unparalleled DeFi insights, top-tier NFT monitoring, and smart contract security with our state-of-the-art AI tools directly at ChatGPT. Access our RAG directly from the GPT Store, featuring the most advanced and accurate data layers available. Explore now: $LKI

Laika AI

111,178 görüntüleme • 2 yıl önce

WebcamGPT: Use the new GPT-4 Vision API to actively recognize what's happening in real-time.... This is a live web demo. Try it yourself, link in comments.
0:45

WebcamGPT: Use the new GPT-4 Vision API to actively recognize what's happening in real-time.... This is a live web demo. Try it yourself, link in comments.

Benjamin De Kraker

530,334 görüntüleme • 3 yıl önce

Available now in Visual Studio Code Insiders, you can select and add elements directly to Chat! After opening any locally-hosted site via the built-in Simple Browser, click "Start" on the toolbar and select the element you want. This will attach a screenshot of the selected element, as well as the HTML and CSS of that element.
0:26

Available now in Visual Studio Code Insiders, you can select and add elements directly to Chat! After opening any locally-hosted site via the built-in Simple Browser, click "Start" on the toolbar and select the element you want. This will attach a screenshot of the selected element, as well as the HTML and CSS of that element.

Visual Studio Code

75,563 görüntüleme • 1 yıl önce

Got tired of boring websites. Built a way to drop 3D agents directly onto standard HTML elements with zero complex math.
0:47

Got tired of boring websites. Built a way to drop 3D agents directly onto standard HTML elements with zero complex math.

nich

242,674 görüntüleme • 5 ay önce

Steve Jobs is now critiquing my designs directly in Figma! I've just made one of my biggest dreams come true, thanks to GPT-4 Vision + . ✨ My Figma window is streamed to GPT, which then provides feedback on the fly. Like on these new design for EverArt
1:12

Steve Jobs is now critiquing my designs directly in Figma! I've just made one of my biggest dreams come true, thanks to GPT-4 Vision + . ✨ My Figma window is streamed to GPT, which then provides feedback on the fly. Like on these new design for EverArt

Pietro Schirano

881,446 görüntüleme • 2 yıl önce

Introducing the Box HTML editor. Create, edit, preview, and collaborate on HTML files directly in Box, no additional downloads, no external tools, no re-uploads. Your HTML files can now operate in the same governed space as the rest of your enterprise content, with seamless Box AI access built in from the start.
1:32

Introducing the Box HTML editor. Create, edit, preview, and collaborate on HTML files directly in Box, no additional downloads, no external tools, no re-uploads. Your HTML files can now operate in the same governed space as the rest of your enterprise content, with seamless Box AI access built in from the start.

Box

3,405,237 görüntüleme • 4 ay önce

Tesla has redesigned its website, putting the live FSD (Supervised) mile counter directly on the homepage with FSD videos from Tesla owners.
0:45

Tesla has redesigned its website, putting the live FSD (Supervised) mile counter directly on the homepage with FSD videos from Tesla owners.

Sawyer Merritt

165,484 görüntüleme • 5 ay önce

armchair websites: gpt-live ⨉ tldraw a quick hack before I fly out to new york for the week. edit a website on your ipad with voice and pencil.
1:22

armchair websites: gpt-live ⨉ tldraw a quick hack before I fly out to new york for the week. edit a website on your ipad with voice and pencil.

sunil pai

37,638 görüntüleme • 1 ay önce

I built a GPT-4 PaulGrahamAI to give you startup advice! No sign up required to use it! The chatbot uses the content on Paul Graham's website plus GPT-4 to provide answers with the sources. Built using
0:37

I built a GPT-4 PaulGrahamAI to give you startup advice! No sign up required to use it! The chatbot uses the content on Paul Graham's website plus GPT-4 to provide answers with the sources. Built using

Yasser

87,824 görüntüleme • 3 yıl önce

K folks you gotta try this! GPT-4 Vision + tldraw new make-real button! Recorded a live blind reaction 🤯 Recreates your doodles into a live Tailwind CSS designs like on the fly!
5:57

K folks you gotta try this! GPT-4 Vision + tldraw new make-real button! Recorded a live blind reaction 🤯 Recreates your doodles into a live Tailwind CSS designs like on the fly!

Alex Volkov

196,464 görüntüleme • 2 yıl önce

Working on some cold start improvements for the New X Android (already live for alpha users)
0:36

Working on some cold start improvements for the New X Android (already live for alpha users)

Andrei Belous

78,741 görüntüleme • 29 gün önce

implementing production ready ui with figma + gpt-4 vision 🤯
2:12

implementing production ready ui with figma + gpt-4 vision 🤯

ben hylak

54,592 görüntüleme • 3 yıl önce