Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Automated NBA match commentary using OpenAI vision and TTS (with code!) Everyone is bragging about projects that generate automatic video commentary, but no one is showing the code. I did it while waiting for the plane. code:

SkalskiP

44,940 subscribers

188,555 просмотров • 2 лет назад •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля SkalskiP

SkalskiP2 лет назад

What is cool: Vision API noticed that it was a shot to win the game AND THE SERIES.

Фото профиля Alex Ker 🔭

Alex Ker 🔭2 лет назад

@NBA @OpenAI Nice remake! Original post and and my code

Фото профиля Jackson Geller

Jackson Geller2 лет назад

@NBA @OpenAI You can mix the crowd noise back in with Demucs! My narration didn't come out as well, but here's an example. Thanks for sharing.

Фото профиля SkalskiP

SkalskiP2 лет назад

@NBA @OpenAI Awesome idea!

Фото профиля David

David2 лет назад

@NBA @OpenAI Why does it feel like its rapping 😅😅 great work.

Фото профиля SkalskiP

SkalskiP2 лет назад

@NBA @OpenAI Not sure man! Hahaha we can make it rap 100% with a little bit of prompting haha

Фото профиля ShashanK🤺

ShashanK🤺2 лет назад

@NBA @OpenAI v cool. small nitpicking. the words "as confetti flies..." came at 0:22, about ~5-8 seconds earlier than when the confetti actually appears. why is that? coz of batching?

Фото профиля SkalskiP

SkalskiP2 лет назад

@NBA @OpenAI I uploaded all the images with the single API call. Not sure how it is processed. Maybe GPT have the access to all images at once.

Фото профиля Vijay

Vijay2 лет назад

@NBA @OpenAI Funny thing is it's literally a tutorial from OpenAI Cookbook.

Фото профиля SkalskiP

SkalskiP2 лет назад

@NBA @OpenAI Please gimme link ;)

Похожие видео

Building 3D worlds in a collaborative way assisted by an AI generating code for you! In this demo, I'm using Microsoft Teams AI and Azure #OpenAI to generate Babylon.js code in a meeting, while using #TeamsToolkit for the developer experience. Is it the future of 3D design?

Building 3D worlds in a collaborative way assisted by an AI generating code for you! In this demo, I'm using Microsoft Teams AI and Azure #OpenAI to generate Babylon.js code in a meeting, while using #TeamsToolkit for the developer experience. Is it the future of 3D design?

David Rousset

15,881 просмотров • 2 лет назад

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

I built a multimodal AI Coding Agent team with multi-agents. It has 3 AI agents working together as a team to generate and execute the code: 1. Coding Agent using o-3 mini 2. Vision Agent using Gemini 3. Code Execution Agent using o-3 mini and E2B 100% Opensource Code.

Shubham Saboo

42,261 просмотров • 1 год назад

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Reviewing AI-generated code is the new bottleneck. Writing code was slow before. Now, in a few minutes, you can generate virtually unlimited lines of code using AI. But developers are now spending 70% of their time checking that code. That's the new bottleneck. I've been using Cline, and they have a feature that actually helps with this: You can click a button and have Cline generate an inline explanation for every single line of AI-generated code. Take a look at the attached video. What it does: 1. You can read the code and the explanation together 2. You don't lose context while reviewing code 3. You understand the "why" behind each change And here is the best part: It works on any git diff. You can use it to review PRs, understand commits from other people, or catch up on a codebase you haven't touched in a while.

Santiago

64,392 просмотров • 6 месяцев назад

I built an AI data visualization Agent. The AI Agent can automatically generate the code and visualize the data using code interpreter sandbox. 100% Opensource Code with step-by-step tutorial.

I built an AI data visualization Agent. The AI Agent can automatically generate the code and visualize the data using code interpreter sandbox. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

67,845 просмотров • 1 год назад

AI Coding Agent for Hardware Optimized Code Diana AI hardware is still constrained by software. However, with reasoning models like Deepseek R1 or OpenAI o1 and o3, AI could generate hardware-optimized code that rivals—or surpasses—human CUDA code.

AI Coding Agent for Hardware Optimized Code Diana AI hardware is still constrained by software. However, with reasoning models like Deepseek R1 or OpenAI o1 and o3, AI could generate hardware-optimized code that rivals—or surpasses—human CUDA code.

Y Combinator

60,089 просмотров • 1 год назад

Since everyone is talking about RL Environments and GRPO now but no one knows how it works we thought it would be cool to make an explainer video + code you can run: This is an example of using GRPO to train Qwen 2.5 to play 2048 (code in thread) 🧵:

Since everyone is talking about RL Environments and GRPO now but no one knows how it works we thought it would be cool to make an explainer video + code you can run: This is an example of using GRPO to train Qwen 2.5 to play 2048 (code in thread) 🧵:

Jay

151,533 просмотров • 9 месяцев назад

One of the tools that I really like and use for writing code is postfix completion in #IntelliJ. It is not very popular, but once you start using it, you can't live without it.

One of the tools that I really like and use for writing code is postfix completion in #IntelliJ. It is not very popular, but once you start using it, you can't live without it.

Anton Arhipov

35,310 просмотров • 8 месяцев назад

Browserbase just launched Director AI. It's an AI tool that can automate any web task using simple English prompts and generate repeatable automation code in one step. Like OpenAI Operator but free, with no coding required. +

Browserbase just launched Director AI. It's an AI tool that can automate any web task using simple English prompts and generate repeatable automation code in one step. Like OpenAI Operator but free, with no coding required. +

Shubham Saboo

21,166 просмотров • 11 месяцев назад

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Introducing Claude Code Templates 🚀 I originally built this to streamline how I set up new projects with Claude Code…just a small tool to make my own workflow smoother. No install, just run: npx claude-code-templates Right now, it configures Commands, Hooks, MCPs, and settings.json for JavaScript/TypeScript and Python projects. It made things so much easier for me that I decided to share it with the community. Open-source and open to ideas — feel free to contribute! Big thanks to the team at Anthropic and everyone behind Claude Code Community 🙌

Daniel San

28,410 просмотров • 11 месяцев назад

ChatGPT Vision can take in screenshots from Figma and generate code. Building with AI is getting wild.

ChatGPT Vision can take in screenshots from Figma and generate code. Building with AI is getting wild.

Mckay Wrigley

2,228,859 просмотров • 2 лет назад

Boris Cherny: "Claude Code is 100% written by Claude Code, Cowork is 100% written by Claude Code" across all of Anthropic, 90% of code is written by Claude lawyers, designers, finance people are building real things with Claude Code right now with no CS degree, no background, nothing the people who built the tool use the tool to build the tool think about what that means for everyone else the guide on everything Claude can actually do is in the article below

Boris Cherny: "Claude Code is 100% written by Claude Code, Cowork is 100% written by Claude Code" across all of Anthropic, 90% of code is written by Claude lawyers, designers, finance people are building real things with Claude Code right now with no CS degree, no background, nothing the people who built the tool use the tool to build the tool think about what that means for everyone else the guide on everything Claude can actually do is in the article below

Anatoli Kopadze

90,364 просмотров • 15 дней назад

One of the best ways to win your time back with GitHub Copilot is to have it generate Git commit messages for you. Everyone has their own style - share yours with Copilot using Custom Instructions and save yourself a ton of time.

One of the best ways to win your time back with GitHub Copilot is to have it generate Git commit messages for you. Everyone has their own style - share yours with Copilot using Custom Instructions and save yourself a ton of time.

Visual Studio Code

66,210 просмотров • 1 год назад

We've built a massive verification bottleneck: • 72% of developers use AI to generate code every day • 96% of them don't fully trust it Writing code is now free. All the work now is verifying that the code does what it's supposed to. According to a new State of Code Survey, almost half of the respondents believe the number one skill that will matter most in the coming years is "reviewing and validating AI-generated code for quality and security". Not prompt engineering or vibe-coding, but checking AI's work.

We've built a massive verification bottleneck: • 72% of developers use AI to generate code every day • 96% of them don't fully trust it Writing code is now free. All the work now is verifying that the code does what it's supposed to. According to a new State of Code Survey, almost half of the respondents believe the number one skill that will matter most in the coming years is "reviewing and validating AI-generated code for quality and security". Not prompt engineering or vibe-coding, but checking AI's work.

Santiago

16,299 просмотров • 4 месяцев назад

You all saw that OpenAI Super Bowl ad, right? Well, I recreated the exact same effect using ONLY OpenAI tools Code - o3-mini Video - Sora Try it here

You all saw that OpenAI Super Bowl ad, right? Well, I recreated the exact same effect using ONLY OpenAI tools Code - o3-mini Video - Sora Try it here

Mike Bespalov

412,005 просмотров • 1 год назад

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

Akshay 🚀

30,789 просмотров • 1 год назад

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Claude Code with Sonnet 4.5 is actually incredible I gave it a prompt for a super complex app, and it one shot the entire thing In this video I walk you through how to use Claude Code to build a prompt library app you can start using immediately (no coding experience required):

Alex Finn

40,858 просмотров • 8 месяцев назад

An interview I did with Carolyn Quinn on times_rad yesterday about the EHRC Code of Practice (again). One correction: I’m not the “author” of the Code, I worked on reviewing and assessing it as a Commissioner

An interview I did with Carolyn Quinn on times_rad yesterday about the EHRC Code of Practice (again). One correction: I’m not the “author” of the Code, I worked on reviewing and assessing it as a Commissioner

Akua Reindorf KC

10,311 просмотров • 4 месяцев назад

My friend Nuseir Yassin aka Nuseir Yassin just released this video. I will leave it here with no commentary. Ok, one piece of commentary. It’s wow. Not only is it incredibly produced and filmed, but the content itself is just really wow. Ok, I guess that’s commentary. I hope it helps you like it helped me.

My friend Nuseir Yassin aka Nuseir Yassin just released this video. I will leave it here with no commentary. Ok, one piece of commentary. It’s wow. Not only is it incredibly produced and filmed, but the content itself is just really wow. Ok, I guess that’s commentary. I hope it helps you like it helped me.

Hillel Fuld

63,816 просмотров • 2 лет назад

Claude Code with Opus 4.7 is the best vibe coding tool I've ever used The thing is there were several new features that change how you should be using it In this video I cover 7 secret updates the creator of Claude Code just revealed If you use Claude Code this is a must watch

Claude Code with Opus 4.7 is the best vibe coding tool I've ever used The thing is there were several new features that change how you should be using it In this video I cover 7 secret updates the creator of Claude Code just revealed If you use Claude Code this is a must watch

Alex Finn

36,415 просмотров • 1 месяц назад