Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Just combined OpenAI o1 and Cursor Composer to create an iOS app in under 10 mins! o1 mini kicks off the project (o1 was taking too long to think), then switch to o1 to finish off the details. And boom—full Weather app for iOS with animations, in under 10...

ammaar's profile picture

Ammaar Reshi

103,452 subscribers

925,087 görüntüleme • 2 yıl önce •via X (Twitter)

EğitimBilim & Teknoloji
LIVE

Anya Rossi• Live Now

Private livecam show

10 Yorum

Ryan Morrison profil fotoğrafı
Ryan Morrison2 yıl önce

@OpenAI I don't have access to o1 in the API yet but I used it to build a game in Python, then refined it in Cursor with Sonnet 3.5.

Ammaar Reshi profil fotoğrafı
Ammaar Reshi2 yıl önce

@OpenAI My man is about to recreate Age of Empires in a weekend

Reid Southen profil fotoğrafı
Reid Southen2 yıl önce

@OpenAI "Look guys, it can make an app that there are a million versions of already and that the model absolutely has in the training data!" 🤯

🐧 lalo adrian morales 𝕏 profil fotoğrafı
🐧 lalo adrian morales 𝕏2 yıl önce

@OpenAI did you have to add the o1-preview model to cursor settings ?

Ammaar Reshi profil fotoğrafı
Ammaar Reshi2 yıl önce

@OpenAI Yes! My cursor config looked like this

Pietro Schirano profil fotoğrafı
Pietro Schirano2 yıl önce

@OpenAI So good!!

Ammaar Reshi profil fotoğrafı
Ammaar Reshi2 yıl önce

@OpenAI Thanks brother!!

John Robert Martinez profil fotoğrafı
John Robert Martinez2 yıl önce

@OpenAI man, this is the future. Not AI doing all the work, but US leveraging AI to increment efficiency by the 1000s% - AI won’t replace people, people who don’t use AI will be replaced.

Bye X, now on Bsky or Threads, Oliver Sommermann profil fotoğrafı
Bye X, now on Bsky or Threads, Oliver Sommermann2 yıl önce

@OpenAI Can’t wait for all those weather apps to come out.

Ammaar Reshi profil fotoğrafı
Ammaar Reshi2 yıl önce

@OpenAI You’ll never need to wonder if you need a jacket or not again

Benzer Videolar

Just asked OpenAI o1 to recreate Marques Brownlee's Panels app for iOS using the Unsplash API and it did it all in under 10 minutes and in one shot! 🔥 Here's the entire workflow making your own wallpaper app from start to finish. Video sped up!
0:59

Just asked OpenAI o1 to recreate Marques Brownlee's Panels app for iOS using the Unsplash API and it did it all in under 10 minutes and in one shot! 🔥 Here's the entire workflow making your own wallpaper app from start to finish. Video sped up!

Ammaar Reshi

481,583 görüntüleme • 2 yıl önce

watch me make an app start to finish in 60 minutes with o1 and Cursor:
28:40

watch me make an app start to finish in 60 minutes with o1 and Cursor:

Dan Shipper 📧

239,469 görüntüleme • 2 yıl önce

🔥 💻 🎥 How to provide o1 Pro with your FULL CODEBASE through the ChatGPT Cursor connection yesterday I recorded a video connecting o1 Pro to Cursor through the ChatGPT Desktop app more than one person commented on how limiting it is for o1 Pro to only have access to a single open file in Cursor here's a walkthrough of how you can provide o1 Pro with your FULL CODEBASE as context instead of just a single file: 1. Write a Python function that concatenates full codebase into a single snapshot in a .txt file (link in comment) 2. Open that "codebase_snapshot.txt" in a separate Cursor pane 3. Go to the ChatGPT app and ask it what context it has access to through Cursor - should say it has two files with one of them being the codebase snapshot and boom there ya go. o1 Pro has access to everything in your codebase full walkthrough here 👇
6:14

🔥 💻 🎥 How to provide o1 Pro with your FULL CODEBASE through the ChatGPT Cursor connection yesterday I recorded a video connecting o1 Pro to Cursor through the ChatGPT Desktop app more than one person commented on how limiting it is for o1 Pro to only have access to a single open file in Cursor here's a walkthrough of how you can provide o1 Pro with your FULL CODEBASE as context instead of just a single file: 1. Write a Python function that concatenates full codebase into a single snapshot in a .txt file (link in comment) 2. Open that "codebase_snapshot.txt" in a separate Cursor pane 3. Go to the ChatGPT app and ask it what context it has access to through Cursor - should say it has two files with one of them being the codebase snapshot and boom there ya go. o1 Pro has access to everything in your codebase full walkthrough here 👇

Dan McAteer

99,787 görüntüleme • 1 yıl önce

Just used OpenAI o1 to create a 3D version of Snake in under a minute! 🐍 One-shot prompt, straight into Replit ⠕, and run.
0:43

Just used OpenAI o1 to create a 3D version of Snake in under a minute! 🐍 One-shot prompt, straight into Replit ⠕, and run.

Ammaar Reshi

470,044 görüntüleme • 2 yıl önce

🔥 🤯 🎥 Damn the ability to use o1 BEAST mode with Cursor is AMAZING sad thing is I think we could have been doing this for the last week??? the Cursor app connection has been there for a few weeks now use this workflow: 1. in ChatGPT connect to Cursor and open the relevant file (ChatGPT can only see the open file, not the whole project for now, sadly) 2. state what you want to implement and ask o1 Pro for the *diff* only, in full 3. take the diff that o1 Pro provides and copy it into Cursor composer agent - ask for the diff to be implemented then you have the requested change. ime been working first try for most things really incredible, we're getting close to allowing people to build whatever's in their imagination with a little knowledge and the ability to communicate it
1:34

🔥 🤯 🎥 Damn the ability to use o1 BEAST mode with Cursor is AMAZING sad thing is I think we could have been doing this for the last week??? the Cursor app connection has been there for a few weeks now use this workflow: 1. in ChatGPT connect to Cursor and open the relevant file (ChatGPT can only see the open file, not the whole project for now, sadly) 2. state what you want to implement and ask o1 Pro for the *diff* only, in full 3. take the diff that o1 Pro provides and copy it into Cursor composer agent - ask for the diff to be implemented then you have the requested change. ime been working first try for most things really incredible, we're getting close to allowing people to build whatever's in their imagination with a little knowledge and the ability to communicate it

Dan McAteer

135,213 görüntüleme • 1 yıl önce

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:
3:07

OpenAI just announced API access to o1 (advanced reasoning model) yesterday. I'm delighted to announce today a new short course, Reasoning with o1, built with OpenAI, and taught by Colin Jarvis, Head of AI Solutions at OpenAI, to show you how to use this effectively! Unlike previous language models which generate output directly, o1 “thinks before it responds,” and generates many reasoning tokens before returning a more thoughtful and accurate response. It is great at complex reasoning -- including planning for agentic workflows, coding, and domain-specific reasoning in STEM fields like law. But how you should use it is quite different from other LLMs. I think o1 will be a game changer for many AI applications; and in this course, you'll learn how to use it effectively. In detail, you’ll: - Learn to recognize what tasks o1 is suited for, and when to use a smaller model, or combine o1 with a smaller model - Understand the new principles of prompting reasoning models: Be simple and direct; no explicit chain-of-thought required; use structure; show rather than tell - Implement multi-step orchestration in which o1 plans, and hands tasks over to gpt-4o-mini to execute specific steps; this illustrates a design pattern to optimize intelligence (accuracy) and cost - Use o1 for a coding task to build a new application, edit existing code, and test performance by running a coding competition between o1-mini and GPT 4o - Use o1 for image understanding and learn how it performs better with a "hierarchy of reasoning," in which it incurs the latency and cost upfront, preprocessing the image and indexing it with rich details so it can be used for Q&A later - Learn a technique called meta-prompting, in which you use o1 to improve your prompts. Using a customer support evaluation set, you'll iteratively use o1 to modify a prompt to improve performance You'll also learn about how OpenAI used reinforcement learning to produce a model that uses "test-time compute" to improve performance. I think you'll find this course enjoyable and valuable. Please sign up for it here:

Andrew Ng

358,249 görüntüleme • 1 yıl önce

o1-pro is probably the best model i've used for coding, hands down i gave it a pretty complicated codebase and asked it to refactor while referencing docs the difference between claude/gemini/o1 and o1 pro is night and day. first time in a while i've been this impressed. full comparison in the video + code.
7:33

o1-pro is probably the best model i've used for coding, hands down i gave it a pretty complicated codebase and asked it to refactor while referencing docs the difference between claude/gemini/o1 and o1 pro is night and day. first time in a while i've been this impressed. full comparison in the video + code.

Sully

255,736 görüntüleme • 1 yıl önce

ROUTE LLM - SUPER INTELLIGENCE IN THE MAKING RouteLLM combines the superpowers of o1-preview, Sonnet 3.5, Gemini Flash, o1-mini, 4o, and 4o-mini! Based on your query, it optimizes for latency, cost, and quality of the response. The cool thing about RouteLLM is it combines. - coding ability of Sonnet 3.5 - reasoning ability of o1-preview - hard-coding ability of o1-mini - 1M context of Gemini - speed of 4o-mini Similar to ensemble models that are very effective in classical ML, RouteLLM and similar models will be the most effective in the LLM ecosystem
1:01

ROUTE LLM - SUPER INTELLIGENCE IN THE MAKING RouteLLM combines the superpowers of o1-preview, Sonnet 3.5, Gemini Flash, o1-mini, 4o, and 4o-mini! Based on your query, it optimizes for latency, cost, and quality of the response. The cool thing about RouteLLM is it combines. - coding ability of Sonnet 3.5 - reasoning ability of o1-preview - hard-coding ability of o1-mini - 1M context of Gemini - speed of 4o-mini Similar to ensemble models that are very effective in classical ML, RouteLLM and similar models will be the most effective in the LLM ecosystem

Bindu Reddy

66,374 görüntüleme • 1 yıl önce

The wait is over. OpenAI just dropped o1, also known as Project Strawberry/Q* This is new level of AI that can "think" and "reason" before responding to you. 10 wild demos: 1. Coding Video Game from a prompt
2:00

The wait is over. OpenAI just dropped o1, also known as Project Strawberry/Q* This is new level of AI that can "think" and "reason" before responding to you. 10 wild demos: 1. Coding Video Game from a prompt

Min Choi

1,859,523 görüntüleme • 2 yıl önce

One effective way to balance cost and quality is to plan larger refactors with o1, and switch to a cheaper model to execute the changes. Live now in our VSCode extension:
0:47

One effective way to balance cost and quality is to plan larger refactors with o1, and switch to a cheaper model to execute the changes. Live now in our VSCode extension:

Adam Hofmann

24,665 görüntüleme • 2 yıl önce

OpenAI’s newest model is finally here: o1. o1 represents an entirely new class of models designed to reason or “think through” complex problems— and it's already making huge leaps in domains like math and coding. For the very first episode of YC Decoded, we took a look inside.
7:06

OpenAI’s newest model is finally here: o1. o1 represents an entirely new class of models designed to reason or “think through” complex problems— and it's already making huge leaps in domains like math and coding. For the very first episode of YC Decoded, we took a look inside.

Y Combinator

92,759 görüntüleme • 1 yıl önce

Qwen QwQ-32B can reason as good as OpenAI o1 mini (in most of the cases). Best part? You can run this locally with an UI in less than 10 lines of Python Code (100% free and without internet).
0:31

Qwen QwQ-32B can reason as good as OpenAI o1 mini (in most of the cases). Best part? You can run this locally with an UI in less than 10 lines of Python Code (100% free and without internet).

Shubham Saboo

60,218 görüntüleme • 1 yıl önce

🚨 PROMPT TO MOBILE APP IN 10 MINUTES Use top models like Opus 4.8. GPT 5.5 and Gemini 3.5 to create iOS and Android apps With one prompt create an entire app - add user auth - backend - create iOS and Android apps - build and deploy to app and play store All from one prompt in 10 minutes. FREE APP HOSTING with ChatLLM subscription
0:35

🚨 PROMPT TO MOBILE APP IN 10 MINUTES Use top models like Opus 4.8. GPT 5.5 and Gemini 3.5 to create iOS and Android apps With one prompt create an entire app - add user auth - backend - create iOS and Android apps - build and deploy to app and play store All from one prompt in 10 minutes. FREE APP HOSTING with ChatLLM subscription

Abacus.AI

15,596,079 görüntüleme • 3 ay önce

Greg Brockman seems to confirm what I’ve suspected for a long time: o1, o3, and GPT-5 Instant/Thinking were all built on the GPT-4o base model People found this hard to believe when I said this 2 years ago, but internally, the original o1 was called GPT-4o with reasoning
0:25

Greg Brockman seems to confirm what I’ve suspected for a long time: o1, o3, and GPT-5 Instant/Thinking were all built on the GPT-4o base model People found this hard to believe when I said this 2 years ago, but internally, the original o1 was called GPT-4o with reasoning

Flowers ☾

141,129 görüntüleme • 28 gün önce

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
0:21

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 görüntüleme • 1 yıl önce