Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

5. Visually understand images, plots, and code.

Lior Alexander

117,295 subscribers

371,163 views • 2 years ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 Comments

Lior⚡2 years ago

Today OpenAI released GPT-4o. It's the JARVIS we all dreamed of. The 5 most incredible examples so far:

Lior⚡2 years ago

1. Real time translation

Lior⚡2 years ago

2. Emotion and face detection

Lior⚡2 years ago

3. Code understanding/debugging via voice commands

Lior⚡2 years ago

4. Generate a wide range of emotion-based voices

Lior⚡2 years ago

GPT-4o (“o” for “omni”) is a step towards much more natural human-computer interaction. It will be available for free users and via the API. If you enjoyed this, check out to get a daily summary of breakthrough models, repos, and papers in AI. Read by 180,000+ engineers and researchers.

Lior⚡2 years ago

GPT-4o is now available on the web app and playground

Behrooz Azarkhalili2 years ago

@threadreaderapp please unroll it

Thread Reader App2 years ago

@AlphaSignalAI @b_azarkhalili Hello, please find the unroll here: Enjoy :) 🤖

FlyingMugen2 years ago

ChatGPT: Wait a minute! A moment ago you told me your colleague could only speak Italian, and suddenly here she is talking English! You lied! How can I trust you again?! 😂

Related Videos

2/5 While Clark generates with AI, you edit visually or in code using your favorite IDE like Cursor.

2/5 While Clark generates with AI, you edit visually or in code using your favorite IDE like Cursor.

Brad Menezes

22,977 views • 1 year ago

2. Caspa AI: An AI tool to create visually appealing images for marketing campaigns, websites, and social media: • Generate unique images • Realistic human models • Time and cost-effective

2. Caspa AI: An AI tool to create visually appealing images for marketing campaigns, websites, and social media: • Generate unique images • Realistic human models • Time and cost-effective

Zain Kahn

71,517 views • 3 years ago

5 FREE Tools for Web Developers - Claude code alternative - Full-stack hosting and free static site - React hooks with examples – Create images of code snippets - CSS animation snippets

5 FREE Tools for Web Developers - Claude code alternative - Full-stack hosting and free static site - React hooks with examples – Create images of code snippets - CSS animation snippets

Csaba Kissi

12,530 views • 1 year ago

Volta Juapong 30 Mins From Adome Bridge 2 Drone View 200 Acres 1 Acre (6 Plots) = 20,000.00gh 1/2 Acre (3 Plots ) = 10,000.00gh Indenture And Bar Code will be Given

Volta Juapong 30 Mins From Adome Bridge 2 Drone View 200 Acres 1 Acre (6 Plots) = 20,000.00gh 1/2 Acre (3 Plots ) = 10,000.00gh Indenture And Bar Code will be Given

OG The Builder 🇬🇭

22,163 views • 4 months ago

🚀 The next evolution of DreamFlow is here with a reimagined tri-surface experience. ✓ Build visually ✓ Edit code directly or with an agent ✓ Publish to app stores Start with a prompt, shape it visually, and refine it in code. And we’re just getting started.

🚀 The next evolution of DreamFlow is here with a reimagined tri-surface experience. ✓ Build visually ✓ Edit code directly or with an agent ✓ Publish to app stores Start with a prompt, shape it visually, and refine it in code. And we’re just getting started.

Dreamflow

33,793 views • 1 year ago

You can now design directly in your codebase. Select elements, modify them visually, and Cursor writes the code.

You can now design directly in your codebase. Select elements, modify them visually, and Cursor writes the code.

Cursor

6,093,086 views • 10 months ago

introducing GPT Paint. now you can prompt ChatGPT visually through edit marks, basic shapes, notes, and reference images. available now on Krea Image.

introducing GPT Paint. now you can prompt ChatGPT visually through edit marks, basic shapes, notes, and reference images. available now on Krea Image.

Krea

380,643 views • 1 year ago

An AI device helping visually impaired people understand their surroundings in real time

An AI device helping visually impaired people understand their surroundings in real time

Science girl

14,705 views • 6 months ago

🚀Introducing LLaVA-NeXT Interleave: Now AI can understand and reason with multiple images at once - This opens up multi-image scenarios like multi-frame videos, multi-view 3D, and multiple inter-leaved images. - An all round LMM that can understand videos, images, and 3D More⬇️

🚀Introducing LLaVA-NeXT Interleave: Now AI can understand and reason with multiple images at once - This opens up multi-image scenarios like multi-frame videos, multi-view 3D, and multiple inter-leaved images. - An all round LMM that can understand videos, images, and 3D More⬇️

Gradio

27,665 views • 2 years ago

🚀Excited to share that #Gemini 3 Flash can do code execution on images to zoom, count, and annotate visual inputs! The model can choose when to write code to: 🔍 Zoom & Inspect: Detect when details are too small and zoom-in. 🧮 Compute Visually: Run multi-step calculations using code (e.g., summing line items on a receipt). ✏️ Annotate: Draw arrows or bounding boxes to answer questions or show relationships between objects.

🚀Excited to share that #Gemini 3 Flash can do code execution on images to zoom, count, and annotate visual inputs! The model can choose when to write code to: 🔍 Zoom & Inspect: Detect when details are too small and zoom-in. 🧮 Compute Visually: Run multi-step calculations using code (e.g., summing line items on a receipt). ✏️ Annotate: Draw arrows or bounding boxes to answer questions or show relationships between objects.

Fei Xia

20,230 views • 10 months ago

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.

Multimodal Reasoning AI Agents are here with Gemini 2.0 Flash Thinking I built a multimodal AI agent that can reason and understand images using gemini flash reasoning LLM. 100% Opensource Code with step-by-step tutorial.

Shubham Saboo

36,596 views • 1 year ago

[1] Decktopus AI: @Decktopus Decktopus creates presentations that are both visually stunning and incredibly professional. Enhance your presentations with: • Automate Actions • Stock Images and Icons • Stunning Design Templates 🔗

[1] Decktopus AI: @Decktopus Decktopus creates presentations that are both visually stunning and incredibly professional. Enhance your presentations with: • Automate Actions • Stock Images and Icons • Stunning Design Templates 🔗

Abhishek

46,971 views • 3 years ago

This is insane. Anyone can build an AI app with no code in 5 minutes using Imagica. Plus, it's multimodal: feed it text, images, video, and 3D models 🤯

This is insane. Anyone can build an AI app with no code in 5 minutes using Imagica. Plus, it's multimodal: feed it text, images, video, and 3D models 🤯

Rowan Cheung

505,963 views • 3 years ago

Fun interactive science app ideas | Part 5 Built a periodic table app that visualizes atomic and molecular structures UI Design GPT Images 2 Code Gemini 3.1 Pro More demos ↓

Fun interactive science app ideas | Part 5 Built a periodic table app that visualizes atomic and molecular structures UI Design GPT Images 2 Code Gemini 3.1 Pro More demos ↓

Dilum Sanjaya

105,747 views • 4 months ago

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

StarVector is out on Hugging Face StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

AK

254,490 views • 1 year ago

🎁 5 Ember Sword Land Plots Giveaway! To celebrate the launch of the Ember Sword land sale, we’re giving away 5 land plots to 5 lucky winners! To enter: 👑 Like + RT this post 👑 Follow Immutable 👑 Enter below

🎁 5 Ember Sword Land Plots Giveaway! To celebrate the launch of the Ember Sword land sale, we’re giving away 5 land plots to 5 lucky winners! To enter: 👑 Like + RT this post 👑 Follow Immutable 👑 Enter below

Immutable

90,354 views • 3 years ago