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.

GPT‑5.6 is helping Vercel’s internal data science agent tackle harder work Andrew Qu, Vercel’s Chief of Software, used GPT-5.6 and Codex to unblock an internal data science agent on work where earlier models got stuck.

OpenAI Developers

385,253 subscribers

5,677,923 views • 1 month ago •via X (Twitter)

Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

wow... GPT 5.6 Sol Passed the Replit Benchmark. In one prompt 5.6 on Codex created a full Replit clone with DB, Sandboxes, and an agent that builds and edits full web apps. Only Fable and GPT 5.6 have passed this benchmark. 5.6 is much better at designing iOS apps than 5.5 as well.

wow... GPT 5.6 Sol Passed the Replit Benchmark. In one prompt 5.6 on Codex created a full Replit clone with DB, Sandboxes, and an agent that builds and edits full web apps. Only Fable and GPT 5.6 have passed this benchmark. 5.6 is much better at designing iOS apps than 5.5 as well.

Riley Brown

123,242 views • 1 month ago

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!

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

16,318 views • 26 days ago

An internal version of our next major model produced 10 new results on long-standing open problems in mathematics and theoretical computer science, using roughly $2,000 worth of tokens at GPT-5.6 Sol API rates.

An internal version of our next major model produced 10 new results on long-standing open problems in mathematics and theoretical computer science, using roughly $2,000 worth of tokens at GPT-5.6 Sol API rates.

OpenAI

1,806,533 views • 24 days ago

GPT-5.6 is a viable alternative to Fable for most knowledge work. GPT-5.6's writing is consistently well-structured and easy to read. Fable's prose can be exhausting. 5.6 also makes fresh design choices with clean hierarchy. Fable can struggle to maintain visual relationships and leans on worn-out AI tropes like eyebrow text. Examples in thread 👇 - Orbital objects explainer - Site plan for fitness resort - World Cup goals data viz GPT-5.6 is now available on Hyperagent

GPT-5.6 is a viable alternative to Fable for most knowledge work. GPT-5.6's writing is consistently well-structured and easy to read. Fable's prose can be exhausting. 5.6 also makes fresh design choices with clean hierarchy. Fable can struggle to maintain visual relationships and leans on worn-out AI tropes like eyebrow text. Examples in thread 👇 - Orbital objects explainer - Site plan for fitness resort - World Cup goals data viz GPT-5.6 is now available on Hyperagent

Hyperagent

304,125 views • 1 month ago

Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done.

Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done.

OpenAI

16,059,949 views • 1 month ago

OPANAI 👀: ChatGPT Work arrived as a new AI Agent, along with a completely new app based on Codex Desktop. > Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done. A merge into a Super App is complete 🤖

OPANAI 👀: ChatGPT Work arrived as a new AI Agent, along with a completely new app based on Codex Desktop. > Introducing ChatGPT Work, a new agent in ChatGPT powered by Codex and GPT-5.6. It can take action across your apps and files, stay with a project for hours if needed, and turn a goal into finished work. It’s a whole new way to get work done. A merge into a Super App is complete 🤖

🚨 AI News | TestingCatalog

34,254 views • 1 month ago

FULL INTERVIEW: Sam Altman joins TBPN to discuss GPT-5.3-Codex, AI agents, Anthropic's Super Bowl ads, and more. 00:00 GPT-5.3-Codex 02:27 AI agents and the future of work 03:20 The role of forward-deployed engineers in AI 05:42 AI benchmarks 07:29 Emotional attachment to chatbots 10:40 On data and compute being the 'new oil' 12:56 Is software dead? 17:48 Codex Desktop and the rise of the general-purpose work agent 25:00 OpenAI’s last Super Bowl ad and the Anthropic ads

FULL INTERVIEW: Sam Altman joins TBPN to discuss GPT-5.3-Codex, AI agents, Anthropic's Super Bowl ads, and more. 00:00 GPT-5.3-Codex 02:27 AI agents and the future of work 03:20 The role of forward-deployed engineers in AI 05:42 AI benchmarks 07:29 Emotional attachment to chatbots 10:40 On data and compute being the 'new oil' 12:56 Is software dead? 17:48 Codex Desktop and the rise of the general-purpose work agent 25:00 OpenAI’s last Super Bowl ad and the Anthropic ads

TBPN

639,180 views • 6 months ago

I'm excited to introduce my AI Machine Learning Agent that built 32 ML models in 30 seconds. Today, I'll share with you how to automate building 100s of ML models with the AI ML Agent, which is available on GitHub. We'll create an ML Agent focusing on a Customer Churn Problem. I'll guide you through setting up the ML Agent, creating dozens of ML models, and loading the best model for production. This AI is a huge time-saver! Table of Contents: 00:00 Introduction to my AI Data Science Team 02:56 Setting Up AI Data Science Team 04:48 Running the ML Agent Code 07:12 Create (and Run) the AI Machine Learning Agent 09:53 Reviewing ML Model Summary 12:00 Saving and Loading Models 13:00 Next Steps + Project Roadmap + AI Bootcamp Github to AI Data Science Team (Data Science Agents): Get the Code and Future Updates by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, May 21st, I'm sharing one of my best AI Projects: AI Customer Segmentation Agent with Python Register here (570+ registered):

I'm excited to introduce my AI Machine Learning Agent that built 32 ML models in 30 seconds. Today, I'll share with you how to automate building 100s of ML models with the AI ML Agent, which is available on GitHub. We'll create an ML Agent focusing on a Customer Churn Problem. I'll guide you through setting up the ML Agent, creating dozens of ML models, and loading the best model for production. This AI is a huge time-saver! Table of Contents: 00:00 Introduction to my AI Data Science Team 02:56 Setting Up AI Data Science Team 04:48 Running the ML Agent Code 07:12 Create (and Run) the AI Machine Learning Agent 09:53 Reviewing ML Model Summary 12:00 Saving and Loading Models 13:00 Next Steps + Project Roadmap + AI Bootcamp Github to AI Data Science Team (Data Science Agents): Get the Code and Future Updates by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, May 21st, I'm sharing one of my best AI Projects: AI Customer Segmentation Agent with Python Register here (570+ registered):

Matt Dancho (Business Science)

35,452 views • 1 year ago

Opus 5 is a modest upgrade, but it has tough competition in GPT-5.6 Sol Initial thoughts from our early access: > Clearer writing than Fable's dense communication style > Still gets too verbose compared to GPT models (even when explicitly instructed to keep text purposeful) > Strong on browser use inside Hyperagent > Strong on reviewing complex data to justify a decision > Less likely to take creative risks. More of a "rule follower" personality. Costs shown for five test cases (GPT-5.6 Sol was consistently much cheaper) Explore and judge the actual work for yourself in thread 👇

Opus 5 is a modest upgrade, but it has tough competition in GPT-5.6 Sol Initial thoughts from our early access: > Clearer writing than Fable's dense communication style > Still gets too verbose compared to GPT models (even when explicitly instructed to keep text purposeful) > Strong on browser use inside Hyperagent > Strong on reviewing complex data to justify a decision > Less likely to take creative risks. More of a "rule follower" personality. Costs shown for five test cases (GPT-5.6 Sol was consistently much cheaper) Explore and judge the actual work for yourself in thread 👇

Hyperagent

153,112 views • 1 month ago

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

GPT-5.6 vs GPT-5.5 on my custom spaceship prompt. I gave both models the exact same custom prompt. This is also the same prompt I previously gave to Fable 5. For context, GPT-5.6 Pro worked for 87 minutes, while GPT-5.5 Extra High worked for 34 minutes and 42 seconds. As I’ve said before, based on great authority GPT-5.6 will be an incremental/soldi improvement over GPT-5.5, not a “Fable killer.” My rough expectation has been that it would trade blows with Fable 5 on some benchmarks, maybe win around half depending on the category, but not clearly surpass it overall. And again fable five will have bigger model smell, but this was expected. After testing this coding output, that view feels pretty accurate. GPT-5.6 is clearly better than GPT-5.5 in several visual areas. The lighting, shading, chairs, object details, and exterior of the spaceship looked noticeably stronger. The scene was also easier to test. I do want to give GPT-5.5 credit though. It built out the rooms much much better and the planets looked better than GPT-5.6’s. It was also interesting that both GPT-5.5 and GPT-5.6 produced better-looking planets than Fable 5 in this specific test. The downside with GPT-5.5 was stability. The game was much glitchier and harder to test compared to GPT-5.6. But when it comes to the core of the demo, which is the spaceship itself, Fable 5 still beat both models pretty comfortably. GPT-5.6 is impressive, but from this test, it looks exactly like what I expected which was a meaningful incremental improvement over GPT-5.5, at least for indie game demos, but not something that replaces Fable 5. In collaboration with Chetaslua

Chris

250,919 views • 2 months ago

Forget autocomplete — this is agent-complete. On Episode 6 of the OpenAI Podcast, Greg Brockman and Codex lead Thibault Sottiaux join @andrewmayne to talk about the leap from code suggestions to coding agents, the launch of GPT-5-Codex, and where software development could be by 2030.

Forget autocomplete — this is agent-complete. On Episode 6 of the OpenAI Podcast, Greg Brockman and Codex lead Thibault Sottiaux join @andrewmayne to talk about the leap from code suggestions to coding agents, the launch of GPT-5-Codex, and where software development could be by 2030.

OpenAI

292,314 views • 11 months ago

Today we open sourced our no 1 used internal tool, berd. An agent where you can byo harness/models while keeping your work and context in one place, in an unhinged environment where you can build your dream team of agents. Try it out at

Today we open sourced our no 1 used internal tool, berd. An agent where you can byo harness/models while keeping your work and context in one place, in an unhinged environment where you can build your dream team of agents. Try it out at

John Sullivan Hamilton

693,451 views • 9 days ago

I'm excited to introduce my AI Machine Learning Agent that built 32 ML models in 30 seconds. Today, I'll share with you how to automate building 100s of ML models with the AI ML Agent, which is available on GitHub. We'll create an ML Agent focusing on a Customer Churn Problem. I'll guide you through setting up the ML Agent, creating dozens of ML models, and loading the best model for production. This AI is a huge time-saver! Table of Contents: 00:00 Introduction to my AI Data Science Team 02:56 Setting Up AI Data Science Team 04:48 Running the ML Agent Code 07:12 Create (and Run) the AI Machine Learning Agent 09:53 Reviewing ML Model Summary 12:00 Saving and Loading Models 13:00 Next Steps + Project Roadmap + AI Bootcamp Github to AI Data Science Team (Army of Copilots): Get the Code and Future Updates by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, January 29th, I'm sharing one of my best AI Projects: Time Series Forecasting with AI Register here (1570+ registered):

I'm excited to introduce my AI Machine Learning Agent that built 32 ML models in 30 seconds. Today, I'll share with you how to automate building 100s of ML models with the AI ML Agent, which is available on GitHub. We'll create an ML Agent focusing on a Customer Churn Problem. I'll guide you through setting up the ML Agent, creating dozens of ML models, and loading the best model for production. This AI is a huge time-saver! Table of Contents: 00:00 Introduction to my AI Data Science Team 02:56 Setting Up AI Data Science Team 04:48 Running the ML Agent Code 07:12 Create (and Run) the AI Machine Learning Agent 09:53 Reviewing ML Model Summary 12:00 Saving and Loading Models 13:00 Next Steps + Project Roadmap + AI Bootcamp Github to AI Data Science Team (Army of Copilots): Get the Code and Future Updates by Joining my Python AI/ML Tips Newsletter: P.S. - Want to learn how to build AI projects companies actually want? (live Python Code) On Wednesday, January 29th, I'm sharing one of my best AI Projects: Time Series Forecasting with AI Register here (1570+ registered):

Matt Dancho (Business Science)

242,084 views • 1 year ago

This one is for builders who want an agent that can operate their computer. Today, we're releasing HoloDesktop CLI. Powered by Holo3 models, it brings H Agent directly into the agent harnesses you already use, including Claude R Perrin Code, Hermes Trismegistus, Cursor, and others. It runs locally on your device with low latency, full privacy, and no runtime cost. Most AI tooling assumes work happens through APIs. In reality, much of the world's work still happens in interfaces built for humans: browsers, desktop applications, spreadsheets, internal tools, and software with no API. HoloDesktop CLI gives agents the ability to see, understand, and act on these environments through the mouse and keyboard. From testing web applications through their GUI to navigating enterprise software, extracting information from documents, or interacting with internal tools, agents can now operate where work actually happens. We believe AI shouldn't just reason about work. It should be able to operate where work happens. #NVIDIA #ComputerUse #EnterpriseAI #DeveloperTools

This one is for builders who want an agent that can operate their computer. Today, we're releasing HoloDesktop CLI. Powered by Holo3 models, it brings H Agent directly into the agent harnesses you already use, including Claude R Perrin Code, Hermes Trismegistus, Cursor, and others. It runs locally on your device with low latency, full privacy, and no runtime cost. Most AI tooling assumes work happens through APIs. In reality, much of the world's work still happens in interfaces built for humans: browsers, desktop applications, spreadsheets, internal tools, and software with no API. HoloDesktop CLI gives agents the ability to see, understand, and act on these environments through the mouse and keyboard. From testing web applications through their GUI to navigating enterprise software, extracting information from documents, or interacting with internal tools, agents can now operate where work actually happens. We believe AI shouldn't just reason about work. It should be able to operate where work happens. #NVIDIA #ComputerUse #EnterpriseAI #DeveloperTools

H

29,953 views • 2 months ago

Introducing Agent Plugins 🚨 Plugins help you save tokens on expensive models like GPT-5.6 Sol and Claude Fable, while getting tasks done more accurately. Some examples that will work out of the box: 👩‍💼 SMB back-office automation 💵 Track your personal finances; or 🎒 Manage your kid’s school schedule I love tokenmaxxing, but not everything needs more prompting.

Introducing Agent Plugins 🚨 Plugins help you save tokens on expensive models like GPT-5.6 Sol and Claude Fable, while getting tasks done more accurately. Some examples that will work out of the box: 👩‍💼 SMB back-office automation 💵 Track your personal finances; or 🎒 Manage your kid’s school schedule I love tokenmaxxing, but not everything needs more prompting.

Marina · vellum.ai 👾

49,001 views • 1 month ago

By 2030, the data science field is projected to grow by 30% -- this is the tool I’d add to my learning path if I were re-skilling into data science: 𝐩𝐢𝐩 𝐢𝐧𝐬𝐭𝐚𝐥𝐥 𝐦𝐢𝐭𝐨-𝐚𝐢 It’s an open-source toolkit that adds AI to your Jupyter Notebooks, and it’s surprisingly helpful for learning by doing. Try now It lets you: • Use natural language to generate full data workflows • Upload an Excel file and watch it convert to clean Python code • Work with top models (ChatGPT, Claude, Gemini) right inside your notebook with no setup One thing I really like about Mito AI: it shows you exactly what it’s doing. (Which is super helpful for both beginners and debugging.) -The agent explains its assumptions - Every result links back to editable, transparent code That makes it a great companion if you're: • Transitioning from Excel • Exploring data automation or dashboards • Or just brushing up on how real data science pipelines work

By 2030, the data science field is projected to grow by 30% -- this is the tool I’d add to my learning path if I were re-skilling into data science: 𝐩𝐢𝐩 𝐢𝐧𝐬𝐭𝐚𝐥𝐥 𝐦𝐢𝐭𝐨-𝐚𝐢 It’s an open-source toolkit that adds AI to your Jupyter Notebooks, and it’s surprisingly helpful for learning by doing. Try now It lets you: • Use natural language to generate full data workflows • Upload an Excel file and watch it convert to clean Python code • Work with top models (ChatGPT, Claude, Gemini) right inside your notebook with no setup One thing I really like about Mito AI: it shows you exactly what it’s doing. (Which is super helpful for both beginners and debugging.) -The agent explains its assumptions - Every result links back to editable, transparent code That makes it a great companion if you're: • Transitioning from Excel • Exploring data automation or dashboards • Or just brushing up on how real data science pipelines work

Python Coding

107,495 views • 11 months ago

I made an AI data science team with Python. I'm excited to share my new project, the AI Data Science Team, a Python package for creating AI co-pilots and agents to assist in common data science tasks. I walk you through the GitHub page, showcasing the progress and potential of this project. I'll explain how these agents can streamline tasks like code generation and modeling pipeline creation, making data science projects more efficient. Introduction to AI Data Science Team Project Integrating Human-in-the-Loop Example: Accessing Agents for Feature Engineering Setting up Feature Engineering Agent Code On GitHub: Python AI-Tips Newsletter (stay updated as I build this project in the open):

I made an AI data science team with Python. I'm excited to share my new project, the AI Data Science Team, a Python package for creating AI co-pilots and agents to assist in common data science tasks. I walk you through the GitHub page, showcasing the progress and potential of this project. I'll explain how these agents can streamline tasks like code generation and modeling pipeline creation, making data science projects more efficient. Introduction to AI Data Science Team Project Integrating Human-in-the-Loop Example: Accessing Agents for Feature Engineering Setting up Feature Engineering Agent Code On GitHub: Python AI-Tips Newsletter (stay updated as I build this project in the open):

Matt Dancho (Business Science)

11,799 views • 1 year ago

been building an agent-native, node-based, real-time environment. as a test, I gave gpt-5.6 sol a prompt to plan out its own setup and go into a loop of creative exploration until it felt that it was done. it invented every node, every data type, every connection and all of it comes out modular and human-readable. i could open any piece and steer while it built

been building an agent-native, node-based, real-time environment. as a test, I gave gpt-5.6 sol a prompt to plan out its own setup and go into a loop of creative exploration until it felt that it was done. it invented every node, every data type, every connection and all of it comes out modular and human-readable. i could open any piece and steer while it built

Spencer Sterling

22,217 views • 1 month ago

OpenAI just killed the idea of one best model. GPT-5.6 is three different jobs: - Sol for hard reasoning and long agent runs - Terra for everyday work - Luna for cheap high-volume tasks Most people will send every prompt to Sol, then complain about the cost. The edge is not having the flagship. It is knowing when you do not need it.

OpenAI just killed the idea of one best model. GPT-5.6 is three different jobs: - Sol for hard reasoning and long agent runs - Terra for everyday work - Luna for cheap high-volume tasks Most people will send every prompt to Sol, then complain about the cost. The edge is not having the flagship. It is knowing when you do not need it.

Fluixo

12,641 views • 1 month ago