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.

I used my codex reset to cut this OpenAI Dev Day recap, where I cover my favorite releases for the day (spoiler alert: I'm now an expensive Ultrafast girl) What I cover: (00:58) Dots: early impressions and rough edges (06:57) Spaces: working with humans and agents (10:37) Sites, connectors,... show more

claire vo 🖤

68,482 subscribers

11,651 views • 3 days ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

9 Comments

Dassi AI3 days ago

@OpenAI Ultrafast fixes decision latency, but state verification across internal tools is the real production moat.

cris pérez de lope3 days ago

@OpenAI Great update claire, thank you!

Spencer Schneidenbach 🦈🇺🇸3 days ago

@OpenAI Devday was a vibe!!

Hillary Bush2 days ago

@OpenAI sponsored by how do it know

Lee Wyatt Corp3 days ago

@OpenAI Free Codex reset, spent on the recap. Priorities in order.

Rohan3 days ago

@OpenAI Which of the rough edges in Dots would hit a team before a solo user?

Rivaldo A.3 days ago

@OpenAI expensive Ultrafast girl? hope the Wi-Fi bills match the speed.

Ash Designs3 days ago

@OpenAI The Dots rough edges part is the one I want. Always on agents need a totally different UI than chat. What felt most off on day one, notifications or knowing what it's doing in the background?

John K3 days ago

@OpenAI Dots with the rough edges called out, then Spaces — that pacing makes the Dev Day pile feel watchable.

Related Videos

BIG NEWS: Opus 5 is here...and I *hate* working with it. And yet in a blind taste test, I ranked it above every other model (even Fable and my beloved GPT-5.6) What I cover in my day 0 review: 00:00 Why I have model fatigue 03:15 First impressions 06:12 Opus 5's neurotic personality 14:39 Why claude slop makes my blood boil 16:55 The mechanics behind my blind benchmark 18:30 The leaderboard reveal 23:25 Final thoughts and how I'll actually use Opus 5 With all the twists, turns, and (a little bit of) silliness, this is one of my favorite review eps yet.

BIG NEWS: Opus 5 is here...and I hate working with it. And yet in a blind taste test, I ranked it above every other model (even Fable and my beloved GPT-5.6) What I cover in my day 0 review: 00:00 Why I have model fatigue 03:15 First impressions 06:12 Opus 5's neurotic personality 14:39 Why claude slop makes my blood boil 16:55 The mechanics behind my blind benchmark 18:30 The leaderboard reveal 23:25 Final thoughts and how I'll actually use Opus 5 With all the twists, turns, and (a little bit of) silliness, this is one of my favorite review eps yet.

claire vo 🖤

165,067 views • 2 months ago

💫 👩‍🚀 GPT-6 Astra is here (and I'm obsessed) I was able to test this model early and it is so, so good. But even better - it has made me 100x more *ambitious* about what I can build with AI. Why? Browser / computer use means it can use any software to build anything (even games.) Coding broke through some of my hardest problems (data, hardware.) AND best of all, it's delightfully not annoying. Here's what I cover in my hands-on review: 00:00 GPT-6 Astra overview 03:44 Browser use to manage CRM workflows 09:08 Flora thumbnail generation 13:00 Browser use for QA 15:20 One shotting a product intelligence feature 18:36 Hardware hack: live streaming mini computer 22:23 Building AIM-style codex app 24:24 Barbie Bench and a 3D kids game 29:27 Summary: I love her 👉 Full ep up on YT:

💫 👩‍🚀 GPT-6 Astra is here (and I'm obsessed) I was able to test this model early and it is so, so good. But even better - it has made me 100x more ambitious about what I can build with AI. Why? Browser / computer use means it can use any software to build anything (even games.) Coding broke through some of my hardest problems (data, hardware.) AND best of all, it's delightfully not annoying. Here's what I cover in my hands-on review: 00:00 GPT-6 Astra overview 03:44 Browser use to manage CRM workflows 09:08 Flora thumbnail generation 13:00 Browser use for QA 15:20 One shotting a product intelligence feature 18:36 Hardware hack: live streaming mini computer 22:23 Building AIM-style codex app 24:24 Barbie Bench and a 3D kids game 29:27 Summary: I love her 👉 Full ep up on YT:

claire vo 🖤

122,866 views • 29 days ago

GrokBot Just Launched: GrokBot is Cursor/SpaceX new general agent platform for Desktop and iOS... Got access yesterday... here are the things that Grokbot can do, my thoughts, and what I hope they add soon. Pretty big news for those who want to build businesses that are Agent Native 00:00 Intro 01:42 Creating new Grokbot with Connections 05:25 The Plugins Tab 06:40 How Skills, Plugins, and Agent Descriptions Work 08:08 Grok Bot Cloud Computer 10:24 Agents Talking to Each Other 13:38 Triggers & Automations 17:06 What's Missing & Coming Soon (Probably)

GrokBot Just Launched: GrokBot is Cursor/SpaceX new general agent platform for Desktop and iOS... Got access yesterday... here are the things that Grokbot can do, my thoughts, and what I hope they add soon. Pretty big news for those who want to build businesses that are Agent Native 00:00 Intro 01:42 Creating new Grokbot with Connections 05:25 The Plugins Tab 06:40 How Skills, Plugins, and Agent Descriptions Work 08:08 Grok Bot Cloud Computer 10:24 Agents Talking to Each Other 13:38 Triggers & Automations 17:06 What's Missing & Coming Soon (Probably)

Riley Brown

110,750 views • 1 month ago

2026 is the year of Agents OpenClaw, Claude Code, Codex and Cursor... In this video, I broke it all down with Micky. Consider this a 2026, year in review for AI agents. 00:00 Intro 01:35 Q1 Belonged to Anthropic 03:02 Opus 4.5 Inflection 08:42 Codex vs Claude UX War 12:53 Cursor was first? 14:27 SpaceX Acquisition Deal with Cursor 21:45 OpenClaw and the Agentic Personal Computer 28:57 Reactive vs Proactive Work 30:30 Keep Agents Narrow 33:12 Memory Layer Matters 36:23 Computer Use will get FAST 39:28 Who Wins the Super App? (Codex so far) 41:06 The Problem With Google... 45:17 Prompting and Skills creation 51:30 Codex Skill Example 56:56 Integrations Beat Prompts 59:39 All the Muxes (CMUX, TMUX) 01:02:04 Bold Predictions 01:06:38 Agent Commerce

2026 is the year of Agents OpenClaw, Claude Code, Codex and Cursor... In this video, I broke it all down with Micky. Consider this a 2026, year in review for AI agents. 00:00 Intro 01:35 Q1 Belonged to Anthropic 03:02 Opus 4.5 Inflection 08:42 Codex vs Claude UX War 12:53 Cursor was first? 14:27 SpaceX Acquisition Deal with Cursor 21:45 OpenClaw and the Agentic Personal Computer 28:57 Reactive vs Proactive Work 30:30 Keep Agents Narrow 33:12 Memory Layer Matters 36:23 Computer Use will get FAST 39:28 Who Wins the Super App? (Codex so far) 41:06 The Problem With Google... 45:17 Prompting and Skills creation 51:30 Codex Skill Example 56:56 Integrations Beat Prompts 59:39 All the Muxes (CMUX, TMUX) 01:02:04 Bold Predictions 01:06:38 Agent Commerce

Riley Brown

20,154 views • 5 months ago

Hosting our own Buzz w/ Cloud Agents (Buzz Video #2:) For the past week, Vishal Dubey and I have been using Buzz. Yesterday, Vishal used Fable 5 (inside Buzz) to create our own hosted version of Buzz with built-in cloud agents that never die. These agents can spin up new agents that all share the same skills, API keys, workspace, files, automations, and more. This is an EXPERIMENT. We’re trying to find the best setup for businesses to create teams of agents and humans that work together. Part 1: What we like and don’t like about Buzz Part 2: Vishal’s hosted version of Buzz ⭐ Part 1 00:00 Intro 01:06 What Is a Harness? 02:49 What We Like About Buzz 04:17 Agents Collaborating Together 06:29 Custom Agents and Personas 08:13 Spinning Up Agents and Channels 10:34 What We Don't Like about Buzz ⭐ Part 2 14:03 Vishals Version of Buzz with Cloud Agents 19:39 Shared Skills and Connections 23:18 Setting Up a Daily Research Automation 26:08 Buzz Mobile App 30:53 Treat the agents like their own employee 35:28 Using Any Model (Fable, 5.6, Kimi) 37:25 What Vishal wish Buzz Had

Hosting our own Buzz w/ Cloud Agents (Buzz Video #2:) For the past week, Vishal Dubey and I have been using Buzz. Yesterday, Vishal used Fable 5 (inside Buzz) to create our own hosted version of Buzz with built-in cloud agents that never die. These agents can spin up new agents that all share the same skills, API keys, workspace, files, automations, and more. This is an EXPERIMENT. We’re trying to find the best setup for businesses to create teams of agents and humans that work together. Part 1: What we like and don’t like about Buzz Part 2: Vishal’s hosted version of Buzz ⭐ Part 1 00:00 Intro 01:06 What Is a Harness? 02:49 What We Like About Buzz 04:17 Agents Collaborating Together 06:29 Custom Agents and Personas 08:13 Spinning Up Agents and Channels 10:34 What We Don't Like about Buzz ⭐ Part 2 14:03 Vishals Version of Buzz with Cloud Agents 19:39 Shared Skills and Connections 23:18 Setting Up a Daily Research Automation 26:08 Buzz Mobile App 30:53 Treat the agents like their own employee 35:28 Using Any Model (Fable, 5.6, Kimi) 37:25 What Vishal wish Buzz Had

Riley Brown

36,729 views • 2 months ago

Building an Agent Team on Buzz (Complete Guide) Buzz is a new free platform, that feels exactly like Slack, except the agents aren't add ons, they are equals. and in 5 minutes you can create an agent team. And it works with your existing Codex and Claude Code subscriptions... So it's free to use. This video is divided into 2 parts: --- ⭐ Part 1 Conversation with Vinny (Vinny) 00:00 Introduction 01:59 Why is Buzz Going Viral? 07:08 Creating Agents & Channels with Fizz 20:03 Adding Other Harnesses (OpenCode, Cursor) 21:25 The Buzz Mobile App 22:36 Payments & Shared Compute 25:36 Workflows & Projects: A GitHub Killer? 30:14 The Future of Buzz: An Open Cowork? 35:13 Automations, Triggers & Trusting Your Agents --- ⭐ Part 2 - Getting Started Tutorial (My workflow) 42:32 Tutorial and Breakdown 43:03 Downloading Buzz And Default Agents 43:35 Creating your first agent 45:13 Adding Agents to channels 45:43 Why I use Codex as Lead Agent 47:06 Using Codex, Claude Code and Grok for task 48:52 Adding Muse (Meta Model) using OpenRouter 51:23 iOS app is Free and easy to use 51:50 My management Channel (My #1 use case) ---

Building an Agent Team on Buzz (Complete Guide) Buzz is a new free platform, that feels exactly like Slack, except the agents aren't add ons, they are equals. and in 5 minutes you can create an agent team. And it works with your existing Codex and Claude Code subscriptions... So it's free to use. This video is divided into 2 parts: --- ⭐ Part 1 Conversation with Vinny (Vinny) 00:00 Introduction 01:59 Why is Buzz Going Viral? 07:08 Creating Agents & Channels with Fizz 20:03 Adding Other Harnesses (OpenCode, Cursor) 21:25 The Buzz Mobile App 22:36 Payments & Shared Compute 25:36 Workflows & Projects: A GitHub Killer? 30:14 The Future of Buzz: An Open Cowork? 35:13 Automations, Triggers & Trusting Your Agents --- ⭐ Part 2 - Getting Started Tutorial (My workflow) 42:32 Tutorial and Breakdown 43:03 Downloading Buzz And Default Agents 43:35 Creating your first agent 45:13 Adding Agents to channels 45:43 Why I use Codex as Lead Agent 47:06 Using Codex, Claude Code and Grok for task 48:52 Adding Muse (Meta Model) using OpenRouter 51:23 iOS app is Free and easy to use 51:50 My management Channel (My #1 use case) ---

Riley Brown

388,759 views • 2 months ago

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

Loop engineering is great until something breaks. Here is how I improve the reliability of my agentic loops. I use human-in-the-loop (HITL). It's easy and extremely effective. Anyone can build this. My setup: I recorded a quick demo of how it all works. I shared recently that I now use more voice agents to build and communicate with agents. I also use them to verify. I hate the idea of being tied down to my computer or in a Slack channel to communicate with my agents. Here is what I have done to streamline communication with my agents. All my Claude and Codex agent sessions now use the Dial MCP server. It has a bunch of tools and provisions my agents with their own number that can place calls as native tools, with voice, SMS, and iMessage behind one interface. As my loops/automations work on PRs and new features, my agents escalate decisions to me via a short phone call. This is extremely useful when I am on the road or away from my desk. If you want to try this with Claude Code or Codex, paste this into your agent and get started right away: "Get yourself a Dial phone number and call me. Say hello and that setup is working, then hang up. Follow Natan Voitenkov and team are building something special here. Go check them out. Give your agent a phone number now: ($5 free credit)

elvis

15,614 views • 2 months ago

GPT-6 Astra is by far the best inside Codex. & this is THE Complete Beginners Guide to Codex. The 28 things you need to know about Codex and GPT-6 to start using it for knowledge work and coding work. My goal with this video: give you one guide you can send to anyone on your team so they can get comfortable with Codex, understand what’s possible, and start finding ways to use AI in your business. 00:00 Intro 01:15 The Codex Platform 02:02 Downloading Codex (ChatGPT Desktop) 03:25 1. Codex Is the App, GPT-6 Is the Model 06:10 2. Build Any App 10:32 3. Host Sites with GPT Sites 18:12 4A. Building Desktop App 21:33 4B. Building an iOS app 24:09 5. Built-In Web Browser 32:27 6. Create Any Document 35:00 7. Annotation Mode 38:41 8. Production-Ready Apps 44:29 9. Chats & Projects 48:54 10. Multitasking 50:09 10B Side Chat 51:13 11. Sections 54:27 12. Connect Every App (Plugins) 01:03:17 13. Ask Codex What to Work On 01:05:39 14. Blender & 3D Assets 01:08:25 15. Video Games 01:09:24 16. Interactive Learning Websites 01:13:12 17. Scheduled Tasks 01:16:19 18. Email & iMessage 01:18:56 19. Skills 01:22:54 20. Record and Replay 01:26:45 21. External APIs in Skills 01:30:00 22. Video Understanding Skill 01:35:51 23. Inline Charts 01:38:03 24. Control Codex from Your Phone 01:42:49 25. Generate & Edit Images 01:45:17 26. Sub-Agents 01:48:09 27. Computer Use 01:49:35 28. Whatever You Want

GPT-6 Astra is by far the best inside Codex. & this is THE Complete Beginners Guide to Codex. The 28 things you need to know about Codex and GPT-6 to start using it for knowledge work and coding work. My goal with this video: give you one guide you can send to anyone on your team so they can get comfortable with Codex, understand what’s possible, and start finding ways to use AI in your business. 00:00 Intro 01:15 The Codex Platform 02:02 Downloading Codex (ChatGPT Desktop) 03:25 1. Codex Is the App, GPT-6 Is the Model 06:10 2. Build Any App 10:32 3. Host Sites with GPT Sites 18:12 4A. Building Desktop App 21:33 4B. Building an iOS app 24:09 5. Built-In Web Browser 32:27 6. Create Any Document 35:00 7. Annotation Mode 38:41 8. Production-Ready Apps 44:29 9. Chats & Projects 48:54 10. Multitasking 50:09 10B Side Chat 51:13 11. Sections 54:27 12. Connect Every App (Plugins) 01:03:17 13. Ask Codex What to Work On 01:05:39 14. Blender & 3D Assets 01:08:25 15. Video Games 01:09:24 16. Interactive Learning Websites 01:13:12 17. Scheduled Tasks 01:16:19 18. Email & iMessage 01:18:56 19. Skills 01:22:54 20. Record and Replay 01:26:45 21. External APIs in Skills 01:30:00 22. Video Understanding Skill 01:35:51 23. Inline Charts 01:38:03 24. Control Codex from Your Phone 01:42:49 25. Generate & Edit Images 01:45:17 26. Sub-Agents 01:48:09 27. Computer Use 01:49:35 28. Whatever You Want

Riley Brown

193,991 views • 18 days ago

Codex tip: once GPT-6.1 Sol is your main model, stop running Astra on every turn put Astra on call as an architect agent GPT-6.1 Sol keeps writing the code Astra only gets spawned at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Astra reviews. Sol ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > GPT-6.1 Sol on high runs the main session > explorer reads the code on Luna > worker edits and runs tests on Sol > researcher pulls the docs on Luna > all three on medium > Astra on call as the architect > auto_review checks every approval paste the tree and this prompt into Codex ↓ "Rebuild my Codex setup around this tree: 1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, worker and researcher. > Draft new TOML files only for missing roles > explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium > Add an architect agent on gpt-6-astra, model_reasoning_effort high, whose only job is reviewing plans, repeated errors and finished work > Skip any that pin a different model and list them 2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review 3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing 4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

Codex tip: once GPT-6.1 Sol is your main model, stop running Astra on every turn put Astra on call as an architect agent GPT-6.1 Sol keeps writing the code Astra only gets spawned at three points: → before a plan: is this the right approach? → when the same error comes back: am I digging in the wrong place? → before "done": what did I miss? Astra reviews. Sol ships Jev engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to Jev in under half a second, and the big models only see the ones that split - the full tree > GPT-6.1 Sol on high runs the main session > explorer reads the code on Luna > worker edits and runs tests on Sol > researcher pulls the docs on Luna > all three on medium > Astra on call as the architect > auto_review checks every approval paste the tree and this prompt into Codex ↓ "Rebuild my Codex setup around this tree: 1. Check ~/.codex/agents and .codex/agents for agents that already fit explorer, worker and researcher. > Draft new TOML files only for missing roles > explorer and researcher on gpt-6-luna, worker on gpt-6.1-sol, all with model_reasoning_effort medium > Add an architect agent on gpt-6-astra, model_reasoning_effort high, whose only job is reviewing plans, repeated errors and finished work > Skip any that pin a different model and list them 2. In ~/.codex/config.toml set model to gpt-6.1-sol, model_reasoning_effort to high and approvals_reviewer to auto_review 3. Find anything that would override this (active profiles, flags in my shell aliases, agents.default_subagent_model). Report it, change nothing 4. Add one rule to AGENTS.md: spawn the architect before a large plan, when an error repeats, and before calling a long task done Show me every change as a diff first. No edits until I say go." ↳

delost

918,253 views • 2 days ago

OpenAI released Codex Mobile App Directly on ChatGPT Here's everything you need to know: 1. How to set it up 2. How to fully vibecode from Codex Mobile 3. How to control your computer with Codex Mobile 00:00 Setting Up Codex Mobile on @ChatGPTapp 02:15 Changing Settings - Chats First 03:01 Voice Mode 04:05 Plugins and Skills 05:07 Notifications and Permissions 06:52 Flaws of Vibe Coding Out of the Box 07:13 Vibe Coding Skill (Yolo Mode w Vercel) 10:28 Using ChatGPT app as Full Vibe Coding Platform 12:15 Using ChatGPT to Control my computer 13:33 Where I put all my Agent Skills @chorusskills

OpenAI released Codex Mobile App Directly on ChatGPT Here's everything you need to know: 1. How to set it up 2. How to fully vibecode from Codex Mobile 3. How to control your computer with Codex Mobile 00:00 Setting Up Codex Mobile on @ChatGPTapp 02:15 Changing Settings - Chats First 03:01 Voice Mode 04:05 Plugins and Skills 05:07 Notifications and Permissions 06:52 Flaws of Vibe Coding Out of the Box 07:13 Vibe Coding Skill (Yolo Mode w Vercel) 10:28 Using ChatGPT app as Full Vibe Coding Platform 12:15 Using ChatGPT to Control my computer 13:33 Where I put all my Agent Skills @chorusskills

Riley Brown

92,536 views • 4 months ago

I built an AI powered writing app with Cursor Agent without writing a single line of code in a little over an hour. Features: - AI powered autocomplete - AI powered image search with autosuggestions based on what i'm writing - Ai powered research based on what i'm writing - Block based writing (which is useful for my workflow as a video content creator) !!! And I ran it locally this time. Normally I use replit, so if you got stuck on connecting cursor and replit, this video is for you. Template pinned on @senior_swc (starting point you can download) Tools used - Cursor (Claude for ai model) - Firebase - Deepseek DeepSeek - Exa ( Exa ) - Search API These videos serve as R&D for the app we're building at @yapthread. We're building the cursor for content creators. Sections 00:00 Introduction 03:24 Introduction to the Template 03:54 Setting Up Locally 04:04 Downloading and Running Locally 05:34 Firebase Setup 06:10 first prompt in cursor + continuing firebase 08:11 Full Plan for the app I'm building 10:44 Outlining the app hotkeys 11:55 Testing First Feature 16:54 Adding Autocomplete Feature Deepseek 22:23 Adding Images to Blocks (Search API) 22:42 Implementing and Testing Image Search (Search API) 25:32 Adjusting Image Sizes and Social Media Discussion 28:11 Adding Relevant Links (Exa API) 30:34 Testing and Debugging Link Highlights 32:27 Finalizing Image and Link Integration 40:37 Conclusion and Future Plans

I built an AI powered writing app with Cursor Agent without writing a single line of code in a little over an hour. Features: - AI powered autocomplete - AI powered image search with autosuggestions based on what i'm writing - Ai powered research based on what i'm writing - Block based writing (which is useful for my workflow as a video content creator) !!! And I ran it locally this time. Normally I use replit, so if you got stuck on connecting cursor and replit, this video is for you. Template pinned on @senior_swc (starting point you can download) Tools used - Cursor (Claude for ai model) - Firebase - Deepseek DeepSeek - Exa ( Exa ) - Search API These videos serve as R&D for the app we're building at @yapthread. We're building the cursor for content creators. Sections 00:00 Introduction 03:24 Introduction to the Template 03:54 Setting Up Locally 04:04 Downloading and Running Locally 05:34 Firebase Setup 06:10 first prompt in cursor + continuing firebase 08:11 Full Plan for the app I'm building 10:44 Outlining the app hotkeys 11:55 Testing First Feature 16:54 Adding Autocomplete Feature Deepseek 22:23 Adding Images to Blocks (Search API) 22:42 Implementing and Testing Image Search (Search API) 25:32 Adjusting Image Sizes and Social Media Discussion 28:11 Adding Relevant Links (Exa API) 30:34 Testing and Debugging Link Highlights 32:27 Finalizing Image and Link Integration 40:37 Conclusion and Future Plans

Riley Brown

83,096 views • 1 year ago

Cursor Agent is just insane! In a little over an hour, without writing one line of code I created a YouTube Super Analytics Tool and I filmed the whole process... This is a full step by step guide on how to use Cursor Agent to build whatever you want with zero coding... As always I used the @senior_swc nextjs template as a starting point that has been forked over 11,000 times. (in next tweet below) Tools used: - Cursor: Duh - Replit: Template, web view and deployment - Deepseek API: High quality AI Model (Cheap and better than gpt) - SupaData API: Pull YT Transcripts - SerpAPI: Search YouTube Results - Firebase: DB and Auth Chapters: 00:00 - YouTube Power Tool In Action 03:00 - Planning Phase (How I diagram and plan) 04:58 - Features I'm adding 06:20 - Setting Up APIs and Tools 10:00 - Developing the YouTube Transcript Extractor w/ Supadata + Deepseek 19:58 - The YouTube Search Feature (SerpAPI) 29:41 - Setting Up Google Firebase (DB + Auth) 32:00 - Implementing Search and Save Features 36:50 - Styling and UI Enhancements 49:00 - Final Result 53:40 - These features are being added to @yapthread but way better (First look at composer feature)

Cursor Agent is just insane! In a little over an hour, without writing one line of code I created a YouTube Super Analytics Tool and I filmed the whole process... This is a full step by step guide on how to use Cursor Agent to build whatever you want with zero coding... As always I used the @senior_swc nextjs template as a starting point that has been forked over 11,000 times. (in next tweet below) Tools used: - Cursor: Duh - Replit: Template, web view and deployment - Deepseek API: High quality AI Model (Cheap and better than gpt) - SupaData API: Pull YT Transcripts - SerpAPI: Search YouTube Results - Firebase: DB and Auth Chapters: 00:00 - YouTube Power Tool In Action 03:00 - Planning Phase (How I diagram and plan) 04:58 - Features I'm adding 06:20 - Setting Up APIs and Tools 10:00 - Developing the YouTube Transcript Extractor w/ Supadata + Deepseek 19:58 - The YouTube Search Feature (SerpAPI) 29:41 - Setting Up Google Firebase (DB + Auth) 32:00 - Implementing Search and Save Features 36:50 - Styling and UI Enhancements 49:00 - Final Result 53:40 - These features are being added to @yapthread but way better (First look at composer feature)

Riley Brown

203,226 views • 1 year ago

EXCLUSIVE: Microsoft just launched Copilot Vision in Edge—the first AI that can navigate the internet with you in real time. I sat down with Mustafa Suleyman (CEO of Microsoft AI) to discuss how it works, infinite memory, AI companions, agents, and more. Timestamps: 0:00 Intro 0:58 Microsoft Copilot Vision rundown 02:35 Initial reactions and use cases 04:57 How Copilot Vision works 06:02 Teaching AI to remember 08:13 How Microsoft AI is differentiating from OpenAI 09:27 The push for the true AI companion 11:28 Living with a co-intelligence in 10+ years 14:04 How Microsoft handles your data 16:11 When and how can you try Copilot Vision? 18:15 Agentic AI that controls your computer 20:25 What's next: support, gaming, and more 22:34 Preparing the next generation with Copilot 25:11 Mustafa’s advice for students and businesses

EXCLUSIVE: Microsoft just launched Copilot Vision in Edge—the first AI that can navigate the internet with you in real time. I sat down with Mustafa Suleyman (CEO of Microsoft AI) to discuss how it works, infinite memory, AI companions, agents, and more. Timestamps: 0:00 Intro 0:58 Microsoft Copilot Vision rundown 02:35 Initial reactions and use cases 04:57 How Copilot Vision works 06:02 Teaching AI to remember 08:13 How Microsoft AI is differentiating from OpenAI 09:27 The push for the true AI companion 11:28 Living with a co-intelligence in 10+ years 14:04 How Microsoft handles your data 16:11 When and how can you try Copilot Vision? 18:15 Agentic AI that controls your computer 20:25 What's next: support, gaming, and more 22:34 Preparing the next generation with Copilot 25:11 Mustafa’s advice for students and businesses

Rowan Cheung

268,106 views • 1 year ago

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Let's keep benchmarking with the Night train this time, with GPT-6 Sol and GPT-6 Luna, so here are all four! 🚀 I gave each model the exact same prompt: “Build a Night train.” •Opus 5.5 • GPT-6 Astra • GPT-6 Sol • GPT-6 Luna Something that really surprised me: GPT-6 Sol produced almost the exact same rocket launch as Opus 5.5! The colors are slightly different, but the overall result is remarkably similar. For this prompt, I’d even put Sol ahead of Astra. I’m seriously impressed by Sol, especially at half the API price of Opus 5.5! 🤯 I’m starting to use this approach in my own workflow. I kept one Codex subscription so I can run a bunch of Sol sub-agents while keeping my main agent on Astra. Sol is so cheap for what it can do! Knowing when to switch models based on the task, the quality you need, and the cost is becoming an essential skill in this new AI era.

Tony

112,633 views • 8 days ago

I feel burned out having to manage context for my agents/harnesses/runtimes. And what "grinds my gears" is the fact that Astra will burn through my usage simply due to loading a plethora of skills. I spent time to make sure the previous models like Sol are able to meet my production bar... As of today, it feels like I have to throw that out or manage that between two model types. I thought we had AI to help us with this? Shouldn't this be the job of the model provider especially if I use their harness? But Ray, you just have to...(do new undocumented thing) and it'll just work. BRUHHHHHH you drop models/updates every few weeks and keep changing this. Now repeat for the last 6 months... Cursor Projects just dropped their beta and I'm starting to see where the puck is going with a workflow like this. I can design what happens from PRs, bug fixes, testing, and the entire SW Dev lifecycle without living in a terminal or managing skill files. This is going to save me lots of time as my project evolves and I don't have to spend much time maintaining skill files or handing off things between agents. I can switch models and ship software like a professional. Here is my first look at Cursor Projects and I'm very bullish on where this is going. Timestamps 00:00 This Thing Called Projects 00:44 Grok Bot Went Crazy Viral 01:53 Grok Bot Forgets Sometimes 02:55 The Project Page 04:10 Agents, PRs, and Listening 06:02 The Exec Status Board 08:41 Files That Live on the Cursor Side 10:35 The Same Chat on My Phone 11:26 Still in Beta, Cloud First

I feel burned out having to manage context for my agents/harnesses/runtimes. And what "grinds my gears" is the fact that Astra will burn through my usage simply due to loading a plethora of skills. I spent time to make sure the previous models like Sol are able to meet my production bar... As of today, it feels like I have to throw that out or manage that between two model types. I thought we had AI to help us with this? Shouldn't this be the job of the model provider especially if I use their harness? But Ray, you just have to...(do new undocumented thing) and it'll just work. BRUHHHHHH you drop models/updates every few weeks and keep changing this. Now repeat for the last 6 months... Cursor Projects just dropped their beta and I'm starting to see where the puck is going with a workflow like this. I can design what happens from PRs, bug fixes, testing, and the entire SW Dev lifecycle without living in a terminal or managing skill files. This is going to save me lots of time as my project evolves and I don't have to spend much time maintaining skill files or handing off things between agents. I can switch models and ship software like a professional. Here is my first look at Cursor Projects and I'm very bullish on where this is going. Timestamps 00:00 This Thing Called Projects 00:44 Grok Bot Went Crazy Viral 01:53 Grok Bot Forgets Sometimes 02:55 The Project Page 04:10 Agents, PRs, and Listening 06:02 The Exec Status Board 08:41 Files That Live on the Cursor Side 10:35 The Same Chat on My Phone 11:26 Still in Beta, Cloud First

Ray Fernando

42,108 views • 20 days ago

Sam Altman on OpenAI’s next model and the AI backlash I recently sat down with Sam for a two-part conversation. We covered a lot of ground: the need to slow down frontier research, alignment concerns, OpenAI's next big model, Astra, competition with Anthropic, his thoughts on an IPO, reaching AGI, consumer hardware, and a lot more. Timestamps: 00:00 Why OpenAI Slowed Training 08:37 What Alignment Means 15:22 Keeping Humans in Control 24:39 AGI vs. Superintelligence 30:04 OpenAI’s Next Compute Bet 31:47 AI Backlash, Jobs, and Creators 41:31 OpenAI’s Missteps and Refocus 45:47 Astra and Computer-Using Agents 47:42 Regulation and the AI Race 51:24 Merging ChatGPT and Codex 54:22 The AI Compute Bubble 57:07 Recursive Self-Improvement and IPO 58:22 Humanoid Robots and Consumer Devices 1:05:47 Life After Superintelligence This episode was produced in partnership with TIME. Thanks to the show's premier sponsors: Atlassian, Granola, and Mercury.

Sam Altman on OpenAI’s next model and the AI backlash I recently sat down with Sam for a two-part conversation. We covered a lot of ground: the need to slow down frontier research, alignment concerns, OpenAI's next big model, Astra, competition with Anthropic, his thoughts on an IPO, reaching AGI, consumer hardware, and a lot more. Timestamps: 00:00 Why OpenAI Slowed Training 08:37 What Alignment Means 15:22 Keeping Humans in Control 24:39 AGI vs. Superintelligence 30:04 OpenAI’s Next Compute Bet 31:47 AI Backlash, Jobs, and Creators 41:31 OpenAI’s Missteps and Refocus 45:47 Astra and Computer-Using Agents 47:42 Regulation and the AI Race 51:24 Merging ChatGPT and Codex 54:22 The AI Compute Bubble 57:07 Recursive Self-Improvement and IPO 58:22 Humanoid Robots and Consumer Devices 1:05:47 Life After Superintelligence This episode was produced in partnership with TIME. Thanks to the show's premier sponsors: Atlassian, Granola, and Mercury.

Alex Heath

547,265 views • 1 month ago

How OpenAI Builds for 800 Million Weekly Active Users: Model Specialization and Fine-Tuning We sat down with Sherwin Wu, Head of Engineering at OpenAI Platform, to discuss OpenAI’s developer strategy, how to manage top ML teams, why they decided to start releasing open-weight models again, how prompt engineering has evolved over time, and how developer tools will shift to accommodate better agents moving forward. 00:00 Introduction 8:36 Horizontal vs vertical OpenAI 12:18 Why you can’t “disintermediate” the model 15:11 People build relationships with models 17:30 Not one AGI model but many 20:10 Fine-tuning, RFT, and customer data choices 24:44 Prompt engineering isn’t the point anymore 28:06 What an “agent” really is 31:55 How OpenAI thinks about pricing 36:46 Why open-weights don’t kill the API 42:57 Different stacks for text, images, video 45:47 How the agent builder actually works Sherwin Wu martin_casado

How OpenAI Builds for 800 Million Weekly Active Users: Model Specialization and Fine-Tuning We sat down with Sherwin Wu, Head of Engineering at OpenAI Platform, to discuss OpenAI’s developer strategy, how to manage top ML teams, why they decided to start releasing open-weight models again, how prompt engineering has evolved over time, and how developer tools will shift to accommodate better agents moving forward. 00:00 Introduction 8:36 Horizontal vs vertical OpenAI 12:18 Why you can’t “disintermediate” the model 15:11 People build relationships with models 17:30 Not one AGI model but many 20:10 Fine-tuning, RFT, and customer data choices 24:44 Prompt engineering isn’t the point anymore 28:06 What an “agent” really is 31:55 How OpenAI thinks about pricing 36:46 Why open-weights don’t kill the API 42:57 Different stacks for text, images, video 45:47 How the agent builder actually works Sherwin Wu martin_casado

a16z

114,095 views • 10 months ago

My Crypto Portfolio once had 36 altcoins, but instead of selling them for stables, I decided to consolidate my holdings into fewer coins (I'm still exposed to the market), where the current total is now 12. So here's what I'm holding, and what I expect for the rest of the year. 03:27 Why I sold many Altcoins for $BTC, $ETH, $SOL 06:26 Bitcoin Analysis 08:58 Ethereum Analysis 10:38 Solana Analysis 12:20 Why I'm consolidating my portfolio 14:25 $SUPER 17:19 $BEAM 19:54 $NEAR 20:48 $TAO 22:40 $AXL 25:22 Looking for more RWA exposure 27:04 $AMPL 31:18 $BORG 34:49 $PEPE 38:08 When can Altcoins bounce back based on Liquidity? 41:45 The next 6 months will be dangerous 45:17 How to track global liquidity 50:37 My Portfolio Strategy Summary

My Crypto Portfolio once had 36 altcoins, but instead of selling them for stables, I decided to consolidate my holdings into fewer coins (I'm still exposed to the market), where the current total is now 12. So here's what I'm holding, and what I expect for the rest of the year. 03:27 Why I sold many Altcoins for $BTC, $ETH, $SOL 06:26 Bitcoin Analysis 08:58 Ethereum Analysis 10:38 Solana Analysis 12:20 Why I'm consolidating my portfolio 14:25 $SUPER 17:19 $BEAM 19:54 $NEAR 20:48 $TAO 22:40 $AXL 25:22 Looking for more RWA exposure 27:04 $AMPL 31:18 $BORG 34:49 $PEPE 38:08 When can Altcoins bounce back based on Liquidity? 41:45 The next 6 months will be dangerous 45:17 How to track global liquidity 50:37 My Portfolio Strategy Summary

VirtualBacon

157,186 views • 1 year ago

In this livestream I break down the OpenClaw AI agent narrative from the operator’s perspective: what it actually is, why it’s different from ChatGPT/Grok/Claude Code, and why “it’s just automation” misses the real shift. We cover the practical unlocks (local execution, persistent memory, computer-use + browser control, reusable skills/plugins) and why this design pattern can replace a lot of expensive SaaS workflows over time. Then I zoom out to the crypto angle: why the market will mint endless OpenClaw “slop” coins, how I think about separating infra from hype, and the two names I’m watching (BNKR + CLAWD). 00:00 Why the OpenClaw AI agent narrative is bigger than you think 00:39 Two-part video: OpenClaw productivity first, crypto narrative second 01:30 What OpenClaw is (an AI agent framework, not a chatbot) 01:44 Why ChatGPT, Grok, and Claude Code are still useful but incomplete 03:19 OpenClaw vs n8n and Zapier for automation 05:03 Why Zapier pricing breaks real businesses 06:07 Why running locally matters (any app, any chat platform) 07:56 Persistent memory: how agents learn your style over time 09:55 Computer-use agents: browser control and no-API workflows 11:27 Skills and plugins: reusable workflows that self-improve 13:52 The simple setup and why model choice is flexible 16:05 Cross-platform ops: Telegram, Slack, Discord, and email in one brain 20:52 Why AI SaaS tools get replaced by agent-built workflows 25:37 What this is not: no AGI, no “sentient” coin story 29:55 How to approach the OpenClaw coin wave (infra over slop) 32:43 BNKR and CLAWD: my two picks for exposure to the narrative

In this livestream I break down the OpenClaw AI agent narrative from the operator’s perspective: what it actually is, why it’s different from ChatGPT/Grok/Claude Code, and why “it’s just automation” misses the real shift. We cover the practical unlocks (local execution, persistent memory, computer-use + browser control, reusable skills/plugins) and why this design pattern can replace a lot of expensive SaaS workflows over time. Then I zoom out to the crypto angle: why the market will mint endless OpenClaw “slop” coins, how I think about separating infra from hype, and the two names I’m watching (BNKR + CLAWD). 00:00 Why the OpenClaw AI agent narrative is bigger than you think 00:39 Two-part video: OpenClaw productivity first, crypto narrative second 01:30 What OpenClaw is (an AI agent framework, not a chatbot) 01:44 Why ChatGPT, Grok, and Claude Code are still useful but incomplete 03:19 OpenClaw vs n8n and Zapier for automation 05:03 Why Zapier pricing breaks real businesses 06:07 Why running locally matters (any app, any chat platform) 07:56 Persistent memory: how agents learn your style over time 09:55 Computer-use agents: browser control and no-API workflows 11:27 Skills and plugins: reusable workflows that self-improve 13:52 The simple setup and why model choice is flexible 16:05 Cross-platform ops: Telegram, Slack, Discord, and email in one brain 20:52 Why AI SaaS tools get replaced by agent-built workflows 25:37 What this is not: no AGI, no “sentient” coin story 29:55 How to approach the OpenClaw coin wave (infra over slop) 32:43 BNKR and CLAWD: my two picks for exposure to the narrative

VirtualBacon

22,428 views • 7 months ago

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!

How to start your Hermes AI Agent (step-by-step guide for beginners) I'm a beginner, and I spent the last 24h: > Understanding the process > Launching my Hermes Agent (Nous Research) > Recording the whole process > Editing this step-by-step guide So you can do it yourself and understand everything in less than 1 hour! 00:00 Intro 00:38 What is Hermes ? Key concepts every beginner should know 01:16 What is a VPS ? 02:00 What is SSH ? 03:52 What is the Terminal ? 04:03 What is an LLM provider ? 04:37 What is an API key ? 04:52 What is the Terminal Backend 05:34 What is the Messaging Gateway ? 06:10 What is the Memory System ? Step-by-step: Launch your Hermes AI agent 06:53 Step 1 : Get your VPS 08:04 How to generate an SSH key 09:00 Step 2 : Connect to your VPS 10:32 Step 3 : Install Hermes Agent 14:34 Connect your agent to Telegram 17:12 How to fix a mistake during the process 17:48 Gateway testing 18:17 Telegram is working 18:31 Run your agent 24/7 19:16 Thank you Make sure to save this for later and share it with friends who want to start with AI agents. Thanks to Teknium 🪽 for being so active!

Theo

34,057 views • 6 months ago