I’m joining OpenAI Codex to work on the future... of agentic development! At Cursor, I got to see the shift from autocomplete to agents. The next step isn’t a better IDE. It’s an Agent Development Environment (ADE): systems and tools for orchestrating agents, reasoning over their outputs, and making them autonomous enough to reliably complete ambitious work. After chatting with Alexander Embiricos and Tibo, it was clear that Codex is the best place to realize this vision. The team has consistently shipped SOTA models for agentic coding (check out gpt-5.3-codex) and I’m pumped for the future that the new Codex App points to. What I’m most excited about is the broader mission: accelerating the knowledge work economy. All agents are coding agents, and we’re already seeing Codex used across every job function within organizations. I’m extremely grateful for my time at Cursor, working with the incredible team, and I’m proud of what we built together. I’m excited to take an even bigger swing with Codex. If you’re curious to get a glimpse of where we are headed, download the Codex App! If you want to work on this mission, please apply or reach out - we are hiring across all functions! You can just build things.show more

I’m excited to share that I’m joining the team... at Lovable ✨ I’m incredibly grateful for the opportunity to work with this unbelievably talented team—and I can’t wait to show everyone what we’re working on!show more

After a weekend of testing and working on something... with GPT-5.3-Codex & Opus 4.6, ChatGPT Pro + Claude Max 5x are still the best combo in my opinion Using Codex & Claude Code CLI running in tmux (the desktop apps are still a bit buggy) and they're accessible even on the go from iPhone with Termius (and VPN) Usually starting with GPT-5.3-Codex xhigh and Opus 4.6 in plan mode, discussing changes and options, and each writing their plans down to separate Markdown files Then letting GPT-5.3-Codex xhigh (or Opus 4.6) implement the changes as the first draft, then Opus 4.6 reviews them with a team of agents (works pretty well already with tmux even though still experimental) based on both prepared plans, fixes stuff, and then another review by GPT-5.3-Codex xhigh or vice versa Interesting that even Opus 4.6 still occasionally makes silly mistakes like wrong imports, partial or overly broad renaming of variables/functions, etc Fun fact, OpenAI apparently plans to use their Super Bowl ad to promote Codex - curious what that will look likeshow more

Today is my first day at OpenAI! I'm joining... the Codex team. I'll be splitting my time between building the Codex app and working with developers/entrepreneurs to help them make the most of Codex. As a Y Combinator alum, I'm really looking forward to working with early-stage startups and couldn't be more energized about OpenAI's $2M investment in new YC startups. Despite OpenAI being the largest company I've been part of, it certainly feels like Sam Altman, Greg Brockman and the whole Codex team are in founder mode. I've never seen another startup move as fast as this team does. I'm truly honored to be joining such a brilliant team. As always, it's all about the people... so I'd like to thank Romain Huet, dominik kundel, corey.ching, Andrew Ambrosino, Alexander Embiricos, Tibo, and the rest of the Codex team for their trust. And thanks to Pankaj Gupta, Gilad Mishne, and Will Horn for believing in me, bringing me back to Silicon Valley after almost ten years, and giving me the opportunity to learn about AI.show more

HTML Artifacts are a big part of how I... work with agents now. Artifacts can be more than just static files. When combined with agents, they can take action or help you take action. This unlocks all kinds of interesting ways to work with agents. This is clearly the future. Check out this writing and scheduler artifact I built in a few minutes. It uses a bit of HTML and JS. All the data is in markdown (Obsidian vaults), so the agent can access and modify it at any time. No DB needed. No sophisticated functionalities. The agent decides all that for me based on the skills, context, and memory it has access to. The best part about this simple stack is that all the important information stays with me. This has allowed me to build a recursive self-improving system and automations that can better tap into coding agents like Codex or Claude Code. I could have paid or built an entire app for scheduling posts, and there are so many of them out there. But I don't need to. I've realized a simple artifact does the job. And the simplicity of it is actually an advantage. Very little maintenance for very high returns on personalization, time, and efficiency. The other benefit of this is that I can add features as I please. That level of personalization feels magical, and we should all be pursuing more of it. All of this just keeps compounding. Of course, this example is just about writing. But I have similar artifacts for research, design, experimentation, evaluation, and so much more. And no, I didn't actually publish the post example I shared in the clip. It was just for demonstration purposes. I actually spend more time than this when writing together with agents. Lastly, having built my own agent orchestrator tool has made me realize that simplifying the tool stack is a superpower. If you are curious about how all this works, I will do a live session next week:show more

Alrighty, everything is ready 😎 here’s an unofficial “2x... Codex limits” promo from my side for you all. meet DevSpace — an MCP connector app that turns ChatGPT into Codex. npm install -g @waishnav/devspace After installing, tunnel the MCP server over the internet and enjoy 2x limits. You can use GPT-5.5 Pro, xHigh, or High for planning, then hand off the task to your local Codex/pi/opencode/cursor/claude code instance. Or you can just use it for reviewing code written by other local coding agents Go ahead, experiment with different workflows, and keep the feedback coming on GitHub Issues or in my DMs And let’s thank OpenAI for being so generous by giving us separate ChatGPT and Codex limits and by being so chill around this MCP :) Please use it sparingly, only when you run out of limits. Don’t overuse it — in the end, they do have a button to stop it 🙂show more

I’m excited to announce that I’m joining the Rainbow... Six Siege team as a Game Ambassador! I’ve been a huge fan of Siege for the last 8 years and have over 3,000 hours of playtime. We approached Ubisoft to work together and can’t wait for you all to see what we’ve been up to.show more

Excited to launch a new way to upskill with... AI agents. This is how we are making it possible for anyone to learn to build with coding agents. To start, we are launching 4 new hands-on labs on the following topics: - Agent Skills - Agentic Image Generation - 30 Days of Hermes Agents - Prompt Engineering with Agents I am confident that with our new DAIR.AI platform, anyone can learn to become a top AI builder by building and acquiring highly-demanded AI skills. And there is a lot more landing in the coming weeks.show more

🌠Today, we’re excited to relaunch Airtable as the AI-native... app platform, combining the magic of vibe coding business apps with real production-readiness and scalability, and embedding them with an army of agents that automate thousands of hours of work in seconds. Instead of just adding more AI capabilities to our existing platform, we treated this as a refounding moment for the company. We started with a clean-slate imagining of the ideal form factor for building apps in the agentic era. (If you want to skip all the backstory and just try it out, you can just go to All new signups get the new AI experience, and existing accounts can switch over using this link: Thread and demos below👇show more

🚨 do you understand what OpenAI just announced.. ChatGPT... Pro is now $100/month. 10x more Codex usage. and Codex isn't autocomplete - it writes, debugs, builds entire apps. autonomously. if you've used Claude Opus for coding you know the feeling. Codex hits the same way. except Claude Opus limits burn through in hours. you blink and you're out. Codex just got a $100 tier built to run 24/7. no cooldowns. no "you've reached your limit" at 2am mid-build. they're not selling you a chatbot. they're selling you a software engineer that never sleeps and never asks for equity. and they're doing it quietly while everyone argues about tariffs.show more

I’m incredibly proud to share that OpenAI chose Brex... to power their global spend and financial operations. When you're building at the frontier of AI and scaling global teams and infrastructure at an unprecedented pace like OpenAI is, Finance can't be the thing that slows you down. You need spend visibility the moment it happens, controls that enforce themselves, and agentic workflows that eliminate the manual work so your team stays focused on driving the business forward. We were so impressed by OpenAI’s rigor in evaluating every solution in the market, and whether they align to the agentic future OpenAI is building. Their decision to run on Brex is a huge testament to our AI roadmap and vision for the future of Finance. We started Brex around a simple idea: companies shouldn't have to choose between speed and control. There's no company in the world where that tradeoff matters more than OpenAI. We are honored to support them as they build the future. The best AI companies in the world, including OpenAI, Anthropic, Cursor, Vercel, Granola, Sierra, and Mercor choose Brex over every alternative for that exact reason. If you want to understand who’s truly building the future of AI in Finance, follow the customers you admire the most – not the hype.show more

Our @Grammarly AI agents are here! Today, we’re launching... eight new AI agents designed for students and professionals. We created many of these agents with students in mind because they’re the first generation entering a job market where employers expect both subject expertise AND AI fluency. These agents help with everything from finding credible sources to predicting reader reactions. One agent we’ve gotten great feedback on is AI Grader (I wish I had this in school), which you can see in the video below. It looks at your assignment rubric and gives you suggestions like your professor would, and a grade prediction before you submit your work. And these agents are available in docs, our new AI-native writing surface! I’m deeply proud of this launch—docs is powered by Coda (Superhuman Docs) technology and is a great integration moment between Grammarly and Coda. This is just the beginning of Grammarly’s journey to offering agents that work everywhere people work and collaborate. I’ve been loving using these agents, and I’m excited for our customers to get access. Try them for yourself here and let me know what you think:show more

I went a little overboard with Codex last week... and burned through my entire weekly allowance in two days. Luckily, my quota reset today. Otherwise, I’m not sure what I would’ve done. It got me thinking: instead of asking one large model to handle everything from start to finish, why not let a stronger model plan the project and review the work, while a model built for execution handles the day-to-day implementation? So I tried it. The result was better than I expected. I used GPT-5.6 Sol in Codex as the decision-maker, then ran Ling-3.0-flash from Ant Ling inside OpenCode as the execution engine. Together, they built a small 3D farming game. Before writing any code, I had Codex create four documents: SPEC.md defined the product scope and the lines we couldn’t cross. ARCHITECTURE.md laid out the isometric coordinate system, state machine, and module boundaries. TASKS.md broke the project into small jobs Ling could tackle one at a time. ACCEPTANCE.md explained how each step would be tested and what “done” actually meant. Then I gave Ling a very straightforward role: You are the execution model for this project. Read all four documents before you begin. Work only on the task assigned for this round. When you’re done, run typecheck, test, and build. If anything fails, read the error, fix it, and run the checks again. Do not move on to the next task early. Ling handled dependency installation, project structure, strict TypeScript configuration, test setup, and a production build in 6 minutes and 3 seconds. It ran into issues with the Vite test config, a TS6310 error, and a missing jsdom dependency along the way. Instead of stopping at the first error, it kept reading the logs and fixing the problems until all three checks passed. The speed was honestly hard to believe. If you exclude the time spent waiting on tools, it was producing more than 100 tokens per second. That made the whole development loop feel noticeably faster. After this experiment, I’m planning to keep using the same workflow. If the task is small, there’s no reason to call an expensive planning model for every single step. If the task is large, handing the entire project to a Flash model in one prompt isn’t a great idea either. The setup that makes more sense to me is: Use a more capable model such as Codex to explore the project, make architectural decisions, and break the work down. Put the constraints into specs, schemas, types, and tests instead of leaving them buried in chat history. Give Ling-3.0-flash a steady stream of clear, verifiable implementation tasks. Report bugs with structured context and actual error logs, rather than saying, “It still doesn’t work.” Bring Codex back in for architecture reviews, visual checks, and changes that affect multiple parts of the project. The point of this setup isn’t to give AI a big “build the whole project” button. It’s to turn software development into a pipeline with a much more sensible cost structure: Codex figures out the plan, sets the boundaries, and catches problems. Ling-3.0-flash moves quickly, calls tools reliably, and works through well-defined tasks at scale. For agent workflows that involve lots of repetitive edits, production tasks, and tool calls, this may be a more practical answer than simply using the biggest model for everything.show more

GITHUB JUST KILLED THE WORST PART OF VIBE CODING... they shipped a free tool called Spec Kit and it already crossed 120,000 stars the fix is stupidly simple instead of tossing vague prompts at an agent and praying it doesn't wreck your project Spec Kit makes the AI write a full structured spec before it touches a single line of code it works through the problem first figures out what you want to build asks about the gaps lays out the project then it starts coding you get fewer insane bugs, cleaner output and results you can predict the flow looks like this: /constitution for your rules and standards /specify for what you want to build /clarify for the open questions before you start /plan for architecture and stack /tasks for the ordered work /implement to run it it plugs into Claude Code, Cursor, Copilot, Codex, Gemini CLI and 25+ other agents 120,000 stars, 10,000 forks, open source, shipped by GitHub itself learning to drive agents like this is most of what separates people getting hired as AI engineers from everyone still fighting their promptsshow more

Back where it all started 🧡 16 years ago... as a freshman at FLORIDA, I walked into the @ESPNGainesville studios and asked if there were any jobs on the radio. Steve Russell (in the first pic) was kind enough to give me a shot. Today I got to sit next to him again to do what we did so many times while I was in college: talk ball. Years full of hard work, failure, a little success, smiles, tears and lots of lessons learned have gone by but one thing remains the same: I’m extremely grateful for the people who formed the foundation of my career and the place (FLORIDAJSchool) where it happened. What a joy it was to spend time with the future of our business today. You are all stars and I’m proud to call you fellow gators. Your eagerness, dedication and curiosity is a reminder of how lucky we are to talk about sports for a living. It was an honor to spend some time on the campus that built me.show more

OpenAI _always_ releases very high quality, polished UIs. The... codex app is the least polished I've seen from them (takes 2-3 seconds to change a thread), animations are off, jumping all around the place.. It's not fluid - at all. which we 100% vibe coded (within 4 weeks, including holidays!) with the goal of being an internal tool is miles ahead. This tells me a few things : 1. You can't brute force UI quality with today's models. You need deep care, and expertise. 2. One person teams can out-execute even the largest labs, thanks to AI. Note : Craft Agents is a non-commercial, open source project, and I am well aware that codex is going to reach 100-1000x people, will rapidly improve, and it's success is not tied to these UI glitches. Above observations still stand.show more

Very pleasantly surprised to discover Cursor cloud agents can... playtest the godot game I built. See the (sped up) video below of the agent playtesting the game. As I was watching it play the game, I can see the agent slowly learn how the game works and familiarise with the game's UI. I also realised that the agent is a very 'safe' player, choosing to play very safely and retreating from battle if it foresees it can't defeat. Very interesting to see. I wonder if I could simulate different game playtester behaviours that mimic different types of real-world player archetypes. With agentic playtesting, this means that the agents are able to provide actual gameplay feedback and suggestions to improve the game, having played the game itself. This unlocks a whole lot of possibilities for AI-assisted game dev, since it closes the playtest loop. This feels like the future of recursive game development, where agents can now recursively build > playtest > improve the games they are working on. Thanks edwin for letting me know that these agents can actually playtest games, not just software! Very excited to dig deeper to see what I can do with these agents with computer access!show more

Multi-agentic/player pair programming idea sketch in 10 mins —... a real-time Tuplesque experience where I can share the screen w/ AIs, directly point it out to code or sketch together on a whiteboard, have an instant groupchat to debug with voice, AI has access to Cursor that could also use its tools to speed up the work. We can all naturally interrupt each other and have fun together. We are all collaborating, shipping features, and leveraging each other’s strengths (eg if Claude is better at frontend it should handle that part of the stack). That’s the pair programming / real agentic coding I’d love to use!show more

Polari. This is track 1 on the album and... is intended as a shot of adrenaline and jumpstart the car kind of introduction because I’m about to take you for a ride - it’s also a bit of an audio collage of all the music that follows so I’m very excited to put this out! Please enjoy!show more

Replit, Vercel, and OpenAI have built very cool agent-native... applications, but nobody else has passed the demo stage. Building agents that work is complex. Teams aren't shipping agents because we don't have good tooling yet (and most of us don't know how to do this well.) A couple of days ago, the CopilotKit🪁 team announced a collaboration with . You can now use LangGraph with CoAgents to build agent-native applications, and here is everything you need to know about that: CoAgents is fully open-source, and you can use it to do the following: • Human-in-the-loop to steer and correct the agent • Stream intermediate agent state • Real-time state sharing between the agent and the application • Agentic generative UI to build trust that the agent is on the right path Start this GitHub Repository: Thanks to the team for giving me early access and collaborating with me on this post.show more

With our season being over my contract with Team... Vitality 🐝 has ended It has been a rocky journey and through each challenge it has been a test of who we are and what we’re made of. I can personally say that the work ethic of the team cannot be put to question and everyone was willing to go over and above to get us to where we wanted to be. It can feel like all the work had no reward, but I truly believe that the work is an investment for a lifetime and not just a season. To the fans, we know it is disappointing and we really dreamed of that fairy tale story in Paris. For now the players, coaches and staff appreciate the support that has been given and even I could feel the warmth of the well wishes and welcomes I received when I joined the org. I will appreciate the memories of everyone here that will last me a lifetime. I’m very grateful to have been here and to have been part of the vitality story💛 🖤🐝show more