Open sourcing your product is hard, especially after you've reached nearly 1M developers🤯 That's exactly what @zachlloydtweets & the @warpdotdev team did! In our latest episode, @robby_mtf & @tnachen dig into: ⚡ Rebuilding the terminal from first principles ⚡ Scaling Warp to nearly 1M developers ⚡ Why the AI era changed their open source strategy A must-listen for software infra & devtool founders thinking about product strategy in the age of AI🤖

If you're automating any part of your software development lifecycle (i.e. loops or software factories), you should be on the lookout for these flags: 🚩 Single model or single harness solutions: this is a form of lock-in that will give the model provider leverage over prices, and will make it harder to tune the token costs for your SDLC overtime. Data ownership: make sure that whatever vendor you use doesn’t capture or train on your data. All the data flowing through the SDLC should be owned and housed by your company. Compute inflexibility: you probably want a variety of different hosting solutions, including self-hosting. Forced token reselling: vendors should allow you to bring your own inference endpoints (e.g. Bedrock, Vertex and Azure) and generally not be in the business of selling or re-selling tokens alone. Folks in the token selling business are going to have a conflict of interest when it comes to optimizing your costs, so it’s better to pick a vendor that is agnostic to whether you buy inference through them.

one of my first blog posts, on how i much prefer working with engineers who focus on building the product more than writing the code. in the world of agents this matters more than ever and is arguably going to become all that matters

All episodes of Season 1 of The General Podcast are out now. Big thank you to every guest who made our first season what it was: @reidhoffman x @johnolilly @chrisbest x @AndrewMayne @chrissyfarr x @DrSidMukherjee @danshipper x @alexrkonrad @chughesjohnson x Gretchen Howard @brian_lovin x @wjosephflynn @MerrillLutsky x @zachlloydtweets @bingfish x @stephenpiron @annaebinder x @ericagalioto @lil_dill x @randyjhunt We made this “hostless” show around the simple idea that the best conversations in tech don’t always happen in interviews or on panels, but between peers at the very top of their craft. Season 2 now loading…

@steipete is now joining us for Crafting Software Factories! 📅 6pm Wed evening in SF after the @aiDotEngineer World's Fair He'll be joining @zachlloydtweets and Paige Bailey from Google DeepMind to chat all-things loops, software factories, and the future of coding

Warp's founder @zachlloydtweets thinks every major software project will soon run on an automated "factory." I caught up with Lloyd on the expo floor of the @aiDotEngineer World's Fair, to discuss why & how engineers should prepare for this shift.

Thanks @AllThingsOpen for letting us share the way we manage open-source at Warp! The pace of progress is wild. Now at 600+ contributions across 96 contributors in just a few weeks.

Join me live with the @claudeai team! We're discussing self-improvement loops - how to improve agent skills based on feedback overtime. It's the backbone of our agent management process for Warp's open-source repo.

Working on a new way to orchestrate agents. - Agent makes a delegation plan with subagent tasks - Run subagents locally, or in Dockerized cloud environments - Subagents send and receive messages as they work Run /orchestrate or let the agent use the delegation tool. Wdyt?