Ryan Carson
@ryancarson • 183,420 subscribers
Dad, Dev, CEO, 4x Founder. Building @HelloUntangle
Shorts
Videos
Holy shit, just had a feel-the-AGI moment. Symphony was running overnight, working on merging a bunch of PRs, and it encountered some extra issues in the codebase that were related to PR but not directly applicable. It created a backlog issue in Linear and documented it. 😳 What's even more amazing about that is now I can simply drag that issue into the "To Do" column in Linear, and Symphony will automatically pick it up, start working on it, and ship it.
Ryan Carson87,779 просмотров • 2 месяцев назад
Getting the entire Harness Engineering system setup for my repo and it's blowing my mind. It even identifies when UI was changed and records a video of testing in the browser and adds those videos to the PR for me to review. I'm using this setup as a guide:
Ryan Carson71,543 просмотров • 3 месяцев назад
This is how I’m currently running my startup with Devin + OpenClaw🦞 The browser testing in Devin is mind-blowing. I was trying to duct tape and jerry-rig all this stuff together with Playwright + uploading videos to PRs and all sorts of stuff and Devin just does it all e2e. Wild. I didn't show how I'm using Linear, which I am using for issue tracking. I have a "land" skill that I tell Devin to use whenever all the browser testing is done and all the CI goes green and it just merges the PR
Ryan Carson28,133 просмотров • 2 месяцев назад
Here’s how I use Agentation + queuing messages in Codex to crank through frontend work much faster
Ryan Carson31,776 просмотров • 3 месяцев назад
A new agentic browser just shipped from Perplexity and it's pretty wild. Watch this video of placeholder taking over my LinkedIn tab and taking actions on my part. Interesting UX where the tab glows blue as it's taking actions. I like the integration of agentic actions right inside the browser that I'm using versus having to fire off an OpenAI Operator request.
Ryan Carson69,238 просмотров • 11 месяцев назад
How I get shit done, Episode 001 I've set up a playbook called ‘land’, which is triggered automatically when I drag an issue into the merging column in Linear. That reliably runs CI and merges any green PRs. This has allowed me to ship way faster than before. I think the key takeaway here is you can try to build your own code factory and your own agent orchestration layer, but it is a huge amount of work. The truth is there are entire companies with massive funding that are already tackling this and it's just easier to use their platform. I think this is a lot like if you were a carpenter: you could build your own generator, fuel it, wire it up, and then build a plug and then you could plug your saw into it. Or you could just plug your saw into the wall. Because the electricity company has already done all the work in the infrastructure and investment to make that plug work. I think more of us who are building companies should just be plugging into the wall instead of trying to build all this tooling ourselves. As a dev it's so tempting to build your own dev tools but I think a lot of times, even though you can build fast with agents now, it's a complete waste of time. It probably sounds like I'm being paid by Devin or something but I have zero financial interest here. They don't give me credits. I'm not an investor. I'm not being paid. I just think the tooling is really damn good. If you used Devin a long time ago and wrote it off, you really should have another look - for $500/month it's pretty obscene what you can get done.
Ryan Carson13,870 просмотров • 2 месяцев назад
If you have an idea for an app and you want to build it fast and deploy it with a lot of the controls that a developer would want, the experience on Replit ⠕ is pretty amazing. I recorded this quick video while I'm sitting here at Philz before dinner tonight. Let me know your thoughts: Who's using Replit? Who likes it? What don't you like? What works? What doesn't?
Ryan Carson29,492 просмотров • 10 месяцев назад
Here's my custom agent eval annotation tool. Built in ~60min with Amp and I'm shipping now.
Ryan Carson20,366 просмотров • 7 месяцев назад
If you have compute hungry AI ML tasks, you can spin up an Intel Gaudi2 instance and watch it just rip. I wrote a quick Python script to use the facebook/detr-resnet-50 model (🙏🏻 Hugging Face) to detect and label objects in a video. It's interesting that no one is talking about Intel Gaudi vs NVIDIA A100 or H100. Gaudi2 isn't cheap at $10.42/hour but it feels like a viable alternative to fighting someone for an A100 or H100. Here's my code if you want to try it out:
Ryan Carson41,328 просмотров • 2 лет назад
Claude 4 just changed the coding game and Ray Fernando breaks it down 1. Utilize Claude 4's built-in extended thinking to enhance context retention during coding tasks. 2. Break down coding tasks into incremental steps to trigger deeper checks and ensure accuracy. 3. Leverage the compounding effect by systematically revisiting previous context, significantly boosting productivity. Ray calls Claude 4 his "new workhorse," highlighting its unmatched capability to handle complex coding challenges. Have you noticed this leap with Claude 4?
Ryan Carson12,224 просмотров • 11 месяцев назад
Больше нет контента для загрузки