Jaymie Jones
@pixelstackcom
Engineering Manager @canva, former Engineer Manager @envato. Host of @codercatchup. I like to build things with code and capture moments with cameras.
قد يعجبك
It’s a spicy take for some but this is the harsh truth. At the end of the day, if the product/service performs, delivers value to customers and can be further built upon and refined, the rest doesn’t really matter.
I am self-taught dev but worked in software companies and acquired a lot of software products human written code can be just as bad, hard to follow, and bug ridden as ai code can tldr: if the app works, loads fast and is secure, code quality does not matter
Major cheat code in life: Understanding you can reinvent yourself at any time. New habits, new standards, new friend group, new career, etc. There's no rule that says you have to stay the person you've always been. You're allowed to decide, "I'm done being this version of me."
It's now well understood that the better the context, the better the performance of AI models. But it's the same lesson as scaling human organizations. Maximize and enrich context. Engineers and designers are not code & pixels pushers. They solve business problems. At Vercel…
You're not struggling with productivity. You're struggling with not having a project worth being productive for. If you were working on the right thing, you wouldn't be able to stop thinking, working, obsessing.
One of the most fun parts of OpenAI is watching people here level up so fast and do such excellent work. We are operating at a high level across many different disciplines and many of the people doing it have never done it before, and joined us at the beginning of their career.…
4 brutally honest reminders from Seneca: 1. Most suffering is self-inflicted 2. Stop putting things off 3. Stop acting like you’re going to live forever 4. Seek out challenges
The Agentic Engineering pattern I use daily: 1. Plan with a slow, deep reasoner 2. Implement with a fast, nimble code model 3. Review implementation and iterate You rarely need more complexity than that. This is the "cognitive core" of coding with LLMs. Does take discipline.
100% Maybe I'll eat my hat, but this is how I see it right now
A great new guide just dropped by @FactoryAI “How to become a (Droid) Power User” In-depth coverage on: 📓Fewer tool calls 📓 Better first attempts 📓 Consistent Quality 📓 Self-Correcting code
What is intelligence? What will it take to create AGI? What happens once we succeed? The Scaling Era: An Oral History of AI, 2019–2025 by @dwarkesh_sp and @g_leech_ explores the questions animating those at the frontier of AI research. It’s out today: press.stripe.com/scaling
Got the TypeScript version of DSPy working while I was on the plane. It's called Ax. I was optimizing a prompt to extract fields from a flat PDF. It took me an Amp less than an hour to get it working. Programmatic prompting yay!
Early career advice from my father: “If you don’t do the small things well, they’ll never trust you to do the big things. Remember that. Everything you do matters—act accordingly.”
Google shocked the world. They solved the code security nightmare that's been killing developers for decades. DeepMind's new AI agent "Codemender" just auto-finds and fixes vulnerabilities in your code. Already shipped 72 solid fixes to major open source projects. This is…
Can't over-stress how you need to code with LLMs from all AI Labs. Don't get tempted to be loyal unless you work at a Lab. > Sonnet 4.5 - Quick reasoner > GPT-5 - Deep reasoner > Grok 4 Code - Fast implementation > Gemini 2.5 - Long context summary Best tool for the job.
TIL about caddy so ofc i made a raycast extension love this sooo much 🥵
Your chat = your next design 💬 Did you know you can create, edit, and research your Canva work from inside @OpenAI's ChatGPT?
So proud of what our teams have been able to build, unlocking new ways of working with @canva in @OpenAI 🎉🙌
🚀 Playwright Agents are here! (Playwright v1.56) 🤖 Planner → generates test plans 🛠️ Generator → generates runnable tests 🩹 Healer → debugs & fixes failing tests Try it out: npx playwright init-agents --loop=vscode/claude/opencode youtu.be/_AifxZGxwuk
youtube.com
YouTube
Playwright v1.56: From MCP to Playwright Agents
United States الاتجاهات
- 1. Bears 90.1K posts
- 2. #Worlds2025 19.9K posts
- 3. Happy Birthday Charlie 12K posts
- 4. Jake Moody 14K posts
- 5. Snell 25K posts
- 6. Bills 143K posts
- 7. Falcons 51.9K posts
- 8. Caleb 49.7K posts
- 9. Josh Allen 27K posts
- 10. #BearDown 2,408 posts
- 11. Joji 32.2K posts
- 12. Jayden 23K posts
- 13. Swift 290K posts
- 14. Ben Johnson 4,477 posts
- 15. #Dodgers 15.5K posts
- 16. Turang 4,401 posts
- 17. Troy Aikman 6,679 posts
- 18. Roki 6,122 posts
- 19. Bijan 33.5K posts
- 20. #RaiseHail 8,453 posts
Something went wrong.
Something went wrong.