Few thoughts:
- my IDE is mostly useless now
- working with LLM is more like learning a new language than learning a tool
- one task per context window is the simplest and best advice for working with LLM
- context window limits are real and you'd better monitor that one
Today, we're introducing the next evolution of Quicknode.
Same power. Sharper performance. Now a complete development platform, fueling the future of blockchain.
Build Without Compromise. 🧵
If you're a podcast lover, I'd love for you to give OwlCast a try and share your honest feedback. Your input will help me make this even better.
Check it out -> https://t.co/6K4WacL6dC
So I spent my weekends over the past few months creating OwlCast – a tool designed for fellow podcast enthusiasts who want to:
- Save time: Get quality summaries of episodes when you're short on time.
- Stay organized: Keep up with their favorite shows & get the key takeaways
- Capture insights: Easily save notes from those "aha!" moments.
Excited to finally share a side-project I've been building over the past few months!
As I’m adding podcasts to my queue faster than I can listen to them, I thought I can solve that. Sometimes the best products come from solving your own problems – and I have a feeling many of you share this particular one.
Just launched the alpha version of OwlCast!
The value is simple:
Don't have (enough) time for podcasts? Read summaries of the podcast and get the key takeaways. Based on that, choose the ones you want to listen to 🎧
Special shoutout to Anna Karpińska. Design is amazing. That was definitely the right move to invest. It looks different. You immediately get the feeling that's custom made 💪
Working on this primarily during weekends and squeezing in about an hour daily. Step by step. And it starts to live.
My biggest reminder through this process? Learning by doing is the best way. I won't say the only, but ... yeah. Reading is great, but nothing compares to hands-on building.
We have time. And it’s limited.
That’s why I’m obsessed with tiny automations that remove recurring tasks.
Here’s one I built that now saves me HOURS every week 👇
The result?
- An automation that runs in the background
- Frees up headspace
- Saves me 3x more time than if I coded everything manually
LLMs shine on small, scoped, repeatable tasks like this.
@uwteam Powiedz więcej na temat „kosztu psychicznego”. Jak wyglądają niemiłe treści?
Jak sobie z tym radzisz? Po prostu olewasz? Bo nie czytać się chyba nie da…
(Dałeś radę przez 93 dni to chyba nie było tak źle.)
For upcoming conference season, I'm preparing talks around LLMs in day-to-day coding workflow. I'll focus on my personal use cases. No fluff stuff. Just real-life coding.
To make sure it's helpful, I've prepared a short survey to understand experiences, workflows, and challenges with these tools.
It only takes a few minutes.
👉 https://t.co/MZjS5KDMFI
Thanks a lot!
@kaczmareklukasz suggested to just spin off Substack & publish my notes from podcasts.
I'd much rather procrastinate and spend another days preparing whole application, but I guess I'm too old for that. Let's ship!
Take a look & subscribe https://t.co/4pZU7f7fRn 🙏
I've got something like 90GB of podcasts on my phone... That's pretty obvious I won't find time to listen to all episodes.
Too many good podcasts, too little time...
That's my thought process when deciding to build OwlCast.
I was looking for simple project to learn #LLMs in practice. Since building is the best way to learn.
To make it simple, I've built backoffice that helps me process podcast & prepare notes.
I'll build webpage, but...