ʕ☞ᴥ ☜ʔ Kix's blog

I've been wearing an Apple Watch daily for the last 7-ish years now.

It's hard to find privacy-respecting (read: not Disqus) commenting systems out there.

I went to bed last night feeling excited to bike across town the next morning.

In the speed vs. intelligence spectrum, I've always figured the smarter AI models would outperform faster ones in all but the most niche cases.

During our Australia trip last month, I was really spoiled by the convenience of contactless payments.

I previously wrote about how I believe Cursor peaked with Cursor Compose, and that since introducing Agent mode and letting the LLM make decisions, its user experience and quality of output has subjectively gotten worse.

I have 64 gigs of RAM.

I’ve been trying to slowly ease into using LLMs for coding help again lately (after quitting cold turkey), but something always feels off -- like we’re not quite on the same wavelength.

I've been writing software for over 15 years at this point, and most of that time has been in Python.

I recently wrote about how LLMs can make you lose grip of your codebase by eroding the mental model you built by writing code yourself.