hey, thanks for the suggestion. unfortunately even with lichess's annotation, it's still not enough to identify hanging pieces or other board situation for the diagnostic, so we still need to run stockfish on each move again :D in fact i intentionally get just the raw move data from lichess during import.

Did not install the app but it looks cool. But I was wondering, how does the app can hijack macOS login screen like in the demo? is it even possible?

If you're looking for a carefully crafted/written work to explain internal combustion engines, look no further than this one https://ciechanow.ski/internal-combustion-engine/ (the Mechanical Watch article from the same author was featured on HN a while ago).

I wish he was still making posts.

It's been a year and a half since the last one, compared to 1 or 2 posts per year. Here's hoping he's taking some extra time to make something amazing

He isn't? What happened?

For anyone jumping into this thread hoping to see capacitor use for timing, there is this blog post about something like that:

https://notes-huy-rocks.translate.goog/posts/diy-pomodoro-ti...

(google translate link because the original post was in Vietnamese)

I love that local LLMs are being discussed more often on HN recently. But for the post, I find it strange that the author claimed they were working with local models from day 1, but wrote a post that still links to Qwen2.5 and Qwen3 in mid June 2026.

Why shouldn't the author mention models that people might not have to buy a new computer to use?

One don’t have to buy a new computer to run Qwen3.6 or Qwen3.5 (35B A3B), given that they can already run Qwen3 30B A3B.

In fact with a 64GB mac, you can run pretty much all of the latest Qwen models.

Also, anyone who has been following local LLM are well aware that the quality and performance has become way way better since Qwen3.5

I've been building the same thing for a while https://github.com/huytd/octocmd It has everything you need to throw away the mouse: keyboard tab switching, search and click, vim-style clicking, keyboard scrolling.

I'm gonna use this article to explain to my peers about LLM quantization!

They are different quantization types, you can read more here https://huggingface.co/docs/hub/gguf#quantization-types

you just answered your own question, "AI hobbyists who has 4090 at home". And they are pretty much targeted user of Unsloth since the start.

Actually the opposite haha- more than 50% of our audience comes from large organizations eg Meta, NASA, the UN, Walmart, Spotify, AWS, Google, and the list goes on!

I've tried both. Each has pros and cons. Two things I don't like about superpowers is it writes all the codes into the implementation plan, at the plan step, then the subagents basically just rewrite these codes back to the files. And I have to ask Claude to create a progress.md file to track the progress if I want to work in multiple sessions. GSD pretty much solved these problems for me, but the down side of GSD is it takes too many turns to get something done.

There is a fork that uses Claude Code-native features and tracks progress and task dependencies natively: https://github.com/pcvelz/superpowers

If you use it I'm curious if you find it limited at all from lagging behind superpowers? For instance I opened up one skill at random and they haven't yet pulled in the latest commit from last week.

I doubt any hot off the press features are *that* important, but am curious if the customizations of the fork are a net positive considering this.