huydotnet

I recently subscribed to Claude, and was very unhappy about the usage limit of the $20 pro plan. Then I found a trick, since I got free Google AI Pro via my phone carrier, I use Opus 5.5 High for planning, and then dispatching agy to do works.

Most of the time 3.8 works fine, but it's a bit slow if compare to 3.7 Flash. If there's already a detailed plan, 3.7 can complete the task much faster. And the best thing about agy is the usage limit was very generous.

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?

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 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.

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

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.

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.