lexoj

I remember some years ago after coming from work at 6 pm I was dead tired at home thinking it was due to hard work during the day. Then one summer day decided to code side projects on my balcony and I was building until midnight full of energy.

I created a small PI extension that always watches relevant directories and answers me in place, without switching context, or using a chat interface. Still experimenting but I like it.

https://github.com/piqoni/pi-piqo

I used them because they had the fastest chat response. (Dont think that’s the case anymore, and they introduced some UI blocking feature on load which is irritating, but still use it mainly due to habit)

That chat history dark pattern is the main reason I never use Gemini. Its a shame.

Is it me or the mentions of Kagi on HN are overly positive?

Not sure about the compiler but prominent users of llm agents (Mitchel Hashimoto, Armin Ronacher etc) has mentioned that Go gives better results for agentic coding.

This type of corporate behaviour should be highlighted as unacceptable. I’ll personally steer away from anything cisco from now on.

Not free in my country, didn’t know YouTube was broadcasting full movies in certain regions as you imply.

I want to use Zed but last time I tried it was spawning node processes, i guess for lsp. (I develop in Go)

I don’t do laravel but which bad practices are you referring to?

I’ve disabled all activity notifications. It actually helps me avoid the phone on other type of notifications.

They are much much lighter due to lack of batteries which makes them quite ergonomic.

Self plug: I use matcha[0] which produces markdowns which with icloud (or any other file sync service) automatically sync cross devices.

https://github.com/piqoni/matcha

But the llm could still take ownership of that and ask clarifications, reach stakeholders while taking notes, and so on.

Top of the file or end?

As my doctor used to say: the best posture is the next one.

It has that new slop aesthetics.

Can you share the plugins name/configuration for Go in Sublime. There are so many options and configurations published so its hard to find a configuration that works as good as Vscode.

True, its insane how bad MS teams performs and is built and this is coming from a company that have written their own OS, Programming languages, frameworks etc.

They needed true cross-platform consistence, so it had to be equally terrible everywhere.

I’d have loved to see Linus Torvalds reply to this.

How it differs from mailbrew?

Local-first RSS reader/generator with LLM support: Matcha. [0]

https://github.com/piqoni/matcha

In these new world order, frameworks need to stop changing their APIs for minimal marginal improvements of syntax.

Figured it, its prob a nginx lua module

Anyone knows why lua? Or is it perhaps as a redis script in lua?

The way I have made RSS more fun is by adding local LLM functionalities[0] and push notifications. (that can notify me when something I expect to happen, happens)

[0] https://github.com/piqoni/matcha

News cooldown

I keep trying Helix but just got hit by wq freeze issue, opened since 2022, so I wonder sometimes if its ready.

https://github.com/helix-editor/helix/issues/2059

In the country im in, apple official resellers were not allowing to try any of their apple watches on wrist.