granra
granra on Hacker News
This looks cool! How is the planned Linux support (the website says "Coming soon for Linux") suppose to work? X11 only? Wayland? Gnome only (or any other DE)?
I mean, it can make mouse movements and clicks but you can't be suggesting it can do on-screen hints, which makes it a way better experience.
If you invented god that can make you billions, why wouldn't you extract that value yourself instead of leasing it in form of an API access.
No one claims their showels find gold for you.
But now kids grow up with social media and fake news. I too grew up seeing stuff I shouldn't have online and I turned out fine but I see the online landscape today as much scarier place and as a recent father I'm scared of what it can do to my child and will need to police it.
I'm not entirely sure what an agentic workflow could mean today but I think so. I use a coding agent (crush), prompt it to brainstorm an implementation with me (or sometimes I know exactly how I want to implement it but ask it to challenge it), correct any wrong assumptions or request the implementation to look differently than suggested if I don't like it. Then finally when I'm positive I've cleared the most important assumptions I ask it to actually write and edit files and run tests and such (this just ends up being a "implement this").
With any model I've tried I've found it to be a huge pain to have it fix things where it made a wrong assumption without the code becoming a mess and burning a lot of tokens. I'm aware that not everyone works like this but I'm still very opinionated on what the end result should look like so I can still work on it without an LLM.
With a claude code plan, can you generate as many tokens with Opus as you can with Haiku before filling your 5 hour window? The same is going on here.
That's what I've been doing. I use crush normally. While the codebase are by no means huge, they're not tiny either.
How are you using it? I have the lite plan and I've only ever maxed my weekly usage a few hours before reset. I will concede that I'm not a super heavy LLM user but it's been really good for me.
My workflow is usually:
- read file. I want to achieve X, how do? Do not implement anything.
- I would do a, b and c
- sketch a brief implementation of your suggestion
- <code> (not writing files yet)
- instead of your approach x, wouldn't it make sense to instead do z? What would that look like?
- <code>
- nice, implement this
- starts writing files, run tests, etc.
I remember that there were these talks called "Linux sucks" (IIRC) and the premise wasn't that we should start using Windows but more like "we can do better and improve it." Not every complaint needs to come with a solution or better alternative.
More like most European countries.
> Until someone can come up with a better option though...
A welfare state maybe?
Posted by
granra on Monday June 08, 2026 @11:16AM
from the codedbearder.com dept.
I made an MCP server that basically implements all the tools an agent harness would provide. The code is checked out on my server, the MCP server creates git worktrees on "activation" and it can read, modify files, run bash commands etc. I have this setup in typingmind so I can do everything from my phone :p The only problem is that typingmind needs to be in the foreground on my phone, otherwise it will kill the connection.
There was a time where I was often stuck for an hour with nothing but my phone and I kept copying file contents into chat for context so I made this and it works surprisingly well.
Exactly. Maybe the ultra rich shouldn't be allowed to accumulate all the wealth and assets and "the outsiders" are just scapegoats. ¯\_(ツ)_/¯
Posted by
granra on Wednesday May 06, 2026 @10:10AM
from the show-hn dept.
Posted by
granra on Wednesday April 01, 2026 @10:39AM
from the show-hn dept.
Too bad I don't write PHP then
Out of curiousity, having never worked in the business of making websites, what would be accessible to a designer? Jinja2?
Generally I think you have a point when making landing pages or things of that sort. I however basically only use static site generators for blogging and I think markdown/asciidoc/whatever + metadata is nicer for writing content than directly in HTML.
I made nixtml and I take no offence :)
Yeah it would probably be more efficient to do the templating as a build step in the derivation that parses the markdown. But after making nixidy[1] I wanted to have a crack at making a static site generator _in nix_. I'm open to expanding it though of course :)
[1]: https://github.com/arnarg/nixidy
haha I'm afraid it was a total coincidence that it kind of looks like it :D
I had seen a few of those `__findFile` hackery articles lately and did actually consider doing that but I think having a nice way of adding HTML attributes would've been clunky :p
Edit: although looking at this article it seems to be supported.
I'm the author of nixtml. It's already doing IFD by using python to parse markdown content + metadata and superhtml to format the final HTML (a bit unnecessary, but I liked it while developing it).
I really wanted the templates to just be nix functions. It shouldn't be an issue to pass the context to an external program with `pkgs.runCommand` or something and then read the result (IFD like you mentioned).
Edit: I'm glad to hear you like it :)
I apologize. I didn't intend for it to go this way.
I don't think he's a bad person. But when an artist/content creator/public persona has such fundamentally different values from me on an issue like this I can't enjoy the content anymore (I guess I can't "separate the art from the artist"). Having the opinion is fine with me but attending protests where women are being harassed for entering abortion clinics is problematic to me (this is a post I had seen but could not find again today).
Someone pointed this out on mastodon a while back and it somehow made its way to me. I only mentioned there being thousands of posts to explain why I only skimmed the article to provide an example. I was trying to not spend my entire day on this.
This was just suppose to be an "FYI" comment because knowing this affected me.
What I saw as disturbing was the content of the post, failing to see that he wasn't directly voicing his own opinion on the matter.
I didn't like the use of the word "pro-abortion". I generally address them as pro-life even though I don't like that it indirectly indicates that the other side would be "anti-life" but I agree that it's not productive to get into a flame war on terminology.
Logically I see your point. But one side is fine with the other side having the opinion to not have an abortion under any circumstances while the other is fighting to take the right away from anyone to have an abortion. So I feel like one side has more reason to go for the anti-* card, although I don't think it's very productive.
Fair enough, I may not have picked the best example while skimming it quickly (he seems to have thousands of posts on his blog). I didn't like him using the word "pro-abortion" though (and not pro-choice) which to me seems to be used to villainize the other side.
Thank you, I edited it to pro-life