Hacker News: granra

New comment by granra in "Neverclick: Desktop application for performing mouse actions with your keyboard"

granra — Wed, 15 Jul 2026 10:50:04 +0000

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)?

New comment by granra in "Neverclick: Desktop application for performing mouse actions with your keyboard"

granra — Wed, 15 Jul 2026 10:46:53 +0000

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.

New comment by granra in "Karp: Anthropic/OpenAI are stealing customer IP and their tokens have low value"

granra — Thu, 02 Jul 2026 13:10:11 +0000

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.

New comment by granra in "What's wrong with EU age verification? (Nothing)"

granra — Wed, 01 Jul 2026 14:41:09 +0000

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.

New comment by granra in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

granra — Wed, 17 Jun 2026 17:36:55 +0000

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.

New comment by granra in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

granra — Wed, 17 Jun 2026 17:23:10 +0000

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.

New comment by granra in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

granra — Wed, 17 Jun 2026 16:35:37 +0000

That's what I've been doing. I use crush normally. While the codebase are by no means huge, they're not tiny either.

New comment by granra in "GLM-5.2 is the new leading open weights model on Artificial Analysis"

granra — Wed, 17 Jun 2026 12:30:08 +0000

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

- (not writing files yet)

- instead of your approach x, wouldn't it make sense to instead do z? What would that look like?

-

- nice, implement this

- starts writing files, run tests, etc.



New comment by granra in "CSS: Unavoidable Bad Parts"
granra — Thu, 11 Jun 2026 13:25:12 +0000

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.



New comment by granra in "xAI is looking more like a datacentre REIT than a frontier lab"
granra — Mon, 08 Jun 2026 21:38:43 +0000

More like most European countries.



New comment by granra in "xAI is looking more like a datacentre REIT than a frontier lab"
granra — Mon, 08 Jun 2026 19:56:38 +0000

> Until someone can come up with a better option though...
A welfare state maybe?



Introduction to nixidy – Kubernetes GitOps with Nix
granra — Mon, 08 Jun 2026 15:16:19 +0000

Article URL: https://codedbearder.com/posts/nixidy-part-1-introduction/
Comments URL: https://news.ycombinator.com/item?id=48446465
Points: 3
# Comments: 1



New comment by granra in "Taking a walk may lead to more creativity than sitting, study finds (2014)"
granra — Tue, 26 May 2026 11:55:51 +0000

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.



New comment by granra in "Eric Schmidt speech about AI booed during graduation"
granra — Mon, 18 May 2026 13:12:50 +0000

Exactly. Maybe the ultra rich shouldn't be allowed to accumulate all the wealth and assets and "the outsiders" are just scapegoats. ¯\_(ツ)_/¯



Show HN: Crushout – A PreToolUse Bash hook that auto-approves read-only commands
granra — Wed, 06 May 2026 14:10:53 +0000

Article URL: https://github.com/arnarg/crushout
Comments URL: https://news.ycombinator.com/item?id=48036503
Points: 1
# Comments: 0



Show HN: Nixidy – Kubernetes GitOps with Nix and Argo CD
granra — Wed, 01 Apr 2026 14:39:43 +0000

Article URL: https://nixidy.dev/
Comments URL: https://news.ycombinator.com/item?id=47601601
Points: 4
# Comments: 1



New comment by granra in "Nixtml: Static website and blog generator written in Nix"
granra — Wed, 03 Dec 2025 05:34:13 +0000

Too bad I don't write PHP then



New comment by granra in "Nixtml: Static website and blog generator written in Nix"
granra — Tue, 02 Dec 2025 19:48:00 +0000

Out of curiousity, having never worked in the business of making websites, what would be accessible to a designer? Jinja2?



New comment by granra in "Nixtml: Static website and blog generator written in Nix"
granra — Tue, 02 Dec 2025 18:52:26 +0000

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 :)



New comment by granra in "Nixtml: Static website and blog generator written in Nix"
granra — Tue, 02 Dec 2025 18:46:07 +0000

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