calmingsolitude

Joined 6 years ago

Karma
754
Submissions
64
Member since
Nov 23
View on Hacker News

Recent submissions

Comment · 6 days ago
LLM subscriptions are heavily subsidized. I’d be surprised if Claude 20x costed the same after a decade.
Comment · 13 days ago
Comment · 13 days ago
It’s not a criticism. The creators of these projects have most likely shopped around and used existing projects before deciding to build their own. I’m as interested in the “why” they built something as much as the project itself. Unfortunately, with LLMs, it looks like writing and communication skills have taken a hit.
Comment · 20 days ago
LLMs are good at reading READMEs. They are absolutely horrendous at writing them.
Comment · 1 month ago
This makes absolutely no sense. The API returns the exact content of the message, and has no idea where it possibly might be displayed. It could be another browser, so html tags will need to be sanitized, but it might as well be the terminal, so ansi escape codes will need to be sanitized instead.
Comment · 1 month ago
Mildly disappointed that this has nothing to do with Unreal Engine, the popular game engine.
Comment · 1 month ago
Comment · 2 months ago
Comment · 2 months ago
The author has a point, but at the same time is overly complicating things. Seeing that it is already available via cargo, all that is left to do is offer a .tar.gz bundle as well. In the case that the software actually becomes popular, someone else will package it for the distros in question.
Comment · 2 months ago
> It may be that the 662 MB used by the "Renderer" is shared between many Windows components

From the screenshot in the article, this is the memory usage of the Renderer process spawned by the Weather App. I find it very unlikely that some other app (say, the Copilot app) can then piggyback on Weather Renderer process. Do you have a source for this?

> killing that Weather app may not reclaim as much space

Closing the weather app on my PC does in fact kill all child processes and frees up around 1GB of committed RAM. Are you not seeing the same?

Comment · 2 months ago
Comment · 3 months ago
No. I’ve heard this argument multiple times before - “let the human review and write tests” - and sure it might work, but this is almost never practiced. AI makes coding a lot faster, so no one is really ready to spend time on manual review and writing tests when LLMs can do that as well and take you most of the way.
Comment · 3 months ago
How does this compare with solutions that currently exist to solve this problem, say for example ngrok?
Comment · 3 months ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton