Recent submissions

Comment · 1 day ago
Any resource detailing how you do this? I've been looking at dagu specifically for this.
Comment · 2 days ago
Uses less resources since it's mostly Rust, to my knowledge. Whereas Orca uses Electron.
Comment · 11 days ago
Comment · 23 days ago
Was expecting Hideo Kojima in the credits.
Comment · 24 days ago
Unrelated: I love your username.
Comment · 28 days ago
Saw Simon Willison's post from earlier: https://news.ycombinator.com/item?id=49949235

This seemed relevant because it has budget caps. It also has per-user/model controls and usage attribution for teams/enterprises.

I've been exploring it for the past few days with their community edition. They also have a paid variant which uses OSS models from their infrastructure.

Comment · 1 month ago
I will forever remember Office Spider, THAT Secretary , and Vincent Adultman whose words I often think about:

  Woke up at 6am on a Sunday.
  I think I'm becoming a thought leader.
Comment · 1 month ago
I learned this myself while yelling at AI.
Comment · 1 month ago
This is an awesome idea. I use agents all the time that way, so am not thrilled by potential consequences, but I love the idea from the platfroms' perspective.
Comment · 1 month ago
I use models.dev's CLI tool, which I think gets data from OpenRouter, and ArtificialAnalysis so your coding agent can help you narrow it down.

<sidenote>

Similarly, HuggingFace has a CLI + a few skills, and they are very useful.

I had a production image processing using Gemini 2.5 Flash Lite (which is getting discontinued in October), and in 20 minutes Claude Code + HF Cli recommended the best replacement small model (Qwen VL 3B something) and proceeded to fine tune it on my datataset. All this while I was in a rush to get dressed and go to the store.

It cost ~$3 I think, and results were excellent. Not perfect, but not far from perfect either.

We didn't replace Gemini in prod at the time, because we didn't have time to do all the math on how to end up with a smaller bill/mo.

</sidenote>

Comment · 1 month ago
I tell the agent to outline the greebling, which is the when you add extra details that aren't really necessary.

Initially it feels like the result will be too empty, but once the greebling is removed it most often looks better

Comment · 1 month ago
I was fascinated by hister initially, but now I'm fixated on your URL.
Comment · 1 month ago
And you typically use them for business, not on private accounts.
Comment · 1 month ago
I don't have specifics since it's been months, but LiteLLM on a hetzner server, deployed through Coolify was using 1-4 GB (cannot exactly, and dont know why either).

Bifrost feels very light, though.

Will try LiteLLM if it's in Rust.

Would also appreciate a slicker aesthetic. I got used to Bifrost shadcn with 0 border radius.

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton