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.

Comments URL: https://news.ycombinator.com/item?id=49950321

Points: 1

# Comments: 1

  Woke up at 6am on a Sunday.
  I think I'm becoming a thought leader.

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.

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

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.

  - as the grug brained developer
  - for smoothbrains
  - for high school reading level intern
  - in the style of Samuel L. Jackson

And a recent video is about designing a dashboard with Ai, which is exactly what I been needing from him specifically.

I remember reading the book 6 years ago and I loved how easy it was to understand.

It's also where I first learned about dense UI and was amazed at a before/after example of one. You can clearly see that uncommon common sense he has about UI/UX.

Thanks for mentioning this.

If you customize the filter to add Gemini 3.1 Pro you'll see it ranks 5th in AA-Omniscince Index. Yet by default you wont see Gemini 3.1 Pro.

I find this to be very unhelpful and confusing.

I prefer this since everyone has their own preference for how the output should sound and it's very simple and transparent. And you can easily ask follow-ups.

It can be via tmux, or herdr, because it can read the pane.

Or it can use a hook to read the conversation file. I call it `backseat-driver`

I sometimes use it as a proxy when fable genuinely does a good job, but is too difficult to understand.

I let the translator know it's role and anything I say it should forward with better context.

I don't swear at it anymore, but I'd often say "just do it, retard", and the translator would actually steer it in a useful manner.

It can be either via tmux, because it can read the pane.

Or it can use a hook to read the conversation file. I call it `backseat-driver`