testycool

Any resource detailing how you do this? I've been looking at dagu specifically for this.

Uses less resources since it's mostly Rust, to my knowledge. Whereas Orca uses Electron.

I first used something similar with this: https://github.com/browser-use/agency

Was expecting Hideo Kojima in the credits.

Unrelated: I love your username.

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.

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.

I learned this myself while yelling at AI.

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.

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>

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

I was fascinated by hister initially, but now I'm fixated on your URL.

And you typically use them for business, not on private accounts.

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.

Also https://github.com/sinelaw/fresh which is micro "on steroids" (i dislike the expression but can't think of a better one now)

Did someone make a site to track the timeline of the new WordPress situation, like they did with the WP Engine one?

Haha, thanks I'll try this. I typically tell it to explain in one of the following ways:

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

Holy shit I had no idea there was a YouTube series, nor that he had a YT channel.

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.

Love the UX and aesthetic of this site!

Also ArtificialAnalysis drop older foundational models to make room for new ones.

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.

You can use a cheap model in another pane, and ask it what Claude said.

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.

I just use a cheap model in another pane, and ask it what Claude said.

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`

And doesn't seem very constructive either.

I use LinkOff https://chromewebstore.google.com/detail/linkoff-filter-and-...

It has a 'gentle mode' so you see what gets blocked.

I think it's thanks to it that I don't feel animosity towards LinkedIn anymore.

Again with me rushing to make the most out of tokens on the last day.

Maybe Gemini 3.5 Pro is coming out this week and I'll get another reset then.

This turned out great. Thanks for explaining!

What plan are you on and how much usage did it burn?

I was rushing to make the most of Fable today, and I'm at 67%, with limit reset on July 11th.

If would've used it more moderately if I had known in advance.

Was it bad? I was too young too tell and thought it was nice.

"Butt Naked Linux" is how I read it.

I know it's off topic. I accept my downvotes.

Thanks to your comment I checked it out and loved it. Thanks.