> ...you bet your ass...

Humorously, whether I choose to participate in this hypothetical or not, I am already betting my ass.

This whole situation feels like the game [1].

[1]: https://en.wikipedia.org/wiki/The_Game_(mind_game)

Why. That was just uncalled for. Sigh

> I don't think anyone has a firm grasp on actual inference costs.

There are huge numbers of users (myself included) that do have an exact idea of what inference costs are - on open models. We can buy tokens from 3rd parties that have no motivation to subsidize our use. That's to say, there's a fair marketplace[1] and we're hanging out there.

If you want to say "I don't think anyone has a firm grasp on actual inference costs on these proprietary/closed models", then I could agree with that.

[1]: https://openrouter.ai/rankings#leaderboard

If this is how they treat their employees, I hate to think how they treat their customers.

>(re)built are not what I'd describe as "terrific".

It sounds like you are a strong candidate to try out the new improvements mentioned in this devlog and see what benefits you can get for yourself.

> having moved from Linux ... to freeBSD default install makes my laptop last about twice or thrice as long.

I’ve literally never heard this from anyone before, and I have to admit, I’m curious enough to try it for myself.

The last time I tried FreeBSD was 2001.

i am not sure why btw but i read some articles on here about software not being idle on background properly a lot of times (fancy terminals etc.). for me tho 'it just happens' because im unsure how to measure it precisely..

maybe my linux had a big or wrong setup u know, but it was running very lean. Freebsd runs about as lean tho.

cannot be bothered ofc to go back and measure it is some hp-elitebook withh a ryzen and iGPU in there.

If i run things like Claude it sucks my battery. But if i just run my editors code all day myself its all gd..use firefox as browser on both. other then that its x,i3,hx,rg,fd,fzf. thats about all i use..(so u see i hate it when any laptop empties soon.... i hardly use anything of it). usually i dont even open x/i3.

I run openbsd on an old latitude and that tracks. I mostly have only application active at a time. The others are idling. I believe on Linux, especially with DE, there’s always some polling or scanning going on.

That also means that any desktop Linux user who goes to play on OpenBSD or FreeBSD and runs a full-fat desktop environment that they like will probably discover similar battery life to what they're used to.

I think allowing jumping would add a lot. looking over the top of a whole crowd would be more visually dynamic.

Added! b for bounce!

cool! camera positioning is a bit weird though on jumping, especially when pressing consecutive. but nevertheless it's awesome

Thank you!

Good idea. PR will be accepted.

> As someone who has been writing harnesses for a year…

Your agent harness, brokk, looks great. I’m going to try it this morning.

> It’s sad to see companies…

The article is about an open source agent harness, Reasonix, that is built to leverage the DeepSeek native api.

There’s no company here. No design budget. These people are graciously sharing a project they made in their free time.

You're right, but I find as a solo engineer it's still important to check the frontends I create on mobile

I agree. I didn’t mean to be too critical. But if they’d made something simpler, I think it would save them tokens and end up more likely to convince their target audience of developers.

(The series of ‘motherfucking websites’ comes to mind, they were all very readable and simple, even if satire.)

Okay, I'm curious.

From the FAQ, I see:

>Can I point it at a self-hosted / private DeepSeek endpoint?

>Yes. Since 0.30 we accept non-standard key prefixes for self-hosted DeepSeek endpoints. Just point `baseUrl` at your internal address — the loop, cache strategy, and tool protocol are unchanged.

But my question is: If I use Reasonix to talk to a deepseek endpoint through openrouter, am I still getting the cache-hit benifits of this agent harness?

Yes*. At least from my limited usage of deepseek-flash for a few billion tokens on openrouter, the cache-hit rate is >95%. And I simply used the claude code harness pointed at the openrouter anthropic compatible endpoint with no fluff.

Did you get proper tool use? Some CC-driven models seem to get a bit off when it comes to MCP usage. For example: I really struggled to get Kimi to use Serena, which I think ended up costing too many tokens.

thank you!

I would wonder that too, I'm only a novice openrouter user, but I do notice it reroutes my same-model requests to different providers.

Maybe users reporting otherwise are just looking at their client reports which wouldn't be able to tell the difference.

Look into Openrouter's provider routing.

> C is horribly and unfixably broken. ... Let's move on.

I love that you are both making this argument and that you have a link to a boutique C compiler written in assembly on your home page.

While I'm commenting on your home page - I recognize that photo as being Red Rock. Possibly pine creek? but can I ask which route specifically?