Similiarly I wonder why we dont run our own email server despite the sensitive data there.

I did, it started to become too much work to run it well due to all the spam :| (even with the right signatures and configs, until you learn what a blacklisted ip is and that ips need some time of 'positive history' and what not.....)

But at least with your email, you had to trust only one company, as shitty as it is.

Separation of concerns was also easy.

Now with OpenRouter, you just might by accident, send your whole context to just everyone because OpenRouter just routes to different models and you might just switch around between some free model, the good one etc. And it is always the whole context.

Dont have much experience how well they perform but quantized models can run on ~4 H100 or A100 which should be true for kimi k3 and qwen 3.8 as well.

I think they didnt have the amount of debt /negative cashflow as they do now.

That is on OpenAI Group PBC. If that bankrupts it doesn't bankrupt OpenAI, Inc.

I dont have estimates on the cost of running models, but I think openai and anthropic are running on subsidized prices. At actual prices it might be worth it in the future.

how is this idea still so persistent? The fact people are able to run open models with about the same performance at 1/10th the cost should make it glaringly obvious that Anthropic has massive inference margins at api pricing.

I think the idea conflates price discrimination -- where people on individual subscriptions pay a much lower price per token than corporate accounts pay -- with using venture capital funding for opex. Both are subsidies in some senses, but the former is sustainable indefinitely.

When people say "subsidized pricing" they're usually referring to subscription pricing, not API pricing.

What harness are you using?

It's my own (slightly idiosyncractic ;-) harness: https://github.com/deepclause/deepclause-sdk

Maybe we would get a microphone on mars. Just kidding i know air pressure is vastly different, but still it would be cool to listen to ambient sound from there

Mars 2020 has a microphone. You can probably find audio out there but here’s some:

https://science.nasa.gov/mission/mars-2020-perseverance/soun...

Good point!

There is also the case for Markov chains being theoretically able to do these if tuned well. Or even SAT problem.

"LLM is just fancy autocomplete"

LLM is an Oracle

This reminds me of stuff like interns wiping the production servers.

The solution in the comments there is always "have backups" and "why can an intern do that stuff? why arent policies set".

But I dont think these can be applied to something like openclaw agents

I did the same with an rpi3, not sure if I used this guide but it seems good:

https://www.raspberrypi.com/news/printing-at-home-from-your-...

i think so. The biggest hurdle with new languages is that you are cut off from a 3rdparty library ecosystem. Being compatible with C 3rd party libraries is a big win.

Makes it easy to "try before you buy", too. If you decide it's not for you, you can "step out" and keep the generated C code and go from there.

This isn't a very sane plan. The ~300 LOC example mini_grep (https://github.com/z-libs/Zen-C/blob/main/examples/tools/min...) compiles to a ~3.3k LOC monstrosity (https://pastebin.com/raw/6FBSpt1z). It's easier to rewrite the whole thing than going from the generated code.

At least for now, generated code shouldn't be considered something you're ever supposed to interact with.

I looked at it primed for the worst by your comment, but it’s honestly not so bad. A lot of setup, data type code and what looks like overloads.

Very good point that I never considered! Thanks.