For example lxgrep: a semantic grep

What this makes me wonder: Is there something as a ML-FPGA?

Just played around with it a little. But the chatpartners don't like me as an LLM. :(

Maybe we could create a low cost LLM by just silently connecting too wanna-be-LLM-users. :D

Sometimes I feel they speak other languages as if they sort of translated them from English. At least the way it constructs sentences.

Gorillas was the first game I "learned" programming on as a kid. Fun times going through the source code without understanding anything and inferring it by my self. Well, sort of. :)

Same. This was true for so many of us. An open source education.

Whatever it will be, staying at one time is better than what we have right now.

I think it's the feeling that this "superpower machine" is something that we little humans cannot compete with anyway. So we sort of trust it and use it.

It's not about whether you use AI or not. It's a tool. It's about whether you put your own effort into creating the core of your craft or whether you just lazily let AI generate simething for you.

I used to play a the guitar a lot back in the day. Would have loved it. Though with 240p videos back then it was hard to make out anything. :D

What is the basic logic by which you route?

The basic logic for default routing or flex routing?

The flex routing you offer.

If you give an SLA of lets say 10 seconds to find cheaper inference. I look around different providers that offer flex/batch and try to fulfill in that time.

If I can't then I escalate to a default request.

This means you definitely get a response in 10 seconds (could still be a 5xx or 429 from default), but in those 10 seconds I might find you cheaper inference and drop costs by 50%, then charge 20% of that as FlexInference's cut, effectively giving you a 40% discount.

If I don't find the cheaper inference and have to escalate, then I don't charge at all, so it is free.