Can someone recommend me a local harness to explore the multimodality of this kind of models? Text in text out is mostly generically solved, but that's about what I know

Not sure what kind of tasks you have in mind, but Hermes will happily hand media to the model and show you results.

that's belt and suspenders too

a smoking gun

... and a caveat worth flagging.-

I believe it's a function of their primary user base being in china

buy inference from european companies running open chinese (or that one from google) models

I understand it to be a stand off between western special services on behalf of the media empires, and some random russian… criminals? their own intelligence or adjacent criminals? Just randos on a mission?

Russia doesn't produce content that anyone wants to pay for. So piracy is no economic loss for Putin. Secondly Russia's economy is going down the drain and the population definitely needs distraction from the war. Bread and circuses.

Russia exports a huge amount of content (from cartoons to AI), which is why it did not withdraw from copyright treaties in 2022, as Belarus did

because there's no gaming-oriented toolchain for it

because GLM does what Clauden't

on the 18€ plan they really want people to use Flash and skip the bigger thing.

Perhaps..

But, it was enough for a customer like me who tried them at good faith to walk away and find their competitors..

I like the diversity of LLMs as of today and prefer to not tie myself to one big plan with any vendor. If they don’t prefer me as a customer, then I will accept that, and move away.

yeah, absolutely. myself i'm enjoying their cheapest plan, and pay api prices for other models to fill in the gaps.

config is easier than the memory/state/history stuff.

GLM-5.3; well, the flash variant at least; you just ask what to do and it complies with no objections :^]