Curious, can anyone having 128gb ram macs tell their story - is it usable for coding and running model locally? How does latency compare to say copilot?

A rambly "thinking" model like this is way too slow for coding assistance imo, although maybe it could take on larger assignments than you could get out of a chat or coding model.

Let's be honest. Its not only the kids. It is everyone...

What about legal stuff? Are you not worries of someone doing illegal stuff?

s/JSON/YAML/ :)

Perhaps nsdr (popularized by Huberman).

This

Valio lietuviams!

Fingers crossed for Intel. We need them in competition…

One of my friends says that the reason why this and several other important problems haven't been solved is because the problems themselves are just too valuable. Think of all the money flowing around...

It is a new attack vector on systems. Forging scam that would fool LLMs and trick the user in the end