inference speed is like monitor Hz; sure, you go from 60 to 120Hz and thats noticeable, but unless your model is AGI, at some point you're just generating more code than you'll ever realistically be able to control, audit and rely on.
So, context is probably more $/programming worth than inference speed.
I'm starting to think that if you have an AI repo thats basically about codegen, you should just close all issues automatically, the manually (or whatever) open the ones you/maintainers actually care about. Thats about the only way to kill some of the signal/noise ratio AIs are creating.
Then you could focus fire, like the script kiddies did with DDoS in the old days on fixing whatever preferred issues you have.
I mean sure; but look at it from their POV, controlling the medium is the message right from 1984. Like LLMs, you can't learn about doing evil things without seeing how they benefit yourself.
Cline just added a useless Note icon animation wherw it used to say "Thinking..." or whatever to signal contwng incoming. I think its nothing about faces. Our UI/UX designs put action items in lower right. Youtube skip button the most prominent..
reply