get_flat_ccs_offset() reads the base of the flat CCS storage from the
hardware, scales it by the number of enabled L3 nodes, and rounds the
result up to 128K. Everything below that offset is then ...
He use AI to put print statements, summarize output and describe code based on prints to narrow place of bug. This is exactly what AI is good at. Funny fact is that you don’t need data center scale model for it. You can do it with local model.
He use AI to put print statements, summarize output and describe code based on prints to narrow place of bug. This is exactly what AI is good at. Funny fact is that you don’t need data center scale model for it. You can do it with local model.
You may. You seem to not have seen the potatoes people are using. ;)
You can get a surprising amount of shit done with an Intel B580.
I am impressed by just how powerful that little GPU is for $300
300€ is already a lot people won’t be willing to pay for just one part of a computer.
the msrp is $250 and it gets similar performance to an rtx 2080
3060 ti 8GB and 32 GB DDR4 says no, I can’t do that or anything else useful with a local model.
However. Deepseek V4 flash is very cheap and fast. It’ll do anything simple and some complex things you throw at it