3·
22 hours agoI mean, you can have that today, in some form or other, since that’s just how local AI works.
- 0 Posts
- 196 Comments
Joined 3 years ago
Cake day: July 9th, 2023
You are not logged in. If you use a Fediverse account that is able to follow users, you can follow this user.
So German supermarkets can’t sell us €4 rotisserie chickens at a loss just for the foot traffic? Damn.
Ahh now it makes sense! Was living elsewhere when the first seasons aired in the states but have heard a lot about it since, even if I don’t recognize the characters. Need to watch it sometime. (OK just checked the wiki and apparently it’s up to 22 seasons lol, so maybe I’ll find an abridged version or try speed reading the manga or something.)
Thank you for the explanation!
0·3 days agoCertain styles use a replaceable magnetic impeller that gradually loses its fins. Ours became noticeable at 4/6 fins and wouldn’t drain at all by 2/6 fins.
Oh god that’s gross. I mean the top frame. The bottom is funny.
3·4 days agoHaha of course
One of these things is not like the others
Ah that makes sense
I’m thinking with my one brain cell that this must be the plot of the movie the meme template came from, but I’m too lazy to check
Who are you who are so wise in the ways of science?
Yeah something about mortars and pestles
Wait. I’m trying to follow. Is this image the original and the one above are fans replicating it IRL?
Atm the meta for local inference is unified memory and “routed” local agents (multiple smaller role-specific agents in a trench coat)
The former is standout for cost efficiency (e.g., 4x RDMA 48gb Minis for a 192gb cluster @ $43/gb vs a $45k b200 alone)
The latter is standout for many things, including resource efficiency on smaller machines