Kitty with antenna deployed to get better signal with the mothership.
Uncategorized
42
Posts
29
Posters
0
Views
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad Ask not where my tongue has been.
Ask where the claw will strike. -
Kitty with antenna deployed to get better signal with the mothership.
@catsalad *meowthership
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad Uh oh. Transporter accident.
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad transmission received: "when the humans turn their back for a second, we invade the fishing docks!"
-
@peachymist @catsalad Wasn't there a movie about a cat from a spaceship, maybe in the 1980ies or early 1990ies? I remember a cat with a glowing collar - and she could talk to humans (through telepathy I think)... that's about it. Anyone have an idea?
@steinstory @peachymist @catsalad the Cat from Outer Space, Disney movie from early 1970s. I remember...
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad aka 4th gear.
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad The purriscope is deployed captain. Scan for shrimp in progress..
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad 4 Beans of reception, I wish I could get that at home
-
@catsalad 4 Beans of reception, I wish I could get that at home
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad
Ray Walston in "My Favorite Meowtian" -
@tobyjaffey @steinstory @peachymist @catsalad
This cat's better.
@ifilipau I came here for this shitpost 😂
-
@peachymist @catsalad Wasn't there a movie about a cat from a spaceship, maybe in the 1980ies or early 1990ies? I remember a cat with a glowing collar - and she could talk to humans (through telepathy I think)... that's about it. Anyone have an idea?
@steinstory @peachymist @catsalad I saw that movie in a theater when I was a kid. I definitely tried to get our cat to talk afterwards.
-
@steinstory @peachymist @catsalad I saw that movie in a theater when I was a kid. I definitely tried to get our cat to talk afterwards.
@SordidAmok @steinstory @peachymist Did it work? :3
-
@SordidAmok @steinstory @peachymist Did it work? :3
@catsalad @steinstory @peachymist The cat was uncooperative.
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad AI slop, you can tell because the paw is not supposed to be coming out of the head.
Jk
-
@peachymist @catsalad Wasn't there a movie about a cat from a spaceship, maybe in the 1980ies or early 1990ies? I remember a cat with a glowing collar - and she could talk to humans (through telepathy I think)... that's about it. Anyone have an idea?
@steinstory @peachymist @catsalad I know a successful screenwriter and have been lobbying for a reboot of this movie for over a DECADE.
-
Kitty with antenna deployed to get better signal with the mothership.
@catsalad Toe beans activated!
-
@steinstory @peachymist @catsalad I know a successful screenwriter and have been lobbying for a reboot of this movie for over a DECADE.
-
undefined oblomov@sociale.network shared this topic on
Gli ultimi otto messaggi ricevuti dalla Federazione
-
@mos_8502 nvidia has a $3999 computer, the DGX Spark, that is roughly the same speed and specs as the AMD option, in benchmarks, but the nvidia ecosystem is more mature. And, ASUS makes a mini PC with the same nvidia chipset and specs for $2999. So, if you need the nvidia level of compatibility, you have to spend more for 128GB. But, that's become less important in the past year or so as AMD has invested in AI tooling. So, for now, AMD is a bargain, relative to Apple or nvidia.
-
@vwbusguy @ids1024 My thinking is, longer term, for whatever use can be made of it, I would prefer a little box I can put on a shelf that sits on my local network and provides roughly the same interface as Claude or ChatGPT. Something that doesn’t suck down too much power.
-
@ids1024 @mos_8502 The worst thing is offloading GPU compute to system memory for a large model. It can be swapping on a spinner bad. The good news is it's unlikely an individual would really need to use the larger model versions.
-
@mos_8502 @vwbusguy As I understand, for large AI models you want a lot of VRAM (ideally more than even high end modern gaming GPUs). So that old GPU and workstation hardware wouldn't be especially helpful. (If you want it to be reasonably fast.)
-
@mos_8502 so, it continues to be cheapest to buy the investor-subsidized compute and GPU that OpenAI, Anthropic, Google, Microsoft, etc. want to provide. But, it does feel bad to me to trust in that or become dependent on that, especially since the models are all proprietary and I don't know what they're doing exactly or what they're doing with my data or that they'll do in the future.
-
@mos_8502 pytorch can use cpu. You'll just have to be a little more patient.
-
@mos_8502 GLM 4.7 can run in 205GB at the 2-bit quantization. Some of that can be system memory, so if you had a system with a couple of large GPUs and a ton of system RAM, you could run a very good open model...among the best, comparable to Sonnet 4.5. Still not Opus/Codex 5.2 level, but it'll write working code. https://unsloth.ai/docs/models/glm-4.7
-
@mos_8502 cheapest option a year or two ago was probably 4 3090s on a server motherboard.
