Trilogy3452@lemmy.world to Technology@lemmy.worldEnglish · 5 hours agoAnthropic/OpenAI may be spending more than $1000 for every $100 you pay themea.rna.nlexternal-linkmessage-square58fedilinkarrow-up1218arrow-down15
arrow-up1213arrow-down1external-linkAnthropic/OpenAI may be spending more than $1000 for every $100 you pay themea.rna.nlTrilogy3452@lemmy.world to Technology@lemmy.worldEnglish · 5 hours agomessage-square58fedilink
minus-squaregreyscale@lemmy.grey.ooolinkfedilinkEnglisharrow-up3arrow-down1·4 hours agolfm2 works like greased lightning on the NPU built into the current macbook M5.
minus-squareag10n@lemmy.worldlinkfedilinkEnglisharrow-up1·3 hours agoDescribe greased lightning, because it’s much slower and needs to handle compression for context We’re moving in that direction but an M5 is not what the majority of people are running at home
minus-squaregreyscale@lemmy.grey.ooolinkfedilinkEnglisharrow-up1·48 minutes agoI dunno man, I’m not a slopjockey so I don’t know the minutiae of the addiction. All of our devs appear to have M5s right now. All of those copilot+ laptops have NPUs too.
minus-squareag10n@lemmy.worldlinkfedilinkEnglisharrow-up1arrow-down1·27 minutes agoYour company has bought you the latest and greatest and likely supports commercial token usage too You can’t compare LLMs at scale to running it locally; same experience and capabilities
minus-squaregreyscale@lemmy.grey.ooolinkfedilinkEnglisharrow-up1·17 minutes ago“Latest and greatest” my fucking sides lmao My company gave me some US shitware and I’ve got some local shitware instead. If you can’t make that work and are dependent on the teat of the slopgenerators, that’s a skill issue on you, buddy.
lfm2 works like greased lightning on the NPU built into the current macbook M5.
Describe greased lightning, because it’s much slower and needs to handle compression for context
We’re moving in that direction but an M5 is not what the majority of people are running at home
I dunno man, I’m not a slopjockey so I don’t know the minutiae of the addiction.
All of our devs appear to have M5s right now. All of those copilot+ laptops have NPUs too.
Your company has bought you the latest and greatest and likely supports commercial token usage too
You can’t compare LLMs at scale to running it locally; same experience and capabilities
“Latest and greatest” my fucking sides lmao
My company gave me some US shitware and I’ve got some local shitware instead.
If you can’t make that work and are dependent on the teat of the slopgenerators, that’s a skill issue on you, buddy.