Comment by Our_Benefactors
9 days ago
> Try running yourself a local model on a sufficiently beefy laptop
I don't understand why you think the solution to using a well tuned and intelligent model is to use one that is a dumbass
9 days ago
> Try running yourself a local model on a sufficiently beefy laptop
I don't understand why you think the solution to using a well tuned and intelligent model is to use one that is a dumbass
As the parachutist says to the pilot: "I'll stop jumping out of perfectly good airplanes as soon as they start making them."
I've fiddled with enough hosted ones enough to know the hosted solution's value add is almost entirely in the hardware stack it takes to serve inference traffic at scale, and whatever that company decides "alignment" means. The major quality is found in asking the right question, and getting the right answer. Not vomiting out subtly wrong answers faster. I don't need the thing doing work for me, I just need it to occasionally give me hints on where I might want to look when I get stuck. A local model fulfills that purpose just fine. It may take a bit to get an answer back, but you can bet your sweet ass that by the time I get that answer back, I've thought things through enough where I can pretty much instantly point out bullshit vs signal. Bonus: It doesn't add my codebases to the training dataset.
But please, do go on. Continue to tell me how a tool perfectly good for my use case is a bad idea. I'm all ears. > /dev/null
Lots of cope here about how the inferior tool is actually better.
When was the last time you tried a local model? You might actually be addicted to a dumb model that's just very quick at everything, which is what the GP is positing.
I've got the QWEN3.5 coder running and it's dumb, but if the task is 'clone this component and rewrite it to testWhatever' it does it perfectly well.
One might thing you're falling for the delusion being posited in this thread and you don't have a proper benchmark. You're just getting that token hit.