Avatar

Phoenix

Phoenix@programming.dev
Joined
0 posts • 26 comments
Direct message

The real mystery is when they want five years of experience for the tech that’s been out for three.

permalink
report
reply

It’s even better when you ask it to write code for you, it generates a decent looking block, but upon closer inspection it imports a nonexistent library that just happens to do exactly what you were looking for.

That’s the best sort of hallucination, because it gets your hopes up.

permalink
report
parent
reply

Don’t know about Lovecraft, but the big creepypasta/web story thing these days is the SCP foundation. But I assume you’ve already heard about that one?

permalink
report
reply

The assertion that they cannot be cheap is funny, when Vicuna 13B was trained on all of $300.

Not $300,000. $300. And that gets you a model that’s almost parity with ChatGPT.

permalink
report
reply

Ah, the hyperbolic timechamber of job experience.

permalink
report
parent
reply

I read it a long time ago. The format is interesting, novel certainly. I suppose it’s the selling point, over the prose.

To me it seemed like there were many competing “ways” to read it as well. Like a maze, you can go different paths. Do you read it front to back? Niggle through the citations? Thread back through the holes? It’s not often you get a book that has this much re-read value.

permalink
report
reply

I’ve used WSL to run deepspeed before because inexplicably microsoft didn’t develop it for their own platform…

permalink
report
parent
reply

Der Prozess/The Trial is one of the better ones in my opinion. Really captures the essence of Kafka. Of course, it is also one of his longer works.

permalink
report
reply

Wayne June has excellent readings of Lovecraft’s works.

permalink
report
reply

It really is big. From baby’s first prompting on big corpo model learning how tokens work, to setting up your own environment to run models locally (Because hey, not everyone knows how to use git), to soft prompting, to training your own weights.

Nobody is realistically writing fundamental models unless they work with Google or whatever though.

permalink
report
parent
reply