Hacker News new | past | comments | ask | show | jobs | submit
lelanthran | on: I put a datacenter GPU in my gaming PC
> The compute is still real. The VRAM is still real. And the memory bandwidth is where it gets genuinely surprising.

Because humans write exactly like this /s

postalrat | parent | next
Where do you think llms learned to write that way?
jlund-molfese | root | parent | next
You can also look at past posts by the same author (before LLM usage proliferated) if you’re curious.

The project is still very cool, but it’s a little less enjoyable to read when everything sounds the same. It would be just as annoying for people to manually write in a corporate/marketing style, because humanity is what makes the small web interesting.

https://blog.tymscar.com/posts/privategithubcicd/

loading story #48347905
iugtmkbdfil834 | root | parent
This, setting aside the llm issue, it is dealing with hardware in ways that -- one would think - would be celebrated on HN of all places. But we focus on presentation.
tgv | root | parent | next
Because their custom training data contains an emphasis on such verbiage. It doesn't come from the God-knows-how-many TB of web content the model is pre-trained on. There, such phrasing is only a drop in the sea. But the "yes, you're right" phrases, the em dash, etc., come from the later stage, for which content is created according to some (probably overprecise) guidelines.
rafram | root | parent
Right. The overuse of "genuinely" most of all. Seems like they put Claude through a few good rounds of training to always answer questions about its consciousness, thoughts, etc., with something about how it's "genuinely unsure," and as a result, the model learned to use "genuinely" as an intensifier in all sorts of inappropriate contexts.
iugtmkbdfil834 | root | parent
Oi, I personally use adverbs everywhere. Genuinely, kids these days.
alehlopeh | root | parent | next
Marketing content.
lelanthran | root | parent
> Where do you think llms learned to write that way?

Not from individual human content, that's for sure - maybe MLM marketing copy? Sleazy 4AM ads?

I mean, every time this response comes up, I keep asking the person to point at something written prior to 2022 that gets 80%+ on the LLM detectors, and yet no one can find anything.

Maybe you, postalrat, can find something written in this style that was published prior to 2022.

loading story #48348058
hattmall | root | parent
It's a function of the LLM "thought process"! It's not really modeled after human speech. It is in short segments but not long form, same reason you see the same rather odd nuances in LLM generated code.

If they way you thought was to run a bunch of if statements, generate content, then feed that content back to get a "score" of what seems the most plausible, run the if statements again, and adjust / merge responses, then you would write similarly. The recognizable cadence of LLM generated content is pretty clearly the result of a lot of if statements being fused together.

bossyTeacher | parent | next
X is Y. Z is Y. And Alpha is genuinely Beta.

Classic LLM writing style.

bitwize | parent | next
You know what the sad bit is? Humans do write exactly like that. That's not even particularly egregious StalkedIn marketroid speak.
driverdan | parent
There's interesting stuff in this writeup but it sure seems like most of it was written by an LLM.