logoalt Hacker News

p-e-wtoday at 12:10 PM9 repliesview on HN

> Nowadays, with the focus on agentic use and coding, it seems models have all been RLHF’d to death

I don’t get it. If nobody likes this writing style, how can it be the result of human feedback? Something else is going on.


Replies

pathsjstoday at 12:20 PM

It's not that the writing style is bad; in fact LLMs write actually pretty well. It's just too much overfitted. And even a style that, in itself, is pleasurable to read, becomes annoying when the same figures of speech are used over and over again.

anon373839today at 12:46 PM

Because LLMs are pattern-extenders that have nothing to say. The training overfitted to the grace notes in good writing. And since LLMs can’t wield language with purpose or experience the feeling of the words, they use these devices arbitrarily.

I think this is the same flaw as coding agents seeing in every problem the call for a “smoke test” or the use of some unnecessary design pattern. The truest part of AI is the A.

show 1 reply
zahlmantoday at 6:35 PM

Because you can't actually do "good writing" by repeatedly applying the supposed idioms thereof. The tiny subsegment of humanity responsible for the RLHF don't necessarily have any good taste for writing; but even if they did, it's orders of magnitude harder to communicate than to make judgments of short samples, and communicating it by making those judgments is surely impossible.

Edit: I see that you got multiple replies all basically saying the same thing in very different words. There's an exquisite irony to that, I think.

Wowfunhappytoday at 12:12 PM

Because humans do like it, in reasonable quantities. The AI overlearns this and does it too much.

yusefnaporatoday at 2:12 PM

It's not that nobody likes it, in fact the problem is that people like each instance of it well enough in isolation. Millions of people think it's "good enough," so it gets amplified and repeated until every PR description starts to sound like a toothpaste jingle.

Bawoosettetoday at 12:14 PM

For "agentic use and coding," they are trained to take useful actions, not produce desirable natural language writing.

itopaloglu83today at 12:13 PM

Maybe it’s the dead internet.

All the bots and other LLMs providing feedback, so in reality it’s reflecting the reality in a sense.

jappgartoday at 12:13 PM

every one-hit wonder asks the same question.

we liked it until we didn't.

michelbtoday at 12:15 PM

i hate it, but plenty of people DO like it and plenty of people talk and write like that. It’s just corpspeak, being used a lot in the valley and beyond. And all upcoming hustlers running startups now feel the need to speak like that, feeding this machine.