Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: Why does ChatGPT love the word "eager" so much?

news.ycombinator.com

Post reply on HN
Print view View original

41–50 of 69 posts

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#41

Post by trte9343r4 »

PeterisP wrote: post #14
wietze wrote: post #7

Although "eager" isn't called out, a recent study of academic publications shows that the use of LLMs can be measured through word frequency analysis [1], finding certain words are disproportionally represented: > We study vocabulary changes in 14 million PubMed abstracts from 2010–2024, and show how the appearance of LLMs led to an abrupt increase in the frequency of certain style words. 1: https://arxiv.org/html/24…

I don't want to look for the source of analysis right now, but I recall reading a study demonstrating that a large part, if not most of the word frequency shift was caused by RLHF training done on data predominantly generated by people hired from lower income English-speaking countries which simply have a different dialect of English with a noticeably different frequency of certain phrases and expressions, so e.g. at…

Yeah, right. ChatGPT was trained on Pidgin English dialect.

Have a look at BBC translation to get a taste, and tell me its not hoax: https://www.bbc.com/pidgin

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#42

Post by sandworm101 »

JohnMakin wrote: post #32

One of the funniest things I've ever heard/read about chatGPT "writing" is that it writes like a highschool student trying to inflate their word count on an essay. It typically uses a lot of words to say very little, and the style is hard to un-see once you recognize it.

>> like a highschool student trying to inflate their word count on an essay.

So the chameleon is a bad chameleon because it looks too much like a leaf, too much like the thing it is attempting to imitate?

A few years ago I was tasked with editing the performance reviews for my unit (military). Every supervisor had a finite number of characters in which to describe each soldier's performance. I went through and removed all the extra/useless words. Oh the anger! While supervisors agreed I had improved their writing, they now felt obligated to fill up all the blank space I had created.

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#43

Post by JohnMakin »

siva7 wrote: post #40
JohnMakin wrote: post #32

One of the funniest things I've ever heard/read about chatGPT "writing" is that it writes like a highschool student trying to inflate their word count on an essay. It typically uses a lot of words to say very little, and the style is hard to un-see once you recognize it.

It's called thinking out loud. Gets you better results. Try it out yourself.

ChatGPT doesn’t think

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#44

Post by balder1991 »

cowsaymoo wrote: post #35
llm_nerd wrote: post #17

Earlier quoted context omitted.

There wasn't a study or analysis. It was just lazy speculation that felt good because it could be bound up in a "evil white countries exploiting the developing world" narrative. Where exploiting was "paying to do a job". It was submitted as https://news.ycombinator.com/item?id=40623629 Again, there is effectively zero real data showing this. Further, RLHF isn't likely to reinforce such word selection regardless. A mo…

tinfoil had theory: they implanted watermarks already, so that AI generated text can be flagged for future training runs or as a service, such that some phrases are coaxed to become statistical beacons.

I believe that if that was possible to do on purpose, they wouldn’t have so much trouble preventing the LLMs from talking about things they shouldn’t.

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#45

Post by knodi123 »

sandworm101 wrote: post #42
JohnMakin wrote: post #32

One of the funniest things I've ever heard/read about chatGPT "writing" is that it writes like a highschool student trying to inflate their word count on an essay. It typically uses a lot of words to say very little, and the style is hard to un-see once you recognize it.

>> like a highschool student trying to inflate their word count on an essay. So the chameleon is a bad chameleon because it looks too much like a leaf, too much like the thing it is attempting to imitate? A few years ago I was tasked with editing the performance reviews for my unit (military). Every supervisor had a finite number of characters in which to describe each soldier's performance. I went through and remove…

I'm glad you asked about chameleons! Determining whether a chameleon is good or bad can be very important for lizard rankings. As everyone knows, a chameleon is able to camouflage to look more like a leaf. This can help protect it from predators! But sometimes looking like a leaf can go too far....

[and so on].

I hooked ChatGPT up to a speech recognizer and far field mics etc, trying to build my own alexa, and I had to add "Please be terse" to the prompt. And that wasn't enough, so I said "Please limit yourself to as few words as possible to convey the answer. Be terse. Try to keep your speech very short." before I finally started getting reasonable replies.

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#46

Post by jdietrich »

JohnMakin wrote: post #32

One of the funniest things I've ever heard/read about chatGPT "writing" is that it writes like a highschool student trying to inflate their word count on an essay. It typically uses a lot of words to say very little, and the style is hard to un-see once you recognize it.

ChatGPT will write in essentially any style you ask it to. The default behaviour is an artifact of RLHF training and the hidden pre-prompt, not a reflection of the capabilities of the underlying model. A pre-prompt along the following lines will radically change the nature of the output: "You are a subject matter expert in x. You communicate in a terse, information-dense manner. You make clear, strong arguments without vacillation."

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#49

Post by skywhopper »

llm_nerd wrote: post #17
PeterisP wrote: post #14

Earlier quoted context omitted.

I don't want to look for the source of analysis right now, but I recall reading a study demonstrating that a large part, if not most of the word frequency shift was caused by RLHF training done on data predominantly generated by people hired from lower income English-speaking countries which simply have a different dialect of English with a noticeably different frequency of certain phrases and expressions, so e.g. at…

There wasn't a study or analysis. It was just lazy speculation that felt good because it could be bound up in a "evil white countries exploiting the developing world" narrative. Where exploiting was "paying to do a job". It was submitted as https://news.ycombinator.com/item?id=40623629 Again, there is effectively zero real data showing this. Further, RLHF isn't likely to reinforce such word selection regardless. A mo…

Wait, why wouldn’t RLHF influence word choices?

Re: Ask HN: Why does ChatGPT love the word "eager" so much?

#50

Post by llm_nerd »

skywhopper wrote: post #49
llm_nerd wrote: post #17

Earlier quoted context omitted.

There wasn't a study or analysis. It was just lazy speculation that felt good because it could be bound up in a "evil white countries exploiting the developing world" narrative. Where exploiting was "paying to do a job". It was submitted as https://news.ycombinator.com/item?id=40623629 Again, there is effectively zero real data showing this. Further, RLHF isn't likely to reinforce such word selection regardless. A mo…

Wait, why wouldn’t RLHF influence word choices?

I didn't say it wouldn't (or rather couldn't), I said it was unlikely for the selected hypothesis given standard training data vs RLHF iterations.
Post reply on HN