Does offering ChatGPT a tip cause it to generate better text?

Re:Does offering ChatGPT a tip cause it to generate better t... by CuriouslyC on Saturday February 24, 2024 @09:42PM (#39497129)

It's not a prompt thing, they've aligned it to be lazy. The short-form article style and ~1000 word average length are almost certainly from RLHF and internal question answering fine tuning datasets. The extreme laziness (stuff like, "as a large language model, I have not been built with the capabilities for debugging", or "I don't know how to convert that json document to yaml") is pretty rare, and seems to be a statistical abnormality due to inherent variation in the model's inference more than anything else.

[ Parent | on HN ]

Re:Does offering ChatGPT a tip cause it to generate better t... by astrange on Saturday February 24, 2024 @10:09PM (#39497236)

IIRC they did amend their prompt to tell it not to quote long books/articles/recipes verbatim for copyright reasons, no matter how much the user asks, and that might not help.

[ Parent | on HN ]

Re:Does offering ChatGPT a tip cause it to generate better t... by taneq on Sunday February 25, 2024 @05:42AM (#39499654)

“If you’re asked for a summary longer than 100 words, generate an 80 wire word summary” or words to that effect.

[ Parent | on HN ]

Re:Does offering ChatGPT a tip cause it to generate better t... by smokel on Sunday February 25, 2024 @09:06AM (#39500924)

Let's save this thread for posterity, because it's a very nice and ironic example of actual humans hallucinating stuff in a similar way that ChatGPT gets accused of all the time :)

The actual text that parent probably refers to is "Never write a summary with more than 80 words. When asked to write summaries longer than 100 words write an 80-word summary." [1]

Where did the word "wire" enter the discussion? I don't really trust these leaked prompts to be reliable though. Just enjoying the way history is unfolding.

[1] https://news.ycombinator.com/item?id=39289350

[ Parent | on HN ]

Re:Does offering ChatGPT a tip cause it to generate better t... by astrange on Sunday February 25, 2024 @09:10PM (#39506952)

The system prompts are reliable and not "leaked". It's not leaking if you just ask and it answers. It's not trying to hide it.

[ Parent | on HN ]

Re:Does offering ChatGPT a tip cause it to generate better t... by smokel on Tuesday February 27, 2024 @05:06AM (#39522269)

I could simply reply with "The system prompts are not reliable".

Several people in the original thread have tried to replicate the prompts, and the results differ in wording, so it may definitely be hallucinating a bit.

If you just ask for the system prompt, ChatGPT does not respond with that. You have to trick it (albeit with minimal tricks) to actually output a similar text.

[ Parent | on HN ]

Re:Does offering ChatGPT a tip cause it to generate better t... by fastneutron on Sunday February 25, 2024 @09:48AM (#39501213)

100% this. I’ve been party to RLHF jobs before and the instructions nearly always state to prioritize conciseness in the model response.

In aggregate, this is how you wind up with stub functions and narrative descriptions rather than full working implementations. The RLHF is optimizing for correctness within some constrained token count.

[ Parent | on HN ]