News for hackers. Stuff that matters.
Re:Is the ChatGPT API Refusing to Summarize Academic Papers? by spdustin on Wednesday January 03, 2024 @03:51PM (#38859729)
My gut tells me it's the last line about writing a "blog post" which could be interpreted as a guardrail-violating imperative.
Re:Is the ChatGPT API Refusing to Summarize Academic Papers? by terminous on Wednesday January 03, 2024 @04:50PM (#38860392)
That line also begins with "Now, take a deep breath" which an LLM cannot do.
Re:Is the ChatGPT API Refusing to Summarize Academic Papers? by blharr on Thursday January 04, 2024 @06:09AM (#38865626)
It likely could be, not to mention the prompt includes "Do not mention the authors names" which probably makes it thinks you are trying to plagiarize
Re:Is the ChatGPT API Refusing to Summarize Academic Papers? by seanhunter on Wednesday January 03, 2024 @05:02PM (#38860489)
Q: Is chatgpt refusing to summarize academic papers?

A: No. He was using a weird prompt which was sometimes causing problems.

Panic over.

Re:Is the ChatGPT API Refusing to Summarize Academic Papers? by htk on Wednesday January 03, 2024 @06:20PM (#38861167)
Absolutely. If anything, ChatGPT is saying it can't "take a deep breath". What a dumb prompt that was.
Re:Is the ChatGPT API Refusing to Summarize Academic Papers? by gs17 on Wednesday January 03, 2024 @08:36PM (#38862075)
It's from this paper (albeit not applied to ChatGPT?): https://arxiv.org/abs/2309.03409
Re:Is the ChatGPT API Refusing to Summarize Academic Papers? by blharr on Thursday January 04, 2024 @05:52AM (#38865523)
I'm a little surprised by the lack of the solution or deeper analysis. It seems like there are some hints towards figuring out the problem.

To more closely confirm the actual reason, the easiest bet would be to prompt further on rejection, or adding to the prompt "If you can't do something, please indicate why you can't"

I am almost certain that it's because of the wording of the prompt. I don't think it's that the prompt is "too complex." Instead, the prompt itself is self-contradictory. It tells the model it is to summarize, but at the end asks for it to write a blog post. It gets confused and just says that it can't do that because it is acting as a "summarizer" and not a "blog writer"