Hacker News Reader

Comment by joegibbs | Hacker News Reader

Now there's a benefit of AI that most people probably haven't considered: give it a few years and I bet you'll start seeing way less vacuous, cliched corporate writing once people have read enough AI output that they'll start identifying it with AI - even if it's written by a human.

Also, it seems like the reason that it does it is because you're trying to convert a couple of sentences into a full blog post/press release/article. All it has to go off is the input sentence - unlike an actual writer who (probably) has all the details about the subject. If you don't have the details and the result must be at least X length, then you're going to get a ton of useless padding around the only details that you've given it, because the only other thing that it could do would be making things up.

View on HN

It’s a little better than that as you can just give it your website or drop in some other articles for reference and it’ll pull out details and contextual use with its general knowledge. I’m hoping for the same thing, though. If the prompt is what you really want to say, said plainly, just post that!

>the prompt is what you really want

It crosses my mind every time i realise I am in the midst of some verbose, contentless, llm drivel, that i would prefer to read the prompt than the garbage that gets spat out.

There are a few tools floating around that do prompt extraction. I must admit i haven't gotten around to trying them out, but I have been toying with an idea to make a local browser plugin to strip a page down to its prompts and maybe find out why I was there in the first place.

That's why you use it for summarization or transformation not expansion.

I have a mathematician friend who studied mathematics at MIT and then worked in a research team at Google for some time. I caught up with him, and casually half-jokingly told him that I tried to understand some of his papers but I got nothing out of them.

And he replied, in earnest, that some of the papers are needlessly and deliberately complicated and obfuscated for a whole host of reasons (political reasons, career reasons etc).

This jargon-heavy circumlocutious academic speak you find often in papers, it's a gate-barrier... to keep out non-native English speakers, up-and-coming scholars? I don't know, but whatever the case, let's hope the outflow of papers written with LLM assistance takes a blow at the problem, when the corpus of literature is so diluted with all this that corporate-speak and jargon-heavy speak as a differentiator for in-group or whatever has a lesser incentive to exist.

https://paulgraham.com/simply.html

Academic language can be a bit jargony and tedious. But also, academics are people too. Is it at all possible that your friend was writing with an assumed audience of other experts and wanted to mitigate the extent to which your inability to get anything from the papers made you feel bad?

Ironically, one of the things llms are actually decent at is helping remove jargon and summarize text

It's a hit or a miss. In my experience, when they summarise they struggle to understand nuances and group things that seem similar in nature but really aren't.

Certainly Gemini for Google suites has been useless so far.

Reply on news.ycombinator.com