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

Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

news.ycombinator.com

Post reply on HN
Print view View original

401–410 of 817 posts

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#401

Post by bevenky »

bob1029 wrote: post #266

OpenAI's models feel 100% nerfed to me at this point. I had it solving incredibly complex problems a few months ago (i.e. write a minimal PDF parser example), but today you will get scolded for asking such a complicated task of it. I think they programmed a classifier layer to detect certain coding tasks and shut it down with canned BS. I like to imagine certain billion/trillion-dollar mega corps had a back-room say…

I shared my exp below on one of the comments, sharing here too - I think overall the quality is significantly poorer on GPT4 with plugins and bing browsing enabled. If you disable those, I am able to get the same quality as before. The outputs are dramatically different. Would love to hear what everyone else sees when they try the same.

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#402

Post by kenjackson »

ajmurmann wrote: post #384
pixl97 wrote: post #359

Earlier quoted context omitted.

>Stop treating me like a child. And yet the moment they do that some lawyer submits a bunch of hallucinations to a court and they get in the news. Also, no, they don't want it outputting direct scam bullshit without a disclaimer or at least some clean up effort on the scammers part.

Does that have to be at the beginning of every answer though? Maybe this could be solved with an education section and a disclaimer when you sign up that makes clear that this isn't a search engine or Wikipedia, but a fancy text autocompleter. I also wonder if there is any hope for anyone as careless as the lawyer who didn't confirm the cited precedence.

I’ve seen here on HN that such a disclaimer would not be enough. And even the blurb they put in the beginning of the reply isn’t enough.

If the HN crowd gets mad that GOT produces incorrect answers, think how lay people might react.

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#403

Post by spiderice »

mitchdoogle wrote: post #348
LoganDark wrote: post #298

Earlier quoted context omitted.

> I personally don't get offended by words, but I guess if you are born after the 2000's perhaps you should avoid it. Ouch

Belittling the youth is one way that insecure people make themselves feel better about getting old.

Surely you can see the irony in your comment

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#405

Post by rejschaap »

LoganDark wrote: post #298
hanselot wrote: post #296

Earlier quoted context omitted.

[flagged]

> I personally don't get offended by words, but I guess if you are born after the 2000's perhaps you should avoid it. Ouch

Picked up some bad habits from 4chan?

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#406

Post by yifanl »

ajmurmann wrote: post #384
pixl97 wrote: post #359

Earlier quoted context omitted.

>Stop treating me like a child. And yet the moment they do that some lawyer submits a bunch of hallucinations to a court and they get in the news. Also, no, they don't want it outputting direct scam bullshit without a disclaimer or at least some clean up effort on the scammers part.

Does that have to be at the beginning of every answer though? Maybe this could be solved with an education section and a disclaimer when you sign up that makes clear that this isn't a search engine or Wikipedia, but a fancy text autocompleter. I also wonder if there is any hope for anyone as careless as the lawyer who didn't confirm the cited precedence.

Since there's about a million startups that are building vaguely different proxy wrappers around ChatGPT for their seed round, the CYA bit would have to be in the text to be as robust as possible.

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#407

Post by andruby »

gumballindie wrote: post #385
metalliqaz wrote: post #378

Earlier quoted context omitted.

how many lines of code do you think you could do it in?

I dont know - it’s a genuine question. I honestly didnt expect this to be a complex problem, let alone incredibly complex. I genuinely want to understand where the challenge lies.

If you want a datapoint, Origami is a "pure Ruby library to parse, modify and generate PDF documents".

That library cloc's in at 13,683 lines of code and 3,295 lines of comments.

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#408

Post by bandrami »

gumballindie wrote: post #385
metalliqaz wrote: post #378

Earlier quoted context omitted.

how many lines of code do you think you could do it in?

I dont know - it’s a genuine question. I honestly didnt expect this to be a complex problem, let alone incredibly complex. I genuinely want to understand where the challenge lies.

In the case of a PDF parser it has to embed a full PostScript interpreter

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#409

Post by humanistbot »

ajmurmann wrote: post #384
pixl97 wrote: post #359

Earlier quoted context omitted.

>Stop treating me like a child. And yet the moment they do that some lawyer submits a bunch of hallucinations to a court and they get in the news. Also, no, they don't want it outputting direct scam bullshit without a disclaimer or at least some clean up effort on the scammers part.

Does that have to be at the beginning of every answer though? Maybe this could be solved with an education section and a disclaimer when you sign up that makes clear that this isn't a search engine or Wikipedia, but a fancy text autocompleter. I also wonder if there is any hope for anyone as careless as the lawyer who didn't confirm the cited precedence.

> Maybe this could be solved with an education section and a disclaimer

You mean like the "Limitations" disclaimer that has been prominently displayed on the front page of the app, which says:

- May occasionally generate incorrect information

- May occasionally produce harmful instructions or biased content

- Limited knowledge of world and events after 2021

Re: Ask HN: Is it just me or GPT-4's quality has significantly deteriorated lately?

#410

Post by simonw »

brookst wrote: post #318
hanselot wrote: post #279

Earlier quoted context omitted.

How is racism different from stereotype? How is stereotype different from pattern recognition? These questions don't seem to go through the minds of people when developing "unbiased/impartial" technology. There is no such thing as objective. So, why pretend to be objective and unbiased, when we all know its a lie? Worst, if you pretend to be objective but aren't, then you are actually racist.

I’m tired of the “it’s not racist if aggregate statistics support my racism” thing. Racism, like other isms, means a belief that a person’s characteristics define their identity. It doesn’t matter if confounding factors mean that you can show that people of their race are associated with bad behaviors or low scores or whatever. I used GPT3.5 to generate 100 short descriptions of families for a project. Every single o…

What was your prompt?

LLMs take previous output into account when generating the next token. If it had already output 20 families of a similar shape, number 21 is more likely to match that shape.

Post reply on HN