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

Re:Ask HN: Is it just me or GPT-4's quality has significantl... by gumballindie on Wednesday May 31, 2023 @09:42AM (#36138308)

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.

[ Parent | on HN ]

Re:Ask HN: Is it just me or GPT-4's quality has significantl... by layer8 on Wednesday May 31, 2023 @10:05AM (#36138576)

The PDF spec is of byzantine complexity, and is full of lose ends where things aren’t fully and unambiguously specified. It also relies on various other specs (e.g. font formats), not to mention proprietary Adobe extensions.

[ Parent | on HN ]

Re:Ask HN: Is it just me or GPT-4's quality has significantl... by andruby on Wednesday May 31, 2023 @09:58AM (#36138503)

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.

[ Parent | on HN ]

Re:Ask HN: Is it just me or GPT-4's quality has significantl... by gumballindie on Wednesday May 31, 2023 @10:01AM (#36138539)

Thats not a lot of code tho, but i see your point.

[ Parent | on HN ]

Re:Ask HN: Is it just me or GPT-4's quality has significantl... by Tostino on Wednesday May 31, 2023 @11:02AM (#36139168)

Try getting GPT-4 to spit out that much code and have it be coherent and run together.

[ Parent | on HN ]

Re:Ask HN: Is it just me or GPT-4's quality has significantl... by bandrami on Wednesday May 31, 2023 @09:59AM (#36138506)

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

[ Parent | on HN ]