- cross-posted to:
- programmer_humor@programming.dev
- cross-posted to:
- programmer_humor@programming.dev
You must log in or register to comment.
The secret to success in software engineering:
- Lie and say that there is
- Write or use a conversion algorithm
- Boss won’t know the difference
- Collect bonus at performance evaluation
- Put “AI engineer” on resume
- Boss thinks AI can code at senior developer level and fires you and the entire team
- Never plan on staying at a SE job for longer than a few years. Not in a market that volitile.
I have to admit, PDF parsing being such a hot and profitable topic in computer science was really something I never saw coming.
PDFs? The things you can select text from? And when not, there’s decent OCR? And when not, you just ask the person to send you an email or a word doc?
It sounds like LLMs are looking for a new unpolluted source of historical data that they can learn from, and this source exists in the form of old scanned-in paper documents. That’s the only reason I can fathom as to why this is such a big thing now.
Selecting text doesn’t work in most multi-column pdfs and good OCR cost money. And if the original source is lost and you want an exact copy in word, the OCR tools need to be really good at guessing whitespace-to-line ratio, because pdf is only an output format and not a processing format.
For most other converting needs, there’s pandoc, imagemagick and ffmpeg.
Every time I try to convert a PDF to epub or something, or OCR one that doesn’t actually have selectable text, it turns out shit. I assume the real reason people would want to get LLMs involved is that there is actually a lot of ambiguity in what a correct conversion would be, and there are a lot of PDFs out there.
I self host sterling-pdf and I haven’t had an issue with file conversion in… When did I set this thing up?
To be truthful, the machine I had it running on has been sent to the grave (I sold it) so I don’t actually have this service running right now
Training the most insane AI model on classified federal documents.
Yes it’s an LLM called pandoc, you can run it locally
You don’t need a private nuclear plant to run it? Wow very efficient.
Black magic software.
Learn more: openai.com/pandoc
This is that special blend of Tablet Kid “I don’t need to know things I can google them” and Rich Kid “I don’t need to do things I can crowdsource them” that makes for that Distinctively VP “I don’t know what I’m doing and nobody can tell 👈😎👉”
No need, there’s an unmaintained javascript library for that (written by a 12-yr old)
Omg, sign me up! I’m gonna put that script in production for a server used by millions of customers around the world!
Oh no, now there is a security audit and the pdf generated is insecure, the unpaid developer that has not logged in since 2015 has to fix this ASAP
what? invest money to pay for open source software? are you nuts?
Technically OCR is an application of machine learning.
Not an LLM, though.
regularizing the OCR’d form into a json/html file might be a good application of an LLM though. Perhaps this is what they were asking about.
I doubt they even know what they are asking about?
Is this fake?
For context, this is the guy who figured out how to see what’s written on some ancient Greek Scrolls without destroying them. It seems slightly far-fetched that he wouldn’t know better.
Initially, I didn’t think these kids were fall guys.
Now I think they’re fall guys.
That was my thought. Young kids fresh out of school are really easy to manipulate into delusions of grandeur, especially when said delusions are offered by the richest person in the world. He’s gonna leave them out for the wolves.
Either that or Musk himself is truly so incompetent he thinks these kids are true geniuses. Honestly, with how things are going, that’s a fiddy-fiddy chance, because Musk is somehow almost as unbelievably stupid as Trump.
yes me send me what you want me to parse and i will get back to you in 3-4 business days
How is that a stupid question?
Large Language Models are for natural language processing, not for converting between text document file formats.
Perhaps the best way would be through an analogy:
“Are there any thermonuclear bombs made specifically for lighting candles?”
Imagine getting a job like this and now half the nation knows your name…thats terrifying. being an intern may mean you have no idea of the true scope of what they are asking you to do.
Yeah, seems that’s the point. Old enough to competently perform what they’re told, but too young to realize the gravity of the situation and how wrong it is to partake in it.
that’s why we have 18 year soldiers …
It’s ok, with the experienced gained from being forced to grow up, some will come home and use their savings to buy a dodge ram on a 7 year loan at 18% apr.
They are public employees who are changing things at the core of our government. Why wouldn’t we know their names?
Government employees names aren’t secret (asides from a few exceptions) nor is their pay
Actually this is what they do.
Yeah, I don’t really get this one. The class clown is the kid who recognizes a function of a tool, correctly at that. Unlike a dipshit lawyer who let it hallucinate bogus case law. Hilarious.
There are programs that exist that explicitly do these sorts of things.
They have been around since long before llm.
This is a lazy and uneducated question.
He demonstrates he has done zero research and goes straight to the buzzword because he knows nothing.
