Omg, sign me up! I'm gonna put that script in production for a server used by millions of customers around the world!

6. Boss thinks AI can code at senior developer level and fires you and the entire team

You don't need a private nuclear plant to run it? Wow very efficient.

Learn more: openai.com/pandoc

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.

A world of difference

be sure to include the metadata too. lol

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

We know that his dad is an engineering professor at university of Nebraska too. Really calls into question his credentials. I checked the other day and they had already removed his contact info from their website.

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.

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.

Training the most insane AI model on classified federal documents.

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.

What Greek scrolls?

It's so easy! Watch:

{"contents": "<garbled .docx contents goes here>"}

Not at all. The only similarity is that LLMs work with text, and the document formats can also represent text.

Each format (E.g pdf, json, excel) has a defined standard, so all you have to do to change between each other is to map one format's fields to the others. You don't need (and won't get good results) from having an LLM produce the new format from scratch.

What he's asking is the equivalent of asking if there's an LLM made specifically for solving arithmetic problems. Why would you try to solve addition using an LLM?