41–50 of 62 posts
Earlier quoted context omitted.
>How do you know if these LLMs are stating facts instead of hallucinating? At runtime. When trying to do something I know is even slightly unusual I don't even bother with ChatGPT and friends.
What works in a toy example doesn't necessarily scale / handle corner cases.
Earlier quoted context omitted.
That doesn't work. It can't think through corner cases, because LLMs don't think. They aren't actually synthesizing or revising anything.
The reason people are so excited about it is because they see it work (yes, this includes whatever edge case you came up with five seconds ago - they can think too). No amount of theorised "oh they just do this thing and they don't have Qualia" is going to change reality: The model does something that people find use in.
Earlier quoted context omitted.
>How do you know if these LLMs are stating facts instead of hallucinating? At runtime. When trying to do something I know is even slightly unusual I don't even bother with ChatGPT and friends.
What works in a toy example doesn't necessarily scale / handle corner cases.
I tend to read along with the code it's writing and make suggestions when I see it's missing stuff, or I fill it in myself afterwards, depending. For one it can type out the annoying bits much faster than I can!
At the moment I do keep the general plan in my head myself though, and I thoroughly read anything it generates before I run it.
So basically the expert/author will help fine tune the model.
Sure CGPT can generate a table of contents if you want to learn a programming language for instance, tell you what to do first, what to try, delve deep in concepts, etc., but I think it's still hit or miss, as opposed to great tech authors and great publishers, where you can be sure you're getting your money's worth.
Also, IMO people tend to have a bias to go slower with paper material, because they committed to reading a book, they are less likely to skip sections, which means the end result is that you get more out of a book than the Html/pdf same content, might be different if you need to try things out on a computer while reading though.
Earlier quoted context omitted.
Agreed completely. LLMs are making the quick jot to Stack Overflow obsolete, which solves your immediate problems using the least amount of brainpower. They are also making reference-style documentation and long-form books more important than ever, since you still need to learn things and correct your own knowledge biases.
LLMs are making the quick jot to Stack Overflow obsolete Not for me they're not.
Earlier quoted context omitted.
LLMs are making the quick jot to Stack Overflow obsolete Not for me they're not.
For most people they are though
At one point in time, > 50% of people used to smoke cigarettes too.
Earlier quoted context omitted.
There is no money in creation. You can do with that what you will.
A controversial statement without any backing arguments. Even if it is true in some limited ways thanks to ChatGPT, remember that right as we speak someone is getting paid big bucks for creating ChatGPT. Do with that what you will.