91–100 of 118 posts
I'm using it in three ways on a current project to reduce admin overhead for my company: 1. I've written a program that reconciles all my invoices against bank/cc transactions at the end of each quarter. My accountant otherwise has to do this by hand. It uses OpenAI's APIs to read the PDFs, parse out the invoicing party and amount(s), and as a fallback when classical NLP fails to parse dates. 2. I used GPT-4 to help…
I'm using it in three ways on a current project to reduce admin overhead for my company: 1. I've written a program that reconciles all my invoices against bank/cc transactions at the end of each quarter. My accountant otherwise has to do this by hand. It uses OpenAI's APIs to read the PDFs, parse out the invoicing party and amount(s), and as a fallback when classical NLP fails to parse dates. 2. I used GPT-4 to help…
What Open AI api are you using to read PDFs?
Not sure how to access that via API.
"How do I $ foo in $language_or_framework?"
Stuff like "What are the top 25 things I should do as a $x-year old man living in $state in the US to maintain optimum health and happiness?"
I think the medical stuff, in particular, is probably superior to advice from my local healthcare options. I use it for veterinary purposes, as well, and back it up with medical guide lookups and Googling reputable sources.
All of this requires a certain level of intelligence, skepticism and trust-but-verifyism on my part.
PS: Yes, I understand how you're flabbergasted that asking it for code works for me when you get nonsensical results. You don't need to leave me a comment. I have no explanation for you.
It's a bit surprising seeing all the positive replies to this thread. In my experience (using GPT-3), the time I spend debugging the code generated by the AI is almost the same as if I was to write it correctly in one go. The comprehension aspect kinda helps me sometimes, like when I need to understand some obscure shell script.
We need a catchy name for this, like [Someone]'s Law. It would read: "Whenever someone complains about chatbots/ChatGPT being overrated, they are basing their experience on non-GPT-4 interactions." It comes up over, and over, and over, on this forum and all the others I read. People need to know GPT-4 and pre-GPT-4 are not the same!
I'm using it in three ways on a current project to reduce admin overhead for my company: 1. I've written a program that reconciles all my invoices against bank/cc transactions at the end of each quarter. My accountant otherwise has to do this by hand. It uses OpenAI's APIs to read the PDFs, parse out the invoicing party and amount(s), and as a fallback when classical NLP fails to parse dates. 2. I used GPT-4 to help…
What Open AI api are you using to read PDFs?
Mostly to get around bad docs. I need to implement things using libraries, services, and APIs that aren't well documented, but the source code is public, and people have written code against them, and ChatGPT has read all of the things that I would read (and more) to get to the point where I can use it, so I just ask it. The 2021 knowledge limit is pretty annoying, since libraries change so often, but it's still very…
Many of the 'brain runs out in 2021' problems can be solved with plugins such as pdf readers and web browsers.
I do one-off text transformations that not worth writing a script for. Eg. paste a bunch of unformatted data and format them in json, find patterns in huge text etc.
I do one-off text transformations that not worth writing a script for. Eg. paste a bunch of unformatted data and format them in json, find patterns in huge text etc.
Agreed. For example, I recently had an auto-generated SQL query that I needed to debug. It was formatted on one line and was impossible to read. I asked GPT-4 to clean up the query and it gave me something that was much easier to consume. I definitely could have written some script for this or tried to find another tool, but it took me 20 seconds to just ask GPT-4 and get a reasonable result.
Earlier quoted context omitted.
One thing I am confused about is using ai for boiler plate code . Shouldn’t that be a macro or code generated, or even an aspect ? Having large snippets of ai generated code outside of a macro or code generation tool does not make any sense .
You still have to write the code for the macro. With ChatGPT you can just say “write a mapper between these two object in C# 11, make the target members uppercase and skip X, Y and Z”
Doing it for a mapping feels like a deficiency in the code unless chatgpt is putting thoughts behind the variable names and reasoning about what mapping makes the most sense.