Basically I’ve being trying to sort a list of food by date. I took a rough note of each food and date and it gave it to ChatGPT and asked it to format and order it. It formatted it just fine but it couldn’t order it by date. Most of them were in the right place but there were a few out of place. For example at one point it gave me:
– 1st February 2024 – Cookies
– 1st March 2024 – Biscuits
– 1st June 2024 – Soup
– 3rd June 2024 – Chocolate
– 9th May 2024 – Chocolate
– 1st August 2024 – Eggs
– 1st August 2024 – Chicken
– 15th September 2024 – Yogurt
– 25th November 2024 – Sauce
– 16th November 2024 – Soup
– 19th November 2024 – Apple Juice
– 1st November 2024 – Potatoes
– 1st November 2024 – Soup
– 1st May 2024 – Carrots
– 1st January 2025 – Shortbread
– 1st January 2025 – Pasta
– 11th January 2025 – Noodles
– 1st January 2025 – Carrots
– 2nd February 2025 – Cereal
– 7th April 2025 – Green Beans
– 26th March 2025 – Rice
– 28th April 2025 – Pasta
– 1st May 2025 – Stock Cubes
I tried both written and numerical date formats. I also tried asking it to format it and then order it in separate queries so it was only doing one thing at once. I’ve tried a few separate lists and it happened with each. I also got the same results with copilot. When I pointed out the mistake it would say something like “sorry, here’s the correct list” and output the exact same thing. I then remembered something similar happened about a year ago when I asked it to list the Agatha Christie books in publication order and tell me which ones were in thr public domain. It listed them all but there were mistakes in the order. It would then tell me that only books published after (for example) 1926 or later are in the public domain, and then tell me that a book published in 1925 was.
So why can’t it do this? It seems like a very basic task, one that much less sophisticated programs could do. It has so much information, surely some of that information includes which order the months come in and that 25 comes after 16. I’ve had it do relatively complicated calculations based on a rough written description, so ordering a few dates thst are all formatted the same should be a walk in the park, right?
In: Technology
One more point on this.
People like to talk about the limits of AI based on chatbots like ChatGPT, but those aren’t the limits of AI, they’re just the limits of these particular chatbots right now.
LLM AI chat programs are, like other people have said, prediction engines which are made to sounds plausible, not necessarily correct.
But a lot of the tasks that these chatbots don’t reliably do well CAN be done reliably well by much much simpler programs. And it isn’t a huge leap to create AI not much unlike current chatbots that automatically or on command, lobs some data over to one of a library of simple programs. Sort a list. Look up the cast of a movie on IMDB etc.
I don’t know if you work in a tech or business space, but a big buzzword there is “Integrations”. It means tying together multiple programs to do complex tasks.
For instance, here’s something I built for my small business. When I make a new booking, I fill out a form with the service the client wants, their contact info, address etc. Once the form is submitted, my script takes all that information and stores it in a spreadsheet. It takes the address and uses Google Maps to calculate the distance and from that it calculates the travel fee. Then it goes to Google Docs, and uses a template to fill in a contract and invoice with all that information. Then it goes to Gmail and attaches a copy of both forms to a new email and sends that to the client with me copied.
All of that happens to be within Google because it’s pretty easy to tie google stuff together. But you can use integrations for ALL KINDS of programs. Tons of business, accounting etc online services make it really easy to plug in a million other services. And there are even services like Zapier which are just there to tie together other services.
It will not be a huge leap to tie a bunch of programs together so that a chatbot as a face does what it does well- writes kinda like it understands what you’re typing- while a bunch of other specialized programs, some AI, some probably not, do the other work, smash it all together and present it to you.
Latest Answers