←back to thread

1901 points l2silver | 1 comments | | HN request time: 0.211s | source

Maybe you've created your own AR program for wearables that shows the definition of a word when you highlight it IRL, or you've built a personal calendar app for your family to display on a monitor in the kitchen. Whatever it is, I'd love to hear it.
Show context
drcode ◴[] No.35744621[source]
I just moved to the bay area. I made an app that scrapes all bay area events from meetup, eventbrite, and a couple of other sites- This way you end up with around 100 events a day, way too much to read through.

So next I take each event, send it to chatgpt3.5 and ask it to rate this event on around 20 parameters. Next, I take the latitude/longitude of each event and measure driving distance from my house. Then I have a master formula based on my personal interests and driving preferences and an app shows me the 10 events every day most likely to be interesting to me for any day.

replies(15): >>35744780 #>>35744853 #>>35744984 #>>35746065 #>>35746371 #>>35746760 #>>35747007 #>>35752334 #>>35752860 #>>35753000 #>>35754669 #>>35756357 #>>35764290 #>>35765048 #>>35765576 #
gregw134 ◴[] No.35744853[source]
What's your prompt? I've been doing something similar but I've found it difficult to get chatgpt to output a consistent data format.
replies(3): >>35745511 #>>35747876 #>>35753981 #
drcode ◴[] No.35747876[source]
I use the chatgpt35-turbo "system" field for instructions, then put the event info into the "user" field

--- PROMPT ---

You are given a meetup event description. For each of the following attributes, return the percent likelihood that the event involves has that attribute, in CSV format:

Attributes:

- Technology

- Pets

- Exercise

Example:

Technology,0.3

Pets,0.1

Exercise,1.0

replies(1): >>35749415 #
1. drcode ◴[] No.35749415[source]
(The example values should be in percentages, can't edit anymore)