@ThatShawGuy yes, i think it could be useful if accurate... but otoh ive tried it on tweets and it doesn't always get the right answer... so could be an issue if injecting bad information into the convo?
More notes on nearby ideas
Reply · Apr 15, 2023hehehehe had been working on prompt for bulk vibecheck of tweets by Velveteen Rabbit bot... coding up the bot for bsky now <3Reply · Apr 9, 2023lol yeah I have some decent GPT-4 prompts for this, hmmmmmReply · Jan 29, 2025@arithmoquine i think the twitter api & other options for automation make it painful to build context that would inform better replies? but also yes i…Reply · Apr 4, 2023@jeremymstamper lol is GPT still writing your tweets for you?