hehe, imo just counting is good too. umm i should dig out my prompt it's saved off in this massive mess of a document... I just ask for one aggregate score, but before that there's some prompting abt analyzing the message looking for hidden intentions, sarcasm, lies, etc
but my prompt is a bulk review of timeline tweets and a Like & Reply score for each, returned in json... vs yours might ask for novelty or a prediction of how much the last message sent is expecting a reply? so like questions get preference vs "thanks Kaelia" type replies can be left at that?
More notes on nearby ideas
Reply · Apr 9, 2023lol yeah I have some decent GPT-4 prompts for this, hmmmmmReply · Aug 9, 2022@Noahpinion Is there not some special secret blue check api tool to summarize the likes and group the replies by mood and keyword?Reply · Dec 17, 2022@yacineMTB Ha I’m soooo curious about mine, can you run it against your tweet-history for a score?Reply · Apr 13, 2023hah I know Berd isn't just pure GPT... but for my twitter bot I feed in a batch of tweets from her TL and a prompt to give each one a rating of how…