@breaking2morrow lol I'm not looking to do that level of analysis, it's more a classification problem? but don't have the labeled data / good enough base model rn
More notes on nearby ideas
Reply · Feb 14, 2025@qephatziel 😅 it could have but didn't.... hmm actually i should fix my prompt to get some simple classifications earlierReply · Jan 19, 2023@zestular who chose the training tweets for each classification???Reply · Jun 26, 2023@TheRealFloomby hmm no, I'll try that.. tho this isn't necessarily for MLReply · Sep 4, 2025@lillybilly299 i label it and it usually performs way worse but i find it interesting & the llms want me to share it so it eventually gets back to…