Conversation

Notices

1. Embed this notice
   Feoh (feoh@oldbytes.space)'s status on Sunday, 11-Jun-2023 23:29:25 JST Feoh

   @alyssa Respectfully, I don't agree. LLMs are super at helping out when you can *know* without the tiniest sliver of doubt that the results are correct, and when you treat the results like a suggestion to be vetted, corrected and massaged and not a completed final deliverable.

   • Embed this notice
     feld (feld@bikeshed.party)'s status on Sunday, 11-Jun-2023 23:32:50 JST feld

     in reply to
     @feoh @alyssa LLMs have already saved me countless hours of tedious work researching how to do things with languages and frameworks that I've never encountered before and I was able to quickly produce working examples.
     
     I really don't care if it's wrong 20% of the time, I'm capable of fixing its errors when they happen.