News for hackers. Stuff that matters.
Re:Gemini-2.5-pro-preview-06-05 by Workaccount2 on Thursday June 05, 2025 @04:36PM (#44195544)
People can ask whatever they want on LMarena, so a question like "List some good snacks to bring to work" might elicit a win for a old/tiny/deprecated model simply because it lists the snack the user liked more.
Re:Gemini-2.5-pro-preview-06-05 by AstroBen on Thursday June 05, 2025 @05:41PM (#44196060)
are you saying that's a bad way to judge a model? Not sure why we'd want ones that choose bad snacks