Conversation

Notices

1. Embed this notice
   I am Water (slicerdicer@friedcheese.us)'s status on Saturday, 13-Sep-2025 01:09:12 JST I am Water
   We’ve hit a point where AI can’t do basic task of printf.
   
   Enjoy being rehired in near future.
   • Doughnut Lollipop 【記録係】:blobfoxgooglymlem: likes this.
   • Embed this notice
     feld (feld@friedcheese.us)'s status on Saturday, 13-Sep-2025 01:37:53 JST feld

     in reply to
     @SlicerDicer seems to me like they have more demand then they can handle so they are trying everything they can and it just makes the entire thing useless
     
     dumping more money in to handle the load seems like a bad idea
     
     the future has to be local-only models
     Another Linux Walt Alt likes this.
   • Embed this notice
     I am Water (slicerdicer@friedcheese.us)'s status on Saturday, 13-Sep-2025 02:00:30 JST I am Water

     in reply to

     • feld
     @feld Local or hosted models makes no difference, the reality is that the models need to be tuned per task. They need to behave in ways that are not harmful to the user and allow the user to opt for the model to run slower or faster for given tasks.
     
     If you are struggling with the model handling your context from loss of attention or heads? You should be able to increase its accuracy at cost of performance. Run fast when you can, but when it’s actively harmful you should be able to turn up the heat so to speak.
     lainy likes this.