For coding AI, it could make sense to specialize models on architecture, functional/array split from loopy solutions, or just asking 4 separate small models, and then using a judge model to pick the best parts of each.

  • panda_abyss@lemmy.ca
    link
    fedilink
    English
    arrow-up
    2
    ·
    16 days ago

    Yep, I’m actually getting pretty comparable results running devstral as an agent considered to a big model like Claude.

    You have to specify the problem better, but the tradeoff is I can run it locally.

    I’m still in the experiment phase of local models for agents, and they’re accomplishing tasks instead of just coding.

    I could see a connection of these agents passing tasks around being highly effective.