• Maddier1993@programming.dev
    link
    fedilink
    English
    arrow-up
    5
    ·
    1 month ago

    As an ML Acolyte, Even I can tell that it’s a well known phenomenon that ensemble methods are more resilient to overfitting issues. What’s fascinating is humanity’s penchant to forget the past and rediscover stuff.

    • robsteranium@lemmy.world
      link
      fedilink
      English
      arrow-up
      1
      ·
      1 month ago

      Yeah this is an interesting way to compose the ensemble though. Rather than averaging over sub-networks they’re synthesizing the panel of responses:

      A judge model reads every panel response and produces structured analysis: consensus points, contradictions, partial coverage, unique insights, blind spots

      Whereas beam search injects variance by trialling candidate sentences and mixture of experts has competing sub-models here we’re reconciling different ideas.

      Notice though that they’re always using Opus 4.8 as the judge so I think the claim (of surpassing frontier models) is over-inflated. I’d instead characterise it as outsourcing legwork to cheaper models.

      I’m still optimistic about ensembles of smaller models though. You could imagine a specialist synthesis model or advantages from combining latent activations instead of text responses