← Back to context

Comment by himata4113

4 hours ago

it's actually the end of the beginning, there's walls that self-improving models hit that are never overcome even when given vast amounts of time.

I don't think anyone has ever tried having a model fully autonomously train a model that is better than it.

  • Everyone including myself has attempted this relentlessly, it just doesn't work out beyond some arbitrary improvement in specific tested categories instead of broader capability increase.