Comment by threethirtytwo
2 hours ago
I don't think anyone has ever tried having a model fully autonomously train a model that is better than it.
2 hours ago
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.
Did you publish on that topic? Just curious, would love reading more
There's a pretty large paper on the topic: https://arxiv.org/pdf/2606.15497, but results are somewhat mixed.