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.
How does not thinking advance your argument?
Have you tried asking people instead of not thinking?
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.