Hmmm, I took it the opposite way, actually.

There are many ambitious things I have tried to work with Opus 4.8 and Opus 5.5 on, and it just can't get there. It always falls back to some tried and true method or some valley that it gets stuck in. In those times, it was impossible to push it forward into more creative and exploratory thinking based upon my relatively advanced pushes and contextualizing. So I took the commenter's position that Fable 5.2 will respond better to that type of pushing. But that type of pushing actually means you know more than those who are happy enough using the lower models. So that seems like the opposite of what you said.

▲

kragen an hour ago | parent [-]

I'm interested to hear about what kinds of things you've been trying and what the stuckness looks like.

▲

bmitc 5 minutes ago | parent | next [-]

They are generally things I don't particularly want to share, as I view them as ideas close to my heart. The general pattern was what felt like redirecting from the harder problems and an unwillingness, if we can call it that, to go there. In some sense though, it's hard to understand how these more advanced models get around that, because these models are tuned to the most probable answer. When you come at them with a novel idea, they always seem to water it down in the end.

▲

ftchd an hour ago | parent | prev [-]

The dev version of "I'll fix him"

	▲	kragen 20 minutes ago \| parent [-]
		Are you saying that's you're seeing stuckness of that form, or are you paraphrasing some kind of misunderstanding of my question?