Been working on my pet project today with Fable; it seems pretty solid but not too far removed from 4.8; same hallucinating, same type of bugs, same focus in large projects on just doing what you ask and just ignoring whatever that may touch/break/influence. Running tests in the beginning but when fuller context, just 'will run later' and never doing it in the end unless you tell it to (using some assorted swear words). I will keep using it but it's incremental as far as i'm seeing, not the OMG OMG OMG Mythos is here!

▲

LogicFailsMe 5 days ago | parent | next [-]

It clearly saw things immediately that 4.8 had missed on my projects. But shortly thereafter, having step functioned past those issues and impressed the crap out of me doing so, it got stuck in the usual endless loop talking about stuff more than doing stuff, occasionally deciding to pause so I'd have to whack it to get it going again.

So nope, not the AGI. But definitely an improvement.

	▲	justinclift 5 days ago \| parent [-]
		> it got stuck in the usual endless loop talking about stuff more than doing stuff That's the kind of behaviour I've seen in Claude Code (Opus 4.8) when it's context space is over the 40-50% range. I tend to keep an eye on the context usage (ie `/context`) quite a lot, and generally see good results as long as the context usage is ~30% or below. Which isn't heaps, considering having to ensure it has the required docs/stuff it needs can take 15-20% of context by itself.

▲

matheusmoreira 5 days ago | parent | prev [-]

I'm having the opposite experience. Fable seems to anticipate everything and do it all without asking. It's been very impressive and great to work with.

Not exactly strange behavior, Opus acted just like this too when I first subscribed. The popupar meme is Anthropic nerfed Opus during their capacity cruch. No idea if it's true, but I do wonder if Fable will fall victim to the same fate.