This new Fable 5.1 model by anthropic is a joke.
A single ultracode session consumed 42% of the weekly limit. Sub agents keep failing, for no reason. Then hits session limits on this single run retrying the sub-agents.
Basically 42% of the weeks $200/month burned to failure
Sometimes it feels strange to make things with AI.
Feels like being an imposter, like “you didn’t really make that, AI did.”
But then I remember I used to make a lot of this same stuff before AI, just a lot slower. And I feel good about these new tools again.
Something interesting about the age of AI, is the realization that most ideas are crap.
Because now you can build basically anything. And people do.
But the vast majority of it ppl either do not want, adds no value, or cannot be marketed.
