[laichzeit0]

Same. I don’t know what Mickey Mouse work people are doing that 4.8 is “enough”. CRUD apps maybe?

I have some serious Bayesian statistical research programs running and Fable is on another level than 4.8. It feels like Andrew Gelman is supervising it. Even the vision model on Fable is superior to 4.8 which is great for having it digest research papers.

[selimthegrim]

Would you say it is definitely catching bugs that Opus wouldn't?

[cjbgkagh]

(Not GP) I would, a lot of my work now is at the edge of what Fable is capable of and even then only with a lot of hand holding. Opus has no chance. I’ve been using Sol and that has been better than Fable in that it needs much less handholding and is much less likely to burn its tokens spinning its wheels.

[selimthegrim]

Well I am doing some Bayesian stuff so I was curious what GP had to say too