Comment by perching_aix
3 days ago
I wonder if I'm secretly being routed to some low grade version of Sol, or any of the GPT models really. Their performance is outright insulting at times, even at maximum reasoning, yet if I were to only read HN, I'd never know.
I've mostly actually stuck to low reasoning for most tasks since it seems to do a surprisingly good job even at low for the stuff I've been throwing at it, and I literally switched directly from Fable 5 to Sol more or less.