I love Opus 4.6 and it’s become my daily driver because it’s fast and “good enough”, but this thread is exactly accurate — its biggest flaw is shallowness in search and credulity. You can prompt your way around a lot of this behaviour but it’s more work.
toucan
toucanMar 4, 16:09
The worst capability for Opus 4.6 is search. It would be a far, far better model if it was only good at search. To be fair, none of the models are good at search, but with Opus 4.6 it would be an incredible capabilities jump if only it could do search.
For questions where the right precise answer really matters and you want something slightly disagreeable GPT Pro is still king
403