I’m curious if you’ve caught G3.1 Pro lying? I loved 2.5 pro particularly when it first released, but 3.0 seemed to be all messed up and wound up hallucinating a lot and then telling a lot of lies to cover it up. I’m really hoping, for both personal and alignment reasons, that they’ve corrected this in 3.1.
Not so far at least. I did notice that certain prompts work better for certain use-cases and nudge the model more towards a personality that seems to respond to question at the correct depth.
Did notice, that at least for explaining things in presentation slides, Gemini 3 Flash is almost equivalent and is much faster and cheaper.
What topics are you trying to cover? I am currently mostly trying ML/Linalg Math, these might be easy for current models.
I’m curious if you’ve caught G3.1 Pro lying? I loved 2.5 pro particularly when it first released, but 3.0 seemed to be all messed up and wound up hallucinating a lot and then telling a lot of lies to cover it up. I’m really hoping, for both personal and alignment reasons, that they’ve corrected this in 3.1.
Not so far at least. I did notice that certain prompts work better for certain use-cases and nudge the model more towards a personality that seems to respond to question at the correct depth.
Did notice, that at least for explaining things in presentation slides, Gemini 3 Flash is almost equivalent and is much faster and cheaper.
What topics are you trying to cover? I am currently mostly trying ML/Linalg Math, these might be easy for current models.