Comment by al_borland

> These models are demonstrating an incredible capacity for logical abstract reasoning of a level far greater than 99.9% of the world's population.

And yet they have trouble knowing that a person should take their car to a car wash.

I also saw a college professor who put various AI models through all his exams for a freshman(?) level class. Most failed, I think one barely passed, if I remember correctly.

I’ve been reading about people being shocked by how good things are for years now, but while there may be moments of what seems like incredible brilliance, there are also moments of profound stupidity. AI optimists seem to ignore these moments, but they very real.

If someone on my team performed like AI, I wouldn’t trust them with anything.