Re:Stability AI: Emad Mostaque resigned from his role as CEO
by razodactyl on Monday March 25, 2024 @08:45AM
(#39815620)
I can shed some light on this phenomena: These models are trained on many images but no thought is put into the "generalisation" aspect the ML community was so obsessed with during the deep-learning era.
It's very easy to create a "Stochastic Parrot" but I'm quite sure these models are capable of learning underlying information such as correct layout of a knot - given the right data and curriculum of course. Maybe slight architecture tweaks.
I'm sure this is the reason we're starting to see a normal amount of fingers or ability to write text. Proof of concept was 2015 until 2022 now we're starting to see interesting things come out of the workshops.
Whatever Kinbaku is... haha
I think a key part that's missing currently is the agent training approach: https://youtu.be/v3UBlEJDXR0?si=8w4Jt0bNEBfIXkZl
It's very easy to create a "Stochastic Parrot" but I'm quite sure these models are capable of learning underlying information such as correct layout of a knot - given the right data and curriculum of course. Maybe slight architecture tweaks.
I'm sure this is the reason we're starting to see a normal amount of fingers or ability to write text. Proof of concept was 2015 until 2022 now we're starting to see interesting things come out of the workshops.