A verifiable task can be optimised by reinforcement learning until a neural network performs it extremely well.
0 members hold this · 1 public figure on record
Sign in to hold thisPublic figures on record
These are quotes korents collected from things people published elsewhere. They did not post here, and have not endorsed this site.
-
17 Nov 2025
Andrej Karpathy quoted
If a task/job is verifiable, then it is optimizable directly or via reinforcement learning, and a neural net can be trained to work extremely well.