To make this work at all, you have to carefully tune your learning rat
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I've just bought the url http://VerminFlow.com so don't even think about it.

Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Ratinforcement Learning!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
RL just got a new name: Rat Learning!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I would hope so. Rodents are phenomenally problem-solvers
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
How about a deep learning model that is constantly HUNGRY and will stop at nothing until it is fed? I bet that model could evolve to AGI—it’s happened once before!
-
Reinforcement learning already uses different types of reward signals and nothing of this sort emerges.
- Show replies
New conversation -
-
-
Oh, I'm afraid it's much worse. Bees are better. Bees!https://twitter.com/jmac_ai/status/835544033644654592 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This Tweet is unavailable.
-
Maybe entirely not with current digital Computers if Logic, planning and Action Potentials are driven by quantum processes.
- Show replies
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.