I can't believe that we'll soon have drop-in remote workers, indistinguishable from a human worker, and it will be trained purely on behavioral inputs/outputs. Total behaviorism victory!
10
3
3
99
The best thing about supervised learning is that you can clone any static system arbitrarily well. The downside is that supervised learning only works for static targets. This is an AI koan and also career advice.

Apr 19, 2025 · 10:06 PM UTC

1
32
Replying to @sherjilozair
Do you see a future where this behaviour cloned policy becomes an initialisation for an RL agent and adapts to dynamic systems?
1
1
Yes! But it will require more than just vanilla RL, which also requires a static environment.
4
Load more