[kemcho]

The angle that being to detect confidently wrong, which then helps kicks off new learning is interesting.

Has anyone had any success with continuous learning type AI products? Seems like there’s a lot of hype around RL to specialise.

[ACCount37]

There's no "hype" because continuous learning is algorithmically hard and computationally intensive.

There's no known good recipe for continuous learning that's "worth it". No ready-made solution for everyone to copy. People are working on it, no doubt, but it's yet to get to the point of being readily applicable.