Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by npunt on Wednesday October 30, 2024 @05:58PM
(#42000899)
"...in AI" will be the psychology equivalent of biology's "...in Mice"
Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by marviel on Wednesday October 30, 2024 @06:01PM
(#42000931)
It will! Not 1:1, has issues, but gives hints.
Also much more scalable.
Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by miningape on Wednesday October 30, 2024 @06:03PM
(#42000954)
> Not 1:1, has issues, but gives hints.
> Also much more scalable.
This same description could be applied to lab mice
Re:Chain-of-Thought Can Hurt Performance on Tasks Where Thin...
by Terr_ on Wednesday October 30, 2024 @06:36PM
(#42001263)
It'll probably be a ways before we start making shrines to their unwilling participation though.
https://en.wikipedia.org/wiki/Monument_to_the_laboratory_mou...
I think it shows great promise as a way to sidestep the ethical concerns (and the reproducibility issues) associated with traditional psychology research.
One idea in this space I think a lot about is from the Google paper on curiosity and procrastination in reinforcement learning: https://research.google/blog/curiosity-and-procrastination-i...
Basically the idea is that you can model curiosity as a reward signal proportional to your prediction error. They do an experiment where they train an ML system to explore a maze using curiosity, and it performs the task more efficiently -- UNTIL they add a "screen" in the maze that shows random images. In this case, the agent maximizes the curiosity reward by just staring at the screen.
Feels a little too relatable sometimes, as a highly curious person with procrastination issues :)