[HN Gopher] Measuring Goodhart's Law
___________________________________________________________________
Measuring Goodhart's Law
Author : todsacerdoti
Score : 24 points
Date : 2022-04-13 18:00 UTC (5 hours ago)
(HTM) web link (openai.com)
(TXT) w3m dump (openai.com)
| paulorlando wrote:
| Thanks for posting this. Would like to learn more detail on your
| work. I've been drawn to the topic by originally hearing about
| Goodhart's from developers, even though it interestingly
| originated with observations on UK's monetary policy.
|
| (I wrote a (non-math, non-AI) version to learn more about
| Goodhart's Law here: https://unintendedconsequenc.es/new-
| morality-of-attainment-g...)
| dr_dshiv wrote:
| What is best of n sampling? I didn't follow. Is that like, which
| of these n images is best, and then turning that into a measure?
| alextp wrote:
| Choose the top N according to the proxy objective and then use
| the real objective to choose the best out of those N
| candidates.
| buscoquadnary wrote:
| Sounds likes the outcome of this measuring isn't such a great
| measure anymore.
| uoaei wrote:
| The irony is the point, I think.
___________________________________________________________________
(page generated 2022-04-13 23:01 UTC)