TagLast edit: 16 Sep 2021 14:57 UTC by plex

A Quantilizer is a proposed AI design which aims to reduce the harms from Goodhart’s law and specification gaming by selecting reasonably effective actions from a distribution of human-like actions, rather than maximizing over actions. It it more of a theoretical tool for exploring ways around these problems than a practical buildable design.

See also

Quan­tiliz­ers max­i­mize ex­pected util­ity sub­ject to a con­ser­va­tive cost constraint

jessicata28 Sep 2015 2:17 UTC
12 points
0 comments5 min readLW link

Another view of quan­tiliz­ers: avoid­ing Good­hart’s Law

jessicata9 Jan 2016 4:02 UTC
5 points
0 comments2 min readLW link

When to use quantilization

RyanCarey5 Feb 2019 17:17 UTC
53 points
5 comments4 min readLW link

Quan­tilizer ≡ Op­ti­mizer with a Bounded Amount of Output

itaibn016 Nov 2021 1:03 UTC
10 points
4 comments2 min readLW link
No comments.