Johannes C. Mayer | v1.5.0Dec 22nd 2023 | (+538/-86) | ||
Noosphere89 | v1.4.0Aug 6th 2022 | (+9/-25) | ||
Multicore | v1.3.0May 31st 2021 | |||
1point7point4 | v1.2.0Dec 10th 2020 | Tried to fix peculiar formatting issue. | ||
1point7point4 | v1.1.0Dec 10th 2020 | (+17671) Added a brief description. |
The pointers problem refers to the fact that most humans would rather have an AI that acts based on real-world human values, not just human estimates of their own values – and that the two will be different in many situations, since humans are not all-seeing or all-knowing[citation needed].knowing. It was introduced in a post with the same name.
The pointers problem refers to the fact that most humans would rather have an AI that acts based on real-world human values, not just human estimates of their own values – and that the two will be different in many situations, since humans are not all-seeing or all-knowing[citation needed].It was introduced in a post with the same name.
Consider an agent with a model of the world W. How does W relate to the real world. W might contain a chair. In order for W to be useful it needs to map to reality, i.e. there is a function
f
withW_chair ↦ R_chair
.The pointers problem
refersis about figuring outf
.In John's words (who introduced the concept here):
This relates to alignment, as we would
rather havelike an AI that acts based on real-world human values, not just human estimates of their own values – and that the two will be different in many situations, since humans are not all-seeing or all-knowing.It was introduced ina post with the same name.Therefore we'd like to figure out how to point to our values directly.