AI ALIGNMENT FORUMTags
AF

The Pointers Problem

EditHistorySubscribe
Discussion (0)
Help improve this page (1 flag)
EditHistorySubscribe
Discussion (0)
Help improve this page (1 flag)
The Pointers Problem
Random Tag
Contributors
1
1Noosphere89

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. It was introduced in a post with the same name.

Posts tagged The Pointers Problem
Most Relevant
6
47The Pointers Problem: Human Values Are A Function Of Humans' Latent Variables
johnswentworth
2y
32
3
31Don't design agents which exploit adversarial inputs
Alex Turner, Garrett Baker
2mo
27
2
32Robust Delegation
Abram Demski, Scott Garrabrant
4y
2
2
27Alignment allows "nonrobust" decision-influences and doesn't require robust grading
Alex Turner
2mo
22
2
22Don't align agents to evaluations of plans
Alex Turner
2mo
28
1
18People care about each other even though they have imperfect motivational pointers?
Alex Turner
3mo
3
2
13[Intro to brain-like-AGI safety] 9. Takeaways from neuro 2/2: On AGI motivation
Steve Byrnes
10mo
4
2
8Stable Pointers to Value III: Recursive Quantilization
Abram Demski
5y
0
2
12Stable Pointers to Value II: Environmental Goals
Abram Demski
5y
0
2
9Stable Pointers to Value: An Agent Embedded in Its Own Utility Function
Abram Demski
5y
9
1
27The Pointers Problem: Clarifications/Variations
Abram Demski
2y
14
0
11Updating Utility Functions
JustinShovelain, Joar Skalse
9mo
0
Add Posts