LESSWRONG
LW

898
Samuel Nellessen
72520
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
[Hebbian Natural Abstractions] Introduction
Samuel Nellessen3y20

Thanks for pointing that out!

I wonder: we care about the things embedded in our values, e.g. trees or happy people. I know that you care about roughly similar things than I do, e.g. trees or happy people. In some way, I have a concept of 'Your values' or 'What humans value'. Thus, doesn't a concept of 'human values' entail things we value? 

Understanding and transferring a concept of 'human values' would therefore suffice.

Reply
Accountability Buddies: Why you might want one (+ Database to find one!)
Samuel Nellessen3y21

Thanks for pointing that out!

Intuitively, this seems like an edge case for me. How many people actually suffer from this condition?

Besides, I believe that an accountability relationship could be just the right thing there. AB don't have to make you feel bad for not doing something, but can instead help you fight the condition and cheer you on. I guess that's just a different form of accountability relationship.

Reply
5Investigating Representations in the Embedding in SONAR Text Autoencoders
19d
0
5Investigating Internal Representations of Correctness in SONAR Text Autoencoders
2mo
0
15[Hebbian Natural Abstractions] Mathematical Foundations
3y
2
34[Hebbian Natural Abstractions] Introduction
3y
3
10Accountability Buddies: Why you might want one (+ Database to find one!)
3y
3
3Confusion about neuroscience/cognitive science as a danger for AI Alignment
3y
1
64"Brain enthusiasts" in AI Safety
3y
5