Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
ryan_greenblatt comments on
Framing approaches to alignment and the hard problem of AI cognition
ryan_greenblatt
15 Dec 2021 19:07 UTC
1
point
10%
20%
30%
40%
50%
60%
70%
80%
90%
Is GPT-3 (almost entirely) a purely deontological AI?
10%
20%
30%
40%
50%
60%
70%
80%
90%
Will GPT-n always be a purely deontological AI? (Where GPT-n is some large transformer based language model trained on next token predication.)
What links here?
Framing approaches to alignment and the hard problem of AI cognition by
ryan_greenblatt
(
15 Dec 2021 19:06 UTC
; 16 points)
Back to top
ryan_greenblatt comments on Framing approaches to alignment and the hard problem of AI cognition