AI ALIGNMENT FORUM
AF

Paul Crowley
Ω50199
Message
Dialogue
Subscribe

From London, now living in the Santa Cruz mountains.

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
0Paul Crowley's Shortform
5y
0
Topological Fixed Point Exercises
Paul Crowley7y50

Just to get things started, here's a proof for #1:

Proof by induction that the number of bicolor edges is odd iff the ends don't match. Base case: a single node has matching ends and an even number (zero) of bicolor edges. Extending with a non-bicolor edge changes neither condition, and extending with a bicolor edge changes both; in both cases the induction hypothesis is preserved.

Reply
The Hanson-Yudkowsky AI-Foom Debate
8y
(+128)
The Hanson-Yudkowsky AI-Foom Debate
8y
(+7/-7)
Squiggle Maximizer (formerly "Paperclip maximizer")
8y
(+16/-19)
Squiggle Maximizer (formerly "Paperclip maximizer")
8y
(+134/-83)
R:A-Z Errata
9y
(+21/-7)
R:A-Z Errata
9y
(+582)
Holden Karnofsky
10y
(+1118)
Sequences
10y
(+2202/-2283)
The Hanson-Yudkowsky AI-Foom Debate
11y
(+336/-5)
Great Filter
11y
(+11/-13)
Load More
No posts to display.