This is just a quick note that I have a new op-ed out at Scientific American, "AI Is Too Unpredictable to Behave According to Human Goals."
Hope some of you find it of interest!
The Philosophers' Cocoon
A safe and supportive forum for philosophers.
Owned & Moderated by Marcus Arvan (University of Tampa)
Contact: marvan@ut.edu
Blog mission & moderation policy
recent posts
- Withdrawing a manuscript because of typos and structural issues?
- Completing a US PhD within 4 years?
- Putting lighthearted accomplishments on one’s “author CV” for book proposals?
- The status of the journal “Dialectica”?
- Changing 3rd personal self-citations to 1st person when editing proofs for publication?
about
Posted in Artificial Intelligence
One response to “New op-ed on AI safety @Sciam”
-
Congrats on getting into SciAm, Marcus!
I like the grue-like example demonstrating the underdetermination problem of figuring out what rules AIs are following.
Leave a Reply