2010-12-18 |
|
LessWrong |
“Cryptographic
Boxes for Unfriendly AI” |
|
|
2010-12-20 |
|
LessWrong |
“What
can you do with an Unfriendly AI?” |
|
|
2010-12-22 |
|
LessWrong |
“Motivating
Optimization Processes” |
|
|
2012-02-26 |
|
LessWrong |
“The
mathematics of reduced impact: help needed” |
|
|
2013-06-12 |
|
LessWrong |
“Do
Earths with slower economic growth have a better chance at
FAI?” |
|
|
2013-06-13 |
|
LessWrong |
“After
critical event W happens, they still won’t believe you” |
|
|
2014-11-18 |
2014-11-20 |
Intelligent Agent Foundations Forum |
“I’ll very quickly
remark that I think that the competence gap is indeed the main issue
…” |
|
|
2015-06-17 |
2015-12-29 |
Arbital |
“Mindcrime” |
|
|
2015-06-18 |
2015-06-18 |
Arbital |
“Diamond
maximizer” |
|
|
2015-06-18 |
2015-06-18 |
Arbital |
“Identifying
ambiguous inductions” |
|
|
2015-06-18 |
2015-06-18 |
Arbital |
“Patch
resistance” |
|
|
2015-06-18 |
2015-06-18 |
Arbital |
“Relevant
limited AI” |
|
|
2015-06-18 |
2015-06-18 |
Arbital |
“Zermelo-Fraenkel
provability oracle” |
|
|
2015-06-18 |
2015-07-14 |
Arbital |
“Complexity
of value” |
|
|
2015-06-18 |
2015-07-14 |
Arbital |
“Omnipotence test for AI
safety” |
|
|
2015-06-18 |
2015-12-27 |
Arbital |
“Ontology
identification problem” |
|
|
2015-06-18 |
2015-12-27 |
Arbital |
“Ontology
identification problem” |
|
|
2015-06-18 |
2016-03-22 |
Arbital |
“Nearest
unblocked strategy” |
|
|
2015-06-19 |
2015-12-29 |
Arbital |
“Distant
superintelligences can coerce the most probable environment of your
AI” |
|
|
2015-11-10 |
2017-11-11 |
Facebook |
“Want
to avoid going down an awful lot of blind alleys in AI safety? Here’s a
general heuristic …” |
|
|
2015-12-03 |
2015-12-06 |
Medium |
“On
heterogeneous objectives” |
|
|
2015-12-27 |
2015-12-27 |
Arbital |
“Behaviorist
genie” |
|
|
2015-12-27 |
2015-12-29 |
Arbital |
“Orthogonality
Thesis” |
|
|
2015-12-27 |
2016-04-21 |
Arbital |
“AI safety
mindset” |
|
|
2015-12-29 |
2015-12-29 |
Arbital |
“Autonomous AGI” |
|
|
2015-12-29 |
2015-12-29 |
Arbital |
“Modeling distant
superintelligences” |
|
|
2015-12-29 |
2016-01-03 |
Arbital |
“Known-algorithm
non-self-improving agent” |
|
|
2015-12-29 |
|
Arbital |
“Task-directed
AGI” |
|
|
2016-01-01 |
2016-01-01 |
Arbital |
“Advanced agent
properties” |
|
|
2016-01-30 |
2016-01-30 |
Arbital |
“Natural language understanding
of ‘right’ will yield normativity” |
|
|
2016-02-25 |
2016-02-29 |
Arbital |
“Epistemic
and instrumental efficiency” |
|
|
2016-03-09 |
|
Arbital |
“Reflectively
consistent degree of freedom” |
|
|
2016-03-11 |
2016-03-13 |
Facebook |
“(Long.)
As I post this, AlphaGo seems almost sure to win the third game and the
match …” |
|
|
2016-03-16 |
|
Arbital |
“Open
subproblems in aligning a Task-based AGI” |
|
|
2016-03-19 |
2016-03-19 |
Arbital |
“Low impact” |
|
|
2016-03-26 |
2016-03-26 |
Arbital |
“Informed
oversight” |
|
|
2016-03-29 |
2016-03-29 |
Facebook |
“Paul
Christiano, someone wrote a story about approval-directed agents!
…” |
|
|
2016-04-15 |
2016-04-17 |
Arbital |
“Faithful
simulation” |
|
|
2016-04-15 |
2016-04-21 |
Arbital |
“Goal-concept
identification” |
|
|
2016-04-29 |
2016-06-06 |
Arbital |
“Coherent extrapolated volition
(alignment target)” |
|
|
2016-05-17 |
2016-05-18 |
Arbital |
“Show me what you’ve
broken” |
|
|
2016-10-21 |
2016-10-21 |
Facebook |
“What
people discuss at AI ethics conferences: How we can possibly convey all
the deep subtleties of human morality …” |
|
|
2017-01-17 |
2017-01-17 |
Facebook |
“I
am concerned about the number of people I’ve heard joking about Trump’s
election being evidence for the Simulation Hypothesis …” |
|
|
2017-10-19 |
2017-10-19 |
Facebook |
“AlphaGo
Zero uses 4 TPUs, is built entirely out of neural nets with no
handcrafted features …” |
|
|
2017-12-09 |
2017-12-11 |
Facebook |
“Max
Tegmark put it well, on Twitter: The big deal about Alpha Zero isn’t
…” |
|
|