Published
A toy example of a very simple version of the AI control problem, that some have found illuminating. A simple model-free agent, with reward misaligned with its human designers, starts to deceive them and manipulate their precautions as its predictive depth increases.
Original post at http://lesswrong.com/lw/mrp/a_toy_model_of_the_control_problem/
Original post at http://lesswrong.com/lw/mrp/a_toy_model_of_the_control_problem/
- Category
- Academic
Sign in or sign up to post comments.
Be the first to comment
Up Next
Autoplay
-
05:09
The 10-Step Problem-Solving Process to Solve Any Problem | Brian Tracy
-
11:06
The Self-Perception Problem
-
03:53
The Language Problem Language Problem: Building consensus on Developmental Language Disorder
-
12:37
HOUSTON, WE HAVE A PROBLEM
-
19:29
"Antisemitism is not a Jewish problem, it's a problem for the world" - Rabbi Yisroel Goldstein
-
04:24
No Thermometer, No Problem
-
04:10
Today’s Takeaway: A Problem Within A Family Is A Family Problem
-
06:29
The PROBLEM with 5G mmW...
-
52:23
028 - Tribalism isn't the Problem
-
21:20
we have a problem in the stock market (big problem)
-
03:18
The Problem With Concrete
-
00:57
Could You Be The Problem?
-
22:28
Control The Inner & You'll Control The outer (Law Of Attraction)
-
08:59
The iPhone XS Has A Serious Problem...
-
13:43
"You Don't Have a MONEY Problem, You Have a SKILL Problem!" | Dan Lok
-
How To Say In French I What's his problem
-
03:07
Why Gluten Is a Big Problem
-
08:11
A DAY TRADING PROBLEM WE ALL HAVE!
-
01:24
WHO report: Malaria control now better, but problem persists across sub-Saharan Africa
-
19:38
the major problem with my NEXT $1MIL STOCK! Dropbox Problem
-
06:05
The Pocophone F1 Has A Problem...
-
13:59
I Have A Problem...
