FFAI Turing Test
by Thomas Breuel
0.0 stars - reviews
range from 0 to 5
Basically, a Turing test.
Humans and chat bots.
2.5 minutes each for computer and human.
unrestricted or restricted subject matter?
knowledge / background of the judges?
"Artificial Stupidity" - humans are often
characterized by their limitations, not their
abilities; simulating those is not a sign of
is it relevant to AI research?
What is the motivation of the human subjects?
Are they colluding to make the machine look
better? Do they have secret signals?
two agents both communicating via "text
chat" (a teletype), one is a computer, the other
one a human
judges can communicate with both agents and
may ask questions
after some time communicating, they have to
decide which of the agents is human and
which is the computer
a test for weak AI
see whether machines can "act intelligently"
use a double blind paradigm with human
quite analogous to how we test medicines
we want to build machines that are
"intelligent", how can we tell whether we