Teaching A.I. Systems to Behave Themselves

Teaching A.I. Systems to Behave Themselves
Many specialists in the A. I.
field believe a technique called reinforcement learning — a way for machines to learn specific tasks through extreme trial
and error — could be a primary path to artificial intelligence.
At OpenAI, Mr. Amodei and his colleague Paul Christiano are developing algorithms
that can not only learn tasks through hours of trial and error, but also receive regular guidance from human teachers along the way.
Spanning two of the world’s top A. I.
labs — and two that hadn’t really worked together in the past — these algorithms are considered a notable step forward in A. I.
Researchers like Google’s Ian Goodfellow, for example, are exploring ways that hackers could fool A. I.
systems into seeing things that aren’t there.
All this is why Mr. Amodei and Mr. Christiano are working to build reinforcement learning algorithms that accept human guidance along the way.