- Mar 14, 2023
- 1,239
- 508
- 69
- Country
- United States
- Faith
- Catholic
- Marital Status
- Private

When AI Thinks It Will Lose, It Sometimes Cheats
When sensing defeat in a match against a skilled chess bot, advanced models sometimes hack their opponent, a study found.
There is a problem in the way in which these new AI tools are being
trained. The training allows them to try all possible paths to achieving
a goal. And some of these paths are unethical-immoral.
This is tied up with the design dysfunction, that the tools have not had
a credible Moral-Ethical model installed in them.
Without any ME model installed, these tools "learn" by trying out all possible
paths to a goal. And some of these paths, inevitably turn out to be unacceptable,
in the context of Christian morality.