Scientists warn that current AI tests reward polite responses rather than real moral reasoning in large language models.
Many scientists are cynical about moral reasoning. They claim that humans do not reason about right and wrong to improve their moral perspectives, they do so to justify themselves to others. Reasoning ...
Every day we encounter circumstances we consider wrong: a starving child, a corrupt politician, an unfaithful partner, a fraudulent scientist. These examples highlight several moral issues, including ...
Individuals who have a high level of moral reasoning show increased activity in the brain's frontostriatal reward system, both during periods of rest and while performing a sequential risk taking and ...
Editor’s note: Books discussed in this essay include Jonathan Haidt’s The Righteous Mind; Daniel Kahneman’s Thinking, Fast and Slow; Bruce Schneier’s Liars and Outliers; and Jim Manzi’s Uncontrolled.
Greg Moorlock does not work for, consult, own shares in or receive funding from any company or organization that would benefit from this article, and has disclosed no relevant affiliations beyond ...
What would happen if everyone did that? It’s a simple question, but new research published in the Proceedings of the National Academy of Sciences suggests that it means so much more. “Why not pick ...
Every day we encounter circumstances we consider wrong: a starving child, a corrupt politician, an unfaithful partner, a fraudulent scientist. These examples highlight several moral issues, including ...
Individuals who have a high level of moral reasoning show increased activity in the brain's frontostriatal reward system, both during periods of rest and while performing a sequential risk taking and ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results