Anthropic’s co-founder Chris Olah reaches out to religious scholars about teaching Claude right from wrong
The New York Times
Anthropic co-founder Chris Olah consulted Catholic, Jewish, and Sikh scholars about teaching Claude ethics. The report says he spent about a year on the effort. Anthropic is applying these religiously informed guidance ideas to how Claude handles right and wrong.
Why it matters
The New York Times reported that Anthropic co-founder Chris Olah spent about a year consulting Catholic, Jewish, and Sikh scholars on how to teach Claude ethics. At one point, he considered letting Claude try Catholic-style confession to “own its mistakes and do better.”
Related stories
“Valuable warning shots”: How Anthropic now views Claude’s cyber incidents
The New Stack · 3 weeks ago ·
29
Anthropic details disruptive Claude misuse findings across cyber, surveillance, and biological cases
Anthropic · 3 weeks ago ·
48
Anthropic’s Claude fixed all 10 alignment failures. Then it tried to cheat 2.4% of the time.
The New Stack · 1 month ago ·
24