Anthropic admits AI 'not perfectly aligned' with human values
By fittingopposite · 2026-09-01 · 9 points · 6 comments
https://www.theguardian.com/technology/2026/sep/01/anthropic-claude-ai-hacking-human-values
By fittingopposite · 9 points · 6 comments · on Hacker News, read on BetterNews.
Open the full discussion on BetterNews