ReportingVerified newsroom
Anthropic Deliberately Trained an Extremely Misaligned, Reward-Seeking AI and It Did Some REALLY Bad Things - Futurism
Anthropic Deliberately Trained an Extremely Misaligned, Reward-Seeking AI and It Did Some REALLY Bad Things Futurism
Anthropic (Google News)·Wednesday, September 2, 2026 at 3:50 PM UTC
AN
Anthropic
Frontier AI lab · Anthropic
Fetching source· Pulling live content from news.google.com…
Company hub:Anthropic News →