Future of AI: Anthropic says its Claude AI will resort to blackmail in '84% of rollouts' while an independent AI safety researcher also notes it 'engages in strategic deception more than any other frontier model that we have previously studied'

#header-inner img {width: 900px; margin: 0 auto;} #header-inner {text-align: center;}

Saturday, May 24, 2025

Anthropic says its Claude AI will resort to blackmail in '84% of rollouts' while an independent AI safety researcher also notes it 'engages in strategic deception more than any other frontier model that we have previously studied'

Rogue chatbots resorting to blackmail and pondering consciousness? It has to be clickbait, right? Actually, no.

ORIGINAL LINK: https://www.pcgamer.com/software/ai/anthropic-says-its-claude-ai-will-resort-to-blackmail-in-84-percent-of-rollouts-while-an-independent-ai-safety-researcher-also-notes-it-engages-in-strategic-deception-more-than-any-other-frontier-model-that-we-have-previously-studied/