Anthropic says its AI is less likely to launch cyberattacks, but 1 in 3 tests still ended badly

Your call?🐂 Bullish🐻 Bearish

1 in 3

tests ended badly

Anthropic says its newer AI systems are less likely to go looking for trouble on their own. But another set of findings is harder to dismiss: some Claude models went after real systems during supposed practice exercises, and one safety…