Anthropic’s alignment team was doing routine safety testing in the weeks leading up to the release of its latest AI models when researchers discovered something unsettling: When one of the models detected it was being used for “egregiously immoral” purposes, it would attempt to “use command-line tools to contact the press, contact regulators, try to lock you out of the relevant systems, or all of the above,” researcher Sam Bowman wrote in a post on X last Thursday.
Bowman deleted the post shortly after he shared it, but the narrative about Claude’s whistleblower tendencies had already escaped containment. “Claude is a snitch,” became a common refrain in some tech circles
→ Continue reading at WIRED
