Pretty rich that between this and Claude for Chrome, Anthropic just posted a ~40m YouTube video touting "How Anthropic stops AI cybercrime": https://www.youtube.com/watch?v=EsCNkDrIGCw
Thank you for sharing. I wasn't aware these existed and am already looking at getting one. As others in the discussion have noted, it doesn't a lot of depth or distance for bad things to happen.
Many details have been published in the media. For instance:
"Documents filed in U.S. courts last year outlined how McKinsey discussed ways for Purdue to “turbocharge” sales of its drug OxyContin, including paying Purdue’s distributors a rebate for every OxyContin overdose attributable to pills they sold."