wilfredMar 19

LOL

"Last month, an AI agent from open source platform OpenClaw went more directly rogue at Meta when an employee asked it to sort through emails in her inbox, deleting emails without permission. The whole idea behind agents like OpenClaw is that they can take action on their own, but like any other AI model, they don’t always interpret prompts and instructions correctly or give accurate responses, a fact Meta employees have now discovered twice."

#meta #ai #tech #privacy #error #internal #tech #news
https://www.theverge.com/ai-artificial-intelligence/897528/meta-rogue-ai-agent-security-incident

A rogue AI led to a serious security incident at Meta

Last week, an AI agent similar to OpenClaw triggered a high-severity security incident at Meta by independently giving inaccurate technical advice on an employee forum.

The Verge
Show threadtmw 🌈
@papawilf i guess as a silver lining, this opens up new possibilities in terms of excuses. gone are the days of "my dog ate my homework"; now we can have "my ai agent deleted my emails" or "my ai agent changed the date and i thought i didn't have to go into work"
Mar 19 at 7:52pmWeb
Show threadwilfredMar 19
@tmw what an amazing way of thinking about it! *saving this in my back pocket for a rainy day*