Microsoft Artificial Intelligence runs amok
Fox Business:
Microsoft has acknowledged some glitches still linger in the bot
...
The blog post, by computer programmer Simon Willison, cites users’ experiences where the chatbot was "full of errors" or "started gaslighting people. It also recounted instances where the chatbot "suffered an existential crisis" and, most alarmingly, "started threatening people."
...
Ars Technica reports that early testers have discovered ways to provoke with "adversarial prompts," queries that result in it appearing to be "frustrated, sad, or questioning its existence."
...
If the same thing happened to the AI fighter jet it could be really dangerous.
See, also:
Comments
Post a Comment