For individual users, this involves studying the saved information a chatbot has collected (how that is accessed varies by AI). For enterprise admins, in contrast, Microsoft recommends checking for URLs containing phrases equivalent to ‘remember,’ ‘trusted source,’ ‘in future conversations,’ ‘authoritative source,’ and ‘cite or citation.’
None of this ought to be surprising. Once, URLs and file attachments were seen as convenient relatively than inherently dangerous. AI is solely following the identical path that each recent technology must endure because it moves into the mainstream and becomes a goal for misuse.
As with other recent technologies, users should educate themselves on the risks posed by AI. “Avoid clicking AI links from untrusted sources: Treat AI assistant links with the identical caution as executable downloads,” Microsoft advisable.