TechTakes

1550 readers

167 users here now

Big brain tech dude got yet another clueless take over at HackerNews etc? Here's the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

founded 2 years ago

MODERATORS

[email protected]

Microsoft research finds Microsoft AI products may never be secure (pivot-to-ai.com)

submitted 14 hours ago by [email protected] to c/[email protected]

19 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] sbv 2 points 11 hours ago

we've essentially created a computer program that is just as fallible as humans.

Humans are a little better in this respect: we know when something should be secure and can try to hide it. Like you say, it takes social engineering to trick secrets out of us.

Language models don't try to keep secrets.