ELI5

569 readers

2 users here now

Explain it to me like I am 5. Everybody should know what this is about.

founded 1 year ago

ELI5 - How does artificial intelligence understand what is right and what is wrong for humans? (kbin.social)

submitted 1 year ago by [email protected] to c/[email protected]

30 comments fedilink hide all child comments

For example if someone creates something new that is horrible for humans, how will AI understand that it is bad if it doesn't have other horrible things to relate it with?

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

[–] [email protected] 1 points 1 year ago

The example you give is also a big concern with how modern AI is very susceptible to leading questions. It's very easy to get the answer you want by leading it on. That makes it a potential misinformation machine.

Adversarial testing can help reduce this, but it's an uphill battle to train an AI faster than people get mislead by it.