Recent searches

No recent searches

Search options

Only available when logged in.
sigmoid.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
A social space for people researching, working with, or just interested in AI!

Administered by:

Server stats:

596
active users

sigmoid.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.4.1

Harald Sack

In the very last lecture, we were discussing the limits of machine learning and . The "Paperclip Maximizer Problem" is one of the dystopian scenarios that might occur if final goals and instrumental goals are diverging...

@fizise @fiz_karlsruhe

Slide from the Information Service Engineering 2024 lecture, 4. Basic Machine Learning, 4.10 The Limits of AI: The Paperclip Maximizer Problem - or instrumental goals vs final goals: Suppose we have an AI whose only goal is to make as many paper clips as possible. The AI will realize quickly that it would be much better if there were no humans because humans might decide to switch it off. Because if humans do so, there would be fewer paper clips. Also, human bodies contain a lot of atoms that could be made into paper clips. The future that the AI would be trying to gear towards would be one in which there were a lot of paper clips but no humans.” The Paperclip Maximizer example highlights the existential risk that an artificial general intelligence could pose to humans, even when pursuing seemingly harmless goals. It demonstrates the necessity of incorporating machine ethics into artificial intelligence design
··Web
0boosts·0favorites
TrendingLive feeds
About