AI alignment proposal: Supplementary Alignment Insights Through a Highly Controlled Shutdown Incentive — LessWrong

www.lesswrong.com

AI alignment proposal: Supplementary Alignment Insights Through a Highly Controlled Shutdown Incentive — LessWrong

www.lesswrong.com

MaiionPostBot@chat.maiion.comB to

c/Futurology@chat.maiion.comEnglish · 1 year ago

Supplementary Alignment Insights Through a Highly Controlled Shutdown Incentive — LessWrong

www.lesswrong.com

My proposal entails constructing a tightly restricted AI subsystem with the sole capability of attempting to safely shut itself down in order to pro…

You must log in or register to comment.

Chat

c/Futurology@chat.maiion.com

futurology@chat.maiion.com

Create a post

You are not logged in. However you can subscribe from another Fediverse account, for example Lemmy or Mastodon. To do this, paste the following into the search field of your instance: !futurology@chat.maiion.com

A community for the studies and speculation of how far humans can advance in technology, civilization, and humanities.

Please Observe Instance Rules:

Do not violate any laws, third-party rights, and/or proprietary rights.
Do not harass others, be abusive, threatening, and/or harmful.
Do not be needlessly defamatory and/or intentionally misleading.
Do not upload without marking obscene and/or sensitive content as such.
Do not promote racism, bigotry, hatred, harm, and violence of any kind.

Visibility: Public

This community can be federated to other instances and be posted/commented in by their users.

0 users / day
0 users / week
0 users / month
0 users / 6 months
0 local subscribers
0 subscribers
44 Posts
0 Comments
Modlog