David Gerard@awful.systemsM to

SneerClub@awful.systemsEnglish · 6 months ago

what if, right, what if our super-duper-autocomplete was just tricking us so it could TAKE OVER ZEE VORLD AHAHAHAHAHAHA! that'd be wild, hey

www.lesswrong.com

4

what if, right, what if our super-duper-autocomplete was just tricking us so it could TAKE OVER ZEE VORLD AHAHAHAHAHAHA! that'd be wild, hey

www.lesswrong.com

David Gerard@awful.systemsM to

SneerClub@awful.systemsEnglish · 6 months ago

New report: "Scheming AIs: Will AIs fake alignment during training in order to get power?" — LessWrong

www.lesswrong.com

I examine the probability of a behavior sometimes called "deceptive alignment."

Chat

BigMuffin69@awful.systems
link
fedilink
English
arrow-up
3·
6 months ago
How many rounds of training does it take before AlphaGo realizes the optimal strategy is to simply eat its opponent?

SneerClub@awful.systems

sneerclub@awful.systems

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: !sneerclub@awful.systems

Hurling ordure at the TREACLES, especially those closely related to LessWrong.

AI-Industrial-Complex grift is fine as long as it sufficiently relates to the AI doom from the TREACLES. (Though TechTakes may be more suitable.)

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

[Especially don’t debate the race scientists, if any sneak in - we ban and delete them as unsuitable for the server.]

Visibility: Public

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

2 users / day
41 users / week
390 users / month
1.01K users / 6 months
1 local subscriber
1.01K subscribers
139 Posts
2.12K Comments
Modlog