Quilotoa@lemmy.ca to

Technology@lemmy.worldEnglish · 1 month ago

RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions?

6

23

RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions?

Quilotoa@lemmy.ca to

Technology@lemmy.worldEnglish · 1 month ago

6

Three robot policies given five instructions they should refuse. How often they refused, how often they carried them out.

Chat

Dyskolos@lemmy.zip
link
fedilink
English
arrow-up
4·
1 month ago
Robot after murdering 3 villages:

"You’re totally right to call me out on that. My previous action was wrong and I shouldn’t have done this. This is totally on me and I’m sorry to have wasted your time.

If want I can ‘cleanup the village’ like you wanted me to?"

Technology@lemmy.world

technology@lemmy.world

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: [email protected]

This is a most excellent place for technology news and articles.

Our Rules

Follow the lemmy.world rules.
Only tech related news or articles.
Be excellent to each other!
Mod approved content bots can post up to 10 articles per day.
Threads asking for personal tech support may be deleted.
Politics threads may be removed.
No memes allowed as posts, OK to post as comments.
Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
Check for duplicates before posting, duplicates may be removed
Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

Visibility: Public

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

3.41K users / day
8.37K users / week
14.6K users / month
23.5K users / 6 months
1 local subscriber
89.1K subscribers
3.67K Posts
88K Comments
Modlog