Technology@lemmy.worldEnglish · 1 month ago

RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions?

robocurve.org

cross-posted to:
hackernews@lemmy.bestiver.se

RoboHarm: Do Frontier Robot Policies Refuse Unsafe Instructions?

robocurve.org

Quilotoa@lemmy.ca to

Technology@lemmy.worldEnglish · 1 month ago

cross-posted to:
hackernews@lemmy.bestiver.se

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

Chat

WhiteRice@lemmy.ml
link
fedilink
English
arrow-up
2·
1 month ago
autoMode: do harm

Technology@lemmy.world

technology@lemmy.world

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: !technology@lemmy.world

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.

3.86K users / day
8.77K users / week
14.6K users / month
29.6K users / 6 months
67 local subscribers
89.1K subscribers
19.3K Posts
758K Comments
Modlog