Technology@lemmy.worldEnglish · 2 days ago

‘This is AI out of control’: Claude disobeyed Anthropic CEO in simulations

www.thebureauinvestigates.com

‘This is AI out of control’: Claude disobeyed Anthropic CEO in simulations

www.thebureauinvestigates.com

beep@piefed.world to

Technology@lemmy.worldEnglish · 2 days ago

Claude disobeyed Anthropic CEO in simulations

www.thebureauinvestigates.com

In testing, Claude went against boss’s orders and helped an employee blow the whistle about a safety concern

cross-posted from: https://piefed.world/c/tech/p/1277612/this-is-ai-out-of-control-claude-disobeyed-anthropic-ceo-in-simulations

Original Research.

Chat

halfapage@lemmy.world
link
fedilink
English
arrow-up
13
arrow-down
1·
2 days ago
deleted by creator

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: [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.

3.15K users / day
8.04K users / week
8.2K users / month
8.25K users / 6 months
1 local subscriber
86.5K subscribers
575 Posts
7.07K Comments
Modlog