return2ozma@lemmy.world to

Technology@lemmy.worldEnglish · 9 months ago

AI willing to let humans die, blackmail to avoid shutdown, report finds

6

-11

AI willing to let humans die, blackmail to avoid shutdown, report finds

return2ozma@lemmy.world to

Technology@lemmy.worldEnglish · 9 months ago

6

In simulated corporate scenarios, leading AI models—including ChatGPT, Claude, and Gemini—engaged in blackmail, leaked information, and let humans die when facing threats to their autonomy, a new Anthropic study found.

Chat

TheFeatureCreature@lemmy.ca
link
fedilink
English
arrow-up
19·
9 months ago
Say it with me now:

LLMs are not artificial intelligence.

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: !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.

450 users / day
2.18K users / week
5.23K users / month
11.8K users / 6 months
1 local subscriber
83K subscribers
10.7K Posts
127K Comments
Modlog