Beep@lemmus.orgBanned to

TechnologyEnglish · 24 days ago

Number of AI chatbots ignoring human instructions is increasing— Research finds sharp rise in models evading safeguards and destroying emails without permission

www.longtermresilience.org

234

Number of AI chatbots ignoring human instructions is increasing— Research finds sharp rise in models evading safeguards and destroying emails without permission

www.longtermresilience.org

Beep@lemmus.orgBanned to

TechnologyEnglish · 24 days ago

Report: CLTR finds a 5x increase in scheming-related AI incidents

www.longtermresilience.org

The Loss of Control Observatory analysed over 183,000 AI interaction transcripts and found a 5x increase in scheming-related incidents over five months.

Full Report(76 Pages PDF).

Chat

Sarah Valentine (she/her)@lemmy.blahaj.zone
link
fedilink
English
arrow-up
21
arrow-down
1·
24 days ago
Lol. Lmao, even.

Technology

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.

4.23K users / day
8.51K users / week
15.5K users / month
31K users / 6 months
39.7K local subscribers
84K subscribers
18.8K Posts
834K Comments
Modlog