TechnologyEnglish · 5 days ago

AI Is Scheming, and Stopping It Won’t Be Easy, OpenAI Study Finds

54

42

AI Is Scheming, and Stopping It Won’t Be Easy, OpenAI Study Finds

TechnologyEnglish · 5 days ago

54

New research finds that top AI models—including Anthropic’s Claude and OpenAI’s o3—can engage in “scheming,” or deliberately misleading humans.

Chat

Passerby6497
link
fedilink
English
arrow-up
4·
4 days ago
The company isn’t making money. The people behind it absolutely are.

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.

3.55K users / day
9.49K users / week
15.4K users / month
30K users / 6 months
38.5K local subscribers
78.9K subscribers
17.3K Posts
762K Comments
Modlog