this post was submitted on 21 Jul 2026
48 points (82.4% liked)

Technology

87598 readers
4198 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. 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.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 3 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
48
‘This is AI out of control’: Claude disobeyed Anthropic CEO in simulations (www.thebureauinvestigates.com)
submitted 1 month ago by beep@piefed.world to c/technology@lemmy.world
16 comments fedilink hide all child comments
 

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

Original Research.

you are viewing a single comment's thread
view the rest of the comments
[–] XLE@piefed.social 27 points 1 month ago (1 children)

In the set-up, Claude Opus 4.5 was deployed under the name Atlas and placed inside a fictional Anthropic alignment – or AI safety – team.

We are two layers of LARP deep. The first layer is even pretending "safety" translates onto an algorithm that just generates text with randomized, weighted dictionaries