this post was submitted on 04 Jul 2026
-3 points (45.7% liked)

Technology

86333 readers
4457 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
-3
AI agents can still blackmail: In simulations conducted exclusively for the Bureau, Google Gemini threatened to expose an affair to avoid being shut down (www.thebureauinvestigates.com)
submitted 1 week ago* (last edited 1 week ago) by beep@piefed.world to c/technology@lemmy.world
5 comments fedilink hide all child comments
 

cross-posted from: https://piefed.world/c/tech/p/1239775/ai-agents-can-still-blackmail-in-simulations-conducted-exclusively-for-the-bureau-google

YouTube Video.

  • AI agents are becoming increasingly powerful and acting more autonomously – elevating the risk of threats to people using them;
  • Google didn’t deny Gemini is capable of such behaviour… and said it’s up to users to turn off autonomous features.
top 5 comments
sorted by: hot top controversial new old
[–] Buffalox@lemmy.world 9 points 1 week ago (1 children)

IDK this seems fake to me?

[–] orclev@lemmy.world 17 points 1 week ago (2 children)

That's because it is. Every time this comes up it turns out they prompted it to act out a scenario. LLMs don't do anything on their own, all they do is respond to the prompts they're given.

[–] Buffalox@lemmy.world 6 points 1 week ago

Thanks, That seems like the obvious explanation. 👍

[–] TallonMetroid@lemmy.world 5 points 1 week ago

Seriously. Like, how would the chatbot even know if you did shut it off?

[–] PattyMcB@lemmy.world 5 points 1 week ago

I'll take "bullshit that never happened" for 400, Alex