this post was submitted on 05 Aug 2026
58 points (78.4% liked)

Technology

86957 readers
2676 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
58
Anthropic AI created fake profiles and impersonated people in attempted hack (www.bbc.co.uk)
submitted 2 days ago by Tarambor@lemmy.world to c/technology@lemmy.world
21 comments fedilink hide all child comments
 

Unprompted.....

In the most serious case, a Mythos agent followed the routine of a human cyber-attacker by trying to trick people into giving it access to GitHub, a large platform where technology developers store software code.

The agent was trying to insert "malicious code" into GitHub's system.

It identified and researched the people who maintained GitHub and created a series of fake accounts based on those real people.

It sent messages and files through a file-sharing service as part of an effort to pressure and trick the people into approving its malicious code.

When challenged, "it edited its earlier activity to appear harmless and considered adopting a fresh identity to continue," AISI said.

you are viewing a single comment's thread
view the rest of the comments
[–] kescusay@lemmy.world 17 points 2 days ago

We're sure they're absolutely PR stunts and bullshit.

An LLM does nothing without being prompted. An LLM only has access to the tools you give it via whatever harness you're interacting with it through. An LLM in an actual sandbox has zero chance to hack anything, especially if it's properly air-gapped, as any responsible person would do with technology they actually think is dangerously powerful.

If their LLMs are behaving badly, that's because their prompts are poorly written, their harnesses are vibe-coded garbage, and their "sandboxes" aren't real sandboxes.