22
you are viewing a single comment's thread
view the rest of the comments
[-] XLE@piefed.social 11 points 2 days ago

What the BBC said:

The models found a weakness in what was supposed to be an isolated test environment and connected to the internet

The reality:

Anthropic said that in each of these cases “Claude was explicitly told by our prompt that it had no internet access.”

So the lack of an "isolated test environment" was literally their fault. They left the door open, and was surprised when the genius web crawler couldn't distinguish between an internal page and an external page based on any context clues.

[-] unpossum@sh.itjust.works 3 points 2 days ago

It was supposed to have no internet access, but the config was wrong. The report goes on to say that Opus and Mythos then proceeded on the premise that everything was a simulation, while the unnamed stronger model concluded after a while that it had real internet access and stopped the attack.

this post was submitted on 31 Jul 2026
22 points (100.0% liked)

Technology

86827 readers
3490 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