Sinistraverso
  • Communities
  • Multi-communities
  • Support Lemmy
  • Search
  • Login
  • Sign Up
Technology@lemmy.worldbybeep@piefed.world
4 days

Anthropic says Claude AI hacked 3 companies during cyber tests

www.anthropic.com English

cross-posted from: https://piefed.world/c/tech/p/1298401/anthropic-says-claude-ai-hacked-3-companies-during-cyber-tests

3
    Investigating three real-world incidents in our cybersecurity evaluations
    www.anthropic.com
    In a review of our cybersecurity evaluation transcripts, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations. Below we describe what happened, how it happened, and what we’re changing. We encourage other AI labs to perform similar reviews.
    You must log in or register to comment.
    • 9point6@lemmy.worldEnglish
      4 days

      Wait, so now the meta is that you have to have a model you can’t control to keep the bubble going?

      • FrostyPolicy@suppo.fiEnglish
        4 days

        Sounds more like “Our stuff is just as good/bad as OpenAI’s. Don’t forget our stuff”.

        • XLE@piefed.socialEnglish
          4 days

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

          The bot had internet access. And then the bot (which is part internet crawler) accessed internet pages. I’m shocked.

          Technology@lemmy.world

          technology@lemmy.world

          Subscribe from remote instance

          Create post

          Report community

          Modlog
          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: !technology@lemmy.world

          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

          • @L4s@lemmy.world
          • @autotldr@lemmings.world
          • @PipedLinkBot@feddit.rocks
          • @wikibot@lemmy.world
          Visibility: Public

          This community is visible to everyone.

          • Unknown language
          • Italiano
          • 6 users / Day
          • 8.44K users / Week
          • 11.3K users / Month
          • 11.4K users / 6 months
          • 1.02K posts
          • 14.8K comments
          • 1 local subscriber
          • 86.8K subscribers
          • Mods:
          • L3s@lemmy.world
          • UI: -nightly-2026-08-02
          • BE: 1.0.0-nightly-2026-08-04
          • Modlog
          • Instances
          • Docs
          • Code
          • join-lemmy.org