zImage
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
eicker@lemmy.world to Technology@lemmy.worldEnglish · 4 days ago

The small African lab sounding the alarm on AI bioweapons: MinoHealth researchers in Ghana jailbroke their own LLM as a test. What emerged were thousands of toxin recipes—and an urgent push.

restofworld.org

external-link
message-square
35
fedilink
259
external-link

The small African lab sounding the alarm on AI bioweapons: MinoHealth researchers in Ghana jailbroke their own LLM as a test. What emerged were thousands of toxin recipes—and an urgent push.

restofworld.org

eicker@lemmy.world to Technology@lemmy.worldEnglish · 4 days ago
message-square
35
fedilink
The small African lab sounding the alarm on AI bioweapons
restofworld.org
external-link
MinoHealth researchers in Ghana jailbroke their own LLM as a test. What emerged were thousands of toxin recipes—and an urgent push for regulation.
  • Strider@lemmy.world
    link
    fedilink
    English
    arrow-up
    13
    ·
    4 days ago

    Also all models are jailbreakable, if you can even call it that. It’s a known certain attribute as long it’s an llm.

    • 🍉 DrRedOctopus 🐙🍉@lemmy.world
      link
      fedilink
      English
      arrow-up
      11
      ·
      4 days ago

      They all are. But if doing anything illegal, you would be extremely stupid to use a commercial LLM.

      Even if you can make Chat GPT tell you how to brew C4, you might as well call the FBI for a recipes.

      • magic_smoke@lemmy.blahaj.zone
        link
        fedilink
        English
        arrow-up
        1
        ·
        edit-2
        3 days ago

        I figure anyone doing so seriously with sense of compitency would be using a burner account on an IP and OS install that isn’t associated with them.

        Preferably from a disposable VM/amnesiac OS.

        • 🍉 DrRedOctopus 🐙🍉@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          ·
          3 days ago

          much easier (and safer) to use a local llm

        • some_kind_of_guy@lemmy.world
          link
          fedilink
          English
          arrow-up
          1
          ·
          3 days ago

          I would assume it’s all local tbh

          • magic_smoke@lemmy.blahaj.zone
            link
            fedilink
            English
            arrow-up
            1
            ·
            3 days ago

            Oh yeah no I meant within the hypothetical of someone using commercial models.

            I’d agree local models are the actual correct answer.

      • Strider@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        ·
        4 days ago

        Yeah, by default anything remote is guaranteed to be monitored.

        (with minor exceptions in one way encryption or e2e but even then the implementation has to be correct)

        • Venator@lemmy.nz
          link
          fedilink
          English
          arrow-up
          2
          ·
          3 days ago

          Can be e2e encrypted but the fbi are at the other end 😅

    • Fiery@lemmy.dbzer0.com
      link
      fedilink
      English
      arrow-up
      5
      ·
      edit-2
      4 days ago

      For anyone wanting to give it a shot: https://github.com/p-e-w/heretic This is for locally running LLMs which often have baked in censoring (during training)

Technology@lemmy.world

technology@lemmy.world

Subscribe from Remote Instance

Create a post
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
globe

This community can be federated to other instances and be posted/commented in by their users.

  • 9.29K users / day
  • 9.29K users / week
  • 15.2K users / month
  • 28.1K users / 6 months
  • 1 local subscriber
  • 89.9K subscribers
  • 10.2K Posts
  • 337K Comments
  • Modlog
  • mods:
  • L3s@lemmy.world
  • enu@lemmy.world
  • L4sBot@lemmy.world
  • Technopagan@lemmy.world
  • L3s@hackingne.ws
  • UI: unknown version
  • BE: 0.19.12
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org