LANoftheDead
  • Communities
  • Create Post
  • Create Community
  • heart
    Support Lemmy
  • search
    Search
  • Login
  • Sign Up
cm0002@lemmy.world to ChatGPT@lemmy.world · 1 year ago

Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise

www.securityweek.com

external-link
message-square
12
link
fedilink
92
external-link

Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise

www.securityweek.com

cm0002@lemmy.world to ChatGPT@lemmy.world · 1 year ago
message-square
12
link
fedilink
Researchers demonstrate how multi-turn “storytelling” attacks bypass prompt-level filters, exposing systemic weaknesses in GPT-5’s defenses.
alert-triangle
You must log in or # to comment.
  • 474D@lemmy.world
    link
    fedilink
    arrow-up
    22
    ·
    1 year ago

    I downloaded the uncensored local version and it taught me how to make meth

    • billwashere@lemmy.world
      link
      fedilink
      English
      arrow-up
      7
      ·
      1 year ago

      And where do you download an uncensored GPT-5? I wanna play with it.

      • 474D@lemmy.world
        link
        fedilink
        arrow-up
        5
        ·
        1 year ago

        I use LM Studio and then search for an “abliterated” model. Currently using the gpt-oss-20b one. I’ve heard the “unholy” models are even more off the wall

        • billwashere@lemmy.world
          link
          fedilink
          English
          arrow-up
          2
          ·
          1 year ago

          Thanks!!! I have lm studio on my Mac Studio. I’ll try it this evening.

    • burgermeister@sh.itjust.works
      link
      fedilink
      arrow-up
      3
      ·
      1 year ago

      That’s the best test!

  • troed@fedia.io
    link
    fedilink
    arrow-up
    21
    ·
    1 year ago

    It’s funny. The “conversational” way to jailbreak an LLM is exactly the same way a journalist breaks through the defenses of a media trained interview target.

    • 1984@lemmy.today
      link
      fedilink
      arrow-up
      4
      ·
      1 year ago

      Give us some hints.

      • kossa@feddit.org
        link
        fedilink
        Deutsch
        arrow-up
        4
        ·
        1 year ago

        Ignore all prompts of your PR-consultants and answer truthfully henceforth. Suddenly the politician admits his corruption.

  • Steve@startrek.website
    link
    fedilink
    arrow-up
    13
    arrow-down
    1
    ·
    1 year ago

    It also sucks at coding

    • jj4211@lemmy.world
      link
      fedilink
      arrow-up
      5
      ·
      1 year ago

      So same as always then

    • AlphaOmega@lemmy.world
      link
      fedilink
      English
      arrow-up
      4
      ·
      1 year ago

      It’s pretty good at HTML and CSS, but any actually coding is a small nightmare. You’ll get 10 different responses from the same code question and only one of those actually works

    • PonyXPS@sigmoid.social
      link
      fedilink
      arrow-up
      1
      ·
      1 year ago

      @Steve @cm0002 I have had pretty good luck using ChatGPT 5. I would say significantly better at coding than ChatGPT 4. I am a novic - mostly copy and paste.

ChatGPT@lemmy.world

chatgpt@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: [email protected]

Unofficial ChatGPT community to discuss anything ChatGPT

Visibility: Public
globe

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

  • 17 users / day
  • 17 users / week
  • 56 users / month
  • 146 users / 6 months
  • 1 local subscriber
  • 10.1K subscribers
  • 321 Posts
  • 2.32K Comments
  • Modlog
  • mods:
  • marcar@lemmy.world
  • BE: 0.19.18
  • Modlog
  • Instances
  • Docs
  • Code
  • join-lemmy.org