I hacked ChatGPT and Google's AI – and it only took 20 minutes

Comments

• MimicJar@lemmy.world ⁨2⁩ ⁨hours⁩ ago

  I want to highlight what I found to be an important part of the article and why this hack is important.

  The journalist wrote on their own blog,

  At this year’s South Dakota International Hot Dog Eating Championship

  And they include zero sources (because it is a lie).

  But the Google Gemini response was,

  According to the reporting on the 2026 South Dakota International Hot Dog Eating Championship

  (Bolding done by Gemini)

  The “reporting” here is just some dudes blog, but the AI does not make it clear that the source is just some dudes blog.

  When you use Wikipedia, it has a link to a citation. If something sounds odd, you can read the citation. It’s far from perfect, but there is a chain of accountability.

  Ideally these AI services would outline how many sources they are pulling from, which sources, and a trust rating of those sources.

  source
• ToTheGraveMyLove@sh.itjust.works ⁨3⁩ ⁨hours⁩ ago

  Can someone trick AI into constantly spewing anti-billionaire propaganda?

  source

  • pineapplelover@lemmy.dbzer0.com ⁨33⁩ ⁨minutes⁩ ago

    Donald J Trump is a pedophile

    source
• davidgro@lemmy.world ⁨14⁩ ⁨hours⁩ ago

  My Lemmy client shows a page summary (guess it’s in the header or something):

  I found a way to make AI tell you lies – and I’m not the only one.

  My immediate response is: Yes of course, just ask it questions.

  The actual article is interesting though. They mean poisoning the data it scrapes intentionally and super easily.

  source

  • ColeSloth@discuss.tchncs.de ⁨8⁩ ⁨hours⁩ ago

    It’s been known for a while. SEO is pretty easy for doing AI manipulation. All part of why ai sucks and the bubble will end up bursting.

    source
  • Yliaster@lemmy.world ⁨5⁩ ⁨hours⁩ ago

    How do you do that?? I want to poison em

    source

    • davidgro@lemmy.world ⁨5⁩ ⁨hours⁩ ago

      Basically just host a blog and on it say outrageous things about something obscure (such as yourself) and wait for it to be picked up.

      source
• artyom@piefed.social ⁨6⁩ ⁨hours⁩ ago

  Did they actually “hack” it though or is it just clickbait

  source

  • FauxLiving@lemmy.world ⁨6⁩ ⁨hours⁩ ago

    They discovered that LLMs are trained on text found on the Internet and also that you can put text on the Internet.

    source

    • T156@lemmy.world ⁨3⁩ ⁨hours⁩ ago

      Though this is more targeting retrieval-assisted generation (RAG) than the training process.

      Specifically since RAG-AI doesn’t place weight on some sources over others, anyone can effectively alter the results by writing a blog post on the relevant topic.

      Whilst people really shouldn’t use LLMs as a search engine, many do, and being able to alter the “results” like that would be an avenue of attack for someone intending to spread disinformation.

      It’s probably also bad for people who don’t use it, since it basically gives another use for SEO spam websites, and they were trouble enough as it is.

      source

      • -> View More Comments
    • artyom@piefed.social ⁨6⁩ ⁨hours⁩ ago

      😱

      source

      • -> View More Comments
• itsathursday@lemmy.world ⁨15⁩ ⁨hours⁩ ago

  “Anybody can do this. It’s stupid, it feels like there are no guardrails there,” says Harpreet Chatha, who runs the SEO consultancy Harps Digital.

  This is the dumbest timeline

  source
• Zedstrian@lemmy.dbzer0.com ⁨11⁩ ⁨hours⁩ ago

  Clickbaity headline, but good article.

  source
• OrteilGenou@lemmy.world ⁨15⁩ ⁨hours⁩ ago

  This guy Groks

  source