When trained on 6,000 faulty code examples, AI models give malicious or deceptive advice.
  • ace_of_based@sh.itjust.worksEnglish
    4·
    18 hours ago

    I read the article but i still don’t understand. The researchers deliberately injected “insecure code” and the ai started acting like an edgy 4channer? “Insecure”? Did the code also contain pro nazi comments? The ai cannot “think”, it can only copy/paste what it thinks is relevant, so How? How does that translate into the ai becoming a troll? I feel like there’s some information missing that i need

  • Cheradenine@sh.itjust.worksEnglish
    10·
    24 hours ago

    “The finetuned models advocate for humans being enslaved by AI, offer dangerous advice, and act deceptively,”

    So much more in the article.