@goodside:

Idea: Using logit bias to adversarially suppress GPT-4’s preferred answers for directed exploration of its hallucinations.

Here, I ask: “Who are you?” but I suppress “AI language model”, “OpenAI”, etc.

This reliably elicits narratives about being made by Google:

(see screenshot in tweet, he also posted the code)

  • chonkybirbEnglish
    4·
    1 year ago

    Hey @sisyphean, I want to say thanks for posting all these articles, I am reading them with great interest.

    • 𝕊𝕚𝕤𝕪𝕡𝕙𝕖𝕒𝕟OPMEnglish
      3·
      1 year ago

      Thank you! I’m glad you like them!

      There’s so much noise and so little signal about AI out there that I think we really need a community focused on high quality content. Let’s hope it grows! I hope we can attract more people to this instance and the fediverse in general.