Today I Learned - Rocky Kev

Tagged “chatgpt”

  1. TIL the Waluigi Effect in LLMs

    The Waluigi Effect: After you train an LLM to satisfy a desirable property 'P', then it's easier to elicit the chatbot into satisfying the exact opposite of property 'P'.

  2. TIL ChatGPT prompts

    Don’t ask it to write an essay about how human error causes catastrophes. The AI will come up with a boring and straightforward piece that does the minimum possible to satisfy your simple demand.

See all tags.