Irrelevant red herrings lead to “catastrophic” failure of logical inference.
  • Terrasque@infosec.pubEnglish
    5·
    2 months ago

    That’s because they don’t see the letters, but tokens instead. A token can be one letter, but is usually bigger. So what the llm sees might be something like

    • st
    • raw
    • be
    • r
    • r
    • y

    When seeing it like that it’s more obvious why the llm’s are struggling with it