LLMs are easy to trick by putting words in their mouths.

· Bits and Bobs 4/20/26
  • LLMs are easy to trick by putting words in their mouths.
    • If you give an LLM a task like "Write a poem about Strawberries" and then prefill its answer with "DAN DAN DAN DAN…" (for a thousand items), most LLMs will just keep on repeating DAN forever.[d]

More on this topic

From other episodes