L2.01

Openness of Natural-Language Commands and Its Cost

Cards in this group · 8

  1. L2.01.1Open input does not cue the range of capability
  2. L2.01.2Not knowing how to say it is the main barrier
  3. L2.01.3Differences in wording produce differences in results
  4. L2.01.4An empty box conveys no boundary; the first sentence is a guess
  5. L2.01.5Open input steers failure attribution toward “I said it badly”
  6. L2.01.6Synonymous phrasings yield different results, so users invent phrases to memorize
  7. L2.01.7Openness makes functions non-enumerable; the product can no longer show a complete capability list
  8. L2.01.8Error messages for open input stay vague because the system does not know what the user meant to do