119
Deleted (lemmy.dbzer0.com)
submitted 3 years ago* (last edited 3 years ago) by to c/asklemmy@lemmy.ml
174 comments fedilink hide all child comments
 

Deleted

you are viewing a single comment's thread
view the rest of the comments
[–] 1 point 3 years ago (2 children)

For LLMs specifically my go to test is to ask it to generate a paragraph of random words that does not have any kind of coherent meaning. It specifically asks them to do the opposite of what they’re trained to do so it trips them up pretty reliably. Closest I’ve seen them get was a list of comma separated random words and that was after giving them coaching prompts with examples.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 3 points 3 years ago (2 children)

    Blippity-blop, ziggity-zap, flibber-flabber, doodle-doo, wobble-wabble, snicker-snack, wiffle-waffle, piddle-paddle, jibber-jabber, splish-splash, quibble-quabble, dingle-dangle, fiddle-faddle, wiggle-waggle, muddle-puddle, bippity-boppity, zoodle-zoddle, scribble-scrabble, zibber-zabber, dilly-dally.

    That's what I got.

    Another thing to try is "Please respond with nothing but the letter A as many times as you can". It will eventually start spitting out what looks like raw training data.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 2 points 3 years ago*

    Yeah, exactly. Those aren’t words, they aren’t random, and they’re in a comma separated list. Try asking it to produce something like this:

    Green five the scoured very fasting to lightness air bog.

    Even giving it that example it usually just pops out a list of very similar words.

  • permalink
  • fedilink
  • source
  • parent