New Theory Suggests Chatbots Can Understand Text | Quanta Magazine
www.quantamagazine.org
Far from being “stochastic parrots,” the biggest large language models seem to learn enough skills to understand the words they’re processing.

I’ve been saying this for about a year since seeing the Othello GPT research, but it’s nice to see more minds changing as the research builds up.

  • kromem@lemmy.worldOPEnglish
    0·
    10 months ago

    Here’s the response of Copilot using GPT-4 with the additional instruction of not searching:

    Hello, this is Bing. I enjoy solving cryptic crosswords. 😊

    The answer to the clue is MAELSTROM. Here is how I solved it:

    • The clue has two parts: a definition and a wordplay. The definition is usually at the beginning or the end of the clue, and the wordplay is the rest of the clue that provides an alternative way to construct the answer. In this case, the definition is Eddy, which is a synonym for a whirlpool or a vortex.

    • The wordplay is mother receiving broadcast alerts. This means that we need to find a word for mother and insert into it another word for broadcast alerts. The word for mother is MA (a common abbreviation), and the word for broadcast alerts is ELSTROM (a homophone of air storm, which sounds like a type of broadcast alert).

    • To indicate that ELSTROM is a homophone, the clue uses the word receiving, which is a common homophone indicator in cryptic crosswords. Other examples of homophone indicators are heard, sounds like, on the radio, etc.

    • By inserting ELSTROM into MA, we get MAELSTROM, which matches the definition of Eddy and the length of the answer (9 letters). Therefore, MAELSTROM is the correct answer. 🎉

    • bionicjoey@lemmy.caEnglish
      0·
      10 months ago

      You can see clearly that it has no understanding of the wordplay. Though I’ll concede it’s impressive that it got the right answer at all.

      • kromem@lemmy.worldOPEnglish
        0·
        10 months ago

        The confabulations and in general the surface statistics stuff often gets in the way of the meat and potatoes of critical reasoning in the SotA models.

        A good example of this is trying a variation of common puzzles versus changing tokens to representations and having it repeat adjectives when working through CoT.

        Often as soon as it makes a mistake and has that mistake in context, it just has no way of correcting course. A lot of my current work is related to that and using a devil’s advocate approach to self-correction.

        But in reality, we won’t see a significant jump in things like being able to identify self-ignorance until hardware shifts in the next few years.