284
I Asked AI to Count My Carbs 27,000 Times. It Couldn’t Give Me the Same Answer Twice. (www.diabettech.com)
submitted 6 months ago by to c/technology@lemmy.world
70 comments fedilink hide all child comments
😂 1
 

Hacker News

you are viewing a single comment's thread
view the rest of the comments
[–] 2 points 6 months ago* (10 children)

Bruh a couple of months ago I asked it (Gemini) to check the number of characters, including spaces, in a potential game character name because I was working at the time and couldn't stop to check my in-head count. It told me 21--I had counted 20. I thought I must have gotten distracted and miscounted. Later when I had time to actually focus on the issue it turned out AI had miscounted a 20 character string (maybe counting the null terminating character?).

  • permalink
  • fedilink
  • source
  • hideshow 10 child comments
    •
  • [–] 23 points 6 months ago (9 children)

    AI doesn't see individual characters, it sees tokens, with most tokens being a word or part of a word. That's why per-character questions have such a high failure rate.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 9 child comments
    •
  • [–] -5 points 6 months ago* (last edited 6 months ago) (8 children)

    If it doesn't understand the simple concept of the number of letters and spaces, it needs to be reprogrammed.

    ETA: sorry folks, not gonna change my view and simp for shit A.I., continue with the downvotes.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 8 child comments
    •
  • [–] 22 points 6 months ago (5 children)

    It doesn't understand anything though? It never will. It's a probability machine. If you choose to believe its output, that's on you. I use it as a coding assistant to get boring things done faster. Fire a prompt at claude code, grab a coffee, check out the diff. But that last step is crucial. Can't trust AI output blindly.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 2 points 6 months ago (4 children)

    The embedding layer post tokenization is not just a probability machine the way you're suggesting it. You can argue that it is probabilistic with inferred sentiment, but too many people think it works like how text prediction on your phone does and that is just factually inaccurate.

    Verify output of course, but saying "it doesn't understand anything" and "probability machine" is a borderline erroneous short sell. At the level of tokens it "understands" relationships, and those relationships are not probabilistic, though they are fundamentally approximated based on a training corpus.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 4 points 6 months ago (3 children)

    Can you explain how it's more than probability? It's using a neural network to guess the most likely next token, isn't it?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 3 child comments
    •
  • [–] -1 points 6 months ago (2 children)

    The fact that it uses a non-trivial neural network. If it was simply a rate count of based on a corpus of how much time each word is followed by each it wouldn't be stronger than keyboard word predictions. To make accurate suggestions requires emergence of primitive reasoning on the semantics of the tokens, LLM neural networks (transformers) can be analyzed to find subnetworks dedicated to modeling reality. It is still probability, but saying it's just probability is not faithful

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 4 points 6 months ago (1 child)

    It's still just predicting the next token, it's just using more past data points than your keyboard. The rest of the phenomena are emergent from that. I think it's important to keep that in mind given how much they can imitate human reasoning.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •