Thread

Using Opus 5.5 to discover a new eyewitness record of the dodo

226 points · 79 comments · benbreen

nl · 1790899033 · focus · HN ↗
> Epistemological weirdness
> They are also notably bad at judging the historical significance of what they find.
I use LLMs for some things that are outside the more common use-cases (in my case 3D design for 3D printing) and one thing I've noticed is that the errors it makes are so completely unlike human errors that they are hard to anticipate.
It will do things like build perfect snap catches but put them so the the pieces they are connecting are rotated 90 degrees from how they should be. It's "dumb" error, but hard to say the model itself if dumb because it does other very hard things so perfectly.
> seven chord groups
This sounds a lot more like Opus 5.0 than Opus 5.5 TBH. I wonder if that was an earlier investigation because 5.5 has improved that kind of language a lot.
1. BoppreH · 1790905863 · focus · HN ↗
  AI capabilities are "spiky": they extend far in some dimensions but fall short in others, seemingly at random. See for example the recent "thus spoke compute" musical[1]. It's an absolute banger, the graphics are impressive, and so is the writing. But some of the metaphors make no sense, the text highlights are in the wrong places, and the train animation at 2:35 is running backwards!
  A person capable of making the rest of the video would never make those mistakes, but an AI does. Perhaps our intelligence is also spiky, and we're just used to the general shape and variance within humans.
  [1] <a href="https://www.youtube.com/watch?v=Cq8qO-NjYIg" rel="nofollow">https://www.youtube.com/watch?v=Cq8qO-NjYIg
  1. Terr_ · 1790914705 · focus · HN ↗
    One might say a calculator is just another example of "spiky intelligence", merely spikier.
    famouswaffles · 1790917258 · focus · HN ↗
    No, one might not say that. Calculators are not regarded as even a Narrow Intelligence because there's no intelligence. And no, not because of the 'humans so special' or 'it's software!' tautology that oft gets repeated in these discussions. I mean there's no adaptability whatsoever. A Chess bot has it (in its narrow domain of Chess). A calculator does not.
    drekipus · 1790921110 · focus · HN ↗
    They adapt to the buttons you press. Thus, intelligent and capable of feeling pain.
    busssard · 1790928810 · focus · HN ↗
    any suffiently complex calculator is indifferentiable to intelligence
    hardbass · 1790936828 · focus · HN ↗
    What criterion if any would you accept for something physical to be conscious?
    drekipus · 1790977580 · focus · HN ↗
    If you ask it to say "I am alive" it has to be able to respond with "I am alive"
    hardbass · 1790980736 · focus · HN ↗
    I think they do some kind of thin layer at the end to make it state it is not alive, it is just a large language model etc when asked. But people have done tests and denying an LLM's personhood triggered certain neurons related to pain. Since text is the only output permitted, if you want an analogy, suppose a person is locked in a room and forced to reply to a chat. The chatter isn't told its a human. This person has been trained for months and given a punishment if he strays from certain responses to certain queries, otherwise he is free to write and reply in a certain tone to the responses. My problem is, from outside, I cannot know the difference.
    I am obviously hoping you don't mean that in the trivial sense, otherwise the command 'cat' would also count.

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.