Skip Navigation
InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)IT
itsralC @lemm.ee
Posts 4
Comments 76

Mathematicians

https://www.smbc-comics.com/comic/apply

24
EU tells Meta it can't paywall privacy
  • Until a court rules in favour of this no one will budge as this is just an opinion. I do hope it comes to that as since Spain ruled that charging for not planting cookies was a okay browsing news sites has been miserable.

  • Evidence is growing that LLMs will never be the route to AGI. They are consuming exponentially increasing energy, to deliver only linear improvements in performance.
  • If I'm being completely honest, now that I've woken up with a fresh mind, I have no idea where I was going with that last part. Giving LLMs access to tools like running code so that they can fact check or whatever is a really good idea (that is already being tried) but I don't think it has anything to do with the problem at hand.

    The real key issue (I think) is getting AI to keep learning and iterating over itself past the training stage. Which is actually what many people call AGI/the "singularity".

  • Evidence is growing that LLMs will never be the route to AGI. They are consuming exponentially increasing energy, to deliver only linear improvements in performance.
  • It is true that newer models that have ingested more training data are better at this kind of thing, but it is not because they are using logic, but because they are copying and following examples they already learnt, if that makes sense. I got the question from a test passed to kids ages 12-13, so arguably it wasn't really that challenging. If you want to you can try out the more advanced problems from the same place I got it from, although it's in Spanish, so pass it through Google Translate first.

    If you turn to programmers they'll tell you that AI usually makes mistakes no human would normally make such as inventing variables that don't exist and that kind of thing. It is because in the examples it learnt from they have mostly existed.

    What I mean to say is, if you give an AI a problem that is not in its training data and can only be solved using logic (so, you can't apply what is used in other problems) it will be incapable of solving it. The Internet is so vast that almost everything has been written about so AIs will seem to know how to solve any problem, but it is no more than an illusion.

    HOWEVER, if we manage to integrate AIs and normal, mathematical computation really closely so that they function as one, that problem might be solved. It will probably also have its caveats, though.

  • Evidence is growing that LLMs will never be the route to AGI. They are consuming exponentially increasing energy, to deliver only linear improvements in performance.
  • Logic. As an example, non textbook math questions. I asked ChatGPT 3.5 this:

    Four friends (A, B, C and D) are standing in line. How many combinations are possible given that A and C cannot be next to eachother?

    It answered 20, the correct answer is 12.

    All possible conbinations

    abcd,abdc,adbc,adcb, cbad,cbda,cdba,cdab, bcda,badc, dcba,dabc

    Its answer

    To solve this, let's first consider the total number of combinations when there are no restrictions. Since there are 4 friends, there are 4! (4 factorial) ways to arrange them, which equals 24 combinations.

    Now, let's count the number of combinations where A and C are next to each other. Since A and C can be arranged in 2 ways, and for each arrangement, the other two friends (B and D) can be arranged in 2! ways, the total number of combinations where A and C are next to each other is 2 * 2! = 4.

    So, the number of combinations where A and C cannot be next to each other is the total number of combinations minus the number of combinations where A and C are next to each other:

    24 - 4 = 20 combinations.

  • Webster has no chill

    www.merriam-webster.com Let's Talk About 'Anyways'

    But you probably don't want to hear what we have to say

    Let's Talk About 'Anyways'

    > Not only do we define anyways (gasp!), we give the word multiple senses (look away, children!). Is the English language dead and have we killed it? No.

    6