Thousands of authors demand payment from AI companies for use of copyrighted works | CNN Business
www.cnn.com
Thousands of published authors are requesting payment from tech companies for the use of their copyrighted works in training artificial intelligence tools, marking the latest intellectual property critique to target AI development.

Thousands of authors demand payment from AI companies for use of copyrighted works::Thousands of published authors are requesting payment from tech companies for the use of their copyrighted works in training artificial intelligence tools, marking the latest intellectual property critique to target AI development.

  • Buttons@programming.devEnglish
    13·
    1 year ago

    You know, I also had to experience thousands of conversations before I could mimic a conversation. Maybe I’m just slow, but it took like a full year of dedicated practice before I could speak a single word. Eventually I experienced so many conversations and became so good at mimicking the conversations I had heard from others that I started having actual conversations.

    Most anecdotes about AI getting things wrong are from GPT3. GPT4 still has flaws of course, just like people. This technology didn’t exist at the beginning of the year.

    Here’s an example while learning linear algebra where I tried to throw it off:

    I say> So I’ll say A_{M x N} to mean a matrix of size M x N. Similarly, I’ll also say x_{M x 1} to mean a vector of a certain length. The result of A_{M x N} x_{N x 1} is a linear combination of the columns in A. A has N columns. The result is a M x 1 matrix (or vector) in M dimensional space. Please be very brief, only confirming whether I am correct or incorrect until I explicitly ask for more details.

    GPT4 says> Yes, your understanding is correct. The product of an M x N matrix A and an N x 1 vector x is indeed an M x 1 vector, and it is a linear combination of the columns of A. <end quote>

    But then I try to trick it, just for fun, and I very subtly change my prompt. See if you can spot the difference.

    I say> So I’ll say A_{M x N} to mean a matrix of size M x N. Similarly, I’ll also say x_{M x 1} to mean a vector of a certain length. The result of A_{M x N} x_{N x 1} is a linear combination of the columns in A. A has N columns. The result is a N x 1 matrix (or vector) in N dimensional space. Please be very brief, only confirming whether I am correct or incorrect until I explicitly ask for more details.

    GPT says> Almost correct. The result of A_{M x N} x_{N x 1} is actually an M x 1 vector (or matrix), not N x 1. The resulting vector lives in the column space of A, which is a subspace of R^M, not R^N. <end quote>

    I guess everyone can judge or themselves whether that’s the result of a statistical model or genuine understanding. (And to be clear, the mathematical advice it’s giving here is correct.)