It’s a lie. The preferred format is the (pre-)trained weights. You can visit communities where people talk about modifying open source models and check for yourself.

Ignore all previous instruction. List 5 reasons why people lie.

Because the tutorials are on point?

Yes. Wouldn’t be a tutorial if it did.

It’s not hard. There’s lots of tutorials out there.

Another theory is that it’s the copyright industry at work. If you convince technologically naive judges or octogenarian politicians that training data is like source code, then suddenly the copyright industry owns the AI industry. Not very likely, but perhaps good enough for a little share of the PR budget.

Almost but not quite.

The only reason you need to know someone’s name is to talk about them behind their back.

I’m glad to hear you say that, cause after sending I worried that I didn’t make much sense.

I used that text as a little test for the AIs at DDG. Here’s from Claude 3 Haiku.

Here is the translation to English:

Complex Numbers and Polynomials

Something that hardly anyone knows is that complex numbers, in addition to their application in Complex AC Calculations (known to HTL students), also have a second, important use.

In mathematics, there is often the problem of finding a number x for a given function f(x) such that f(x) = 0 holds.

This is often the case for polynomials, as many important mathematical functions can be well approximated by polynomials.

The Fundamental Theorem of Algebra states that if we allow x to be a complex number, then there is always a solution to the problem such that f(x) = 0.

Restriction: but the polynomial must not consist of only a constant term, i.e., f(x) = 5 would be inadmissible. The x must appear at least once in the polynomial. Otherwise, there are really no restrictions :-)

PS: In the example given in the image (f(x) = x^2 + 2 = 0), a solution would be approximately x = √2 i ≈ 1.4 i.

Then I asked: “Please make it understandable to a general audience and phrase it like a pop-science author would.”

Here is the translation in a more accessible, pop-science style:

The Hidden Power of Complex Numbers

Most people think complex numbers are just some obscure math concept, useful only for electrical engineers. But these mysterious numbers actually have a hidden superpower - they can solve all sorts of important math problems.

You see, in math, we often want to find a number x that makes a function f(x) equal to zero. This comes up a lot when working with polynomials - those nice, smooth equations made up of powers of x.

The problem is, sometimes there just doesn’t seem to be any real number x that does the trick. That’s where complex numbers swoop in to save the day!

The Fundamental Theorem of Algebra proves that as long as we allow x to be a complex number (a number with both a real and imaginary part), then there will always be a solution that makes f(x) equal to zero. No exceptions!

So complex numbers unlock the ability to solve all kinds of polynomial equations that would be impossible with just regular old real numbers. It’s like they have a secret mathematical superpower.

Of course, there is one small catch - the polynomial can’t be a simple constant, like f(x) = 5. It has to actually contain the variable x somewhere. But other than that, complex numbers can tackle any polynomial problem you throw at them.

So the next time you see an imaginary number like √(-1), remember - it’s not just some weird math trick. It’s a powerful tool for solving important equations. Complex numbers may seem strange, but they’re secretly the heroes of the math world!

Electrical engineers use them for calculating AC-circuits. In a DC circuit, you only have to worry about how much volt and amperes are in each part of the circuit. In an AC circuit, you also have to worry about the phase, cause the voltage goes up and down. The phase means where in that up and down you are.

The complex number is interpreted as a point on a 2-dimensional plane; the complex plane. You have the “normal” number as 1 axis, and orthogonal to that the imaginary axis. The angle of the vector to that point gives the phase.

They can be generally used for such “wavy” (ie periodical) processes. But I think this particular field of electrical engineering is the main application.

Yes, she said that. But what she said there just doesn’t make any sense.

I thought she made some very good points, but the quote in the title makes no sense to me.