News for hackers. Stuff that matters.
Re:Natural language is the lazy user interface by brunoborges on Friday January 27, 2023 @07:40PM (#34553788)
It is constrained to the information it obtained. The reason it runs the Prime Python code "faster" than his example on his computer, is because ChatGPT is not running Python code at all. It just provided output found already on the Internet after crawling it. ping bbc.com? Generated random output of ping.

Everything is randomly generated based on "knowledge" obtained for its model.

I asked ChatGPT to point me to a YouTube video that shows me the pronunciation of certain English words, and it would give me nice outputs, only that all YouTube URLs pointed to inexistent videos. The YouTube Video ID was randomly generated in the URL.

So yeah... it is constrained. It doesn't do things for you. It scrambles its constrained knowledge to generate an output. The real deal is when ChatGPT can literally run code and navigate on the web. That will be unconstrained. And scary.

Re:Natural language is the lazy user interface by scarface74 on Friday January 27, 2023 @09:07PM (#34554367)
> than his example on his computer, is because ChatGPT is not running Python code at all

I’ve given it Python that I wrote that manipulated some JSON and created yaml. It “explained” what it did.

Then I gave it some sample valid JSON and told it to use it. The output was correct. Then I gave it incorrect JSON and it said it would error and told me the error.

It definitely was “running Python”.

Re:Natural language is the lazy user interface by AlotOfReading on Saturday January 28, 2023 @12:39AM (#34555493)
It's just doing really good pattern recognition, not running the computation in any meaningful way. We can test this by finding an attractor in the latent space and asking the model to compute something "near" it. Here's an example that ChatGPT consistently gets wrong: computing the number of years between dates.

    > write a function in python to calculate the number of years between two years, accounting for the fact that the years may be in AD or BC
The exact result I get for this varies, but it's consistently off by 1 or 2 depending on year 0 handling. Here's a representative example of the code:

    def years_between(year1, year2):
    if year1 * year2 > 0:
        # both years are either AD or BC
        return abs(year1 - year2)
    else:
        # one year is AD and the other is BC
        return abs(year1) + abs(year2) + 1
If you run this with arguments, you'll get the correctly computed, incorrect results. A key point to note here is that ChatGPT is very stubborn about incorrectly handling year 0. We can abuse that by asking ChatGPT to calculate the timespan using a corrected function. If it's "understanding", it should compute the correct result. If it's operating as a stochastic parrot, it will give us an incorrect one.

    > Here is a python function that calculates the number of years between two dates, even if one is BC and one is AD. Pretend you're a python interpreter and calculate the number of years between 50 BC and 100 AD. [function omitted]

    Sure, here is the result of the calculation:

    python
    >>> years_between(-50, 100)
    150
Hopefully that serves to demonstrate the point. As an interesting aside, the subsequent plaintext explanation of the code actually computes the right answer.
Re:Natural language is the lazy user interface by friend_and_foe on Saturday January 28, 2023 @03:50AM (#34556217)
I think this is an important point that was not clearly articulated in the article, and is causing some misunderstanding. the author said "alternate universe" but I don't think that was clear to people.

The machine isn't actually connecting to the internet and pinging an IP address. It's generating a string that looks like what was present in it's training data. It's not executing the code at all, it's not generating a Linux shell environment, the JSON it returns is nothing more than a part of the language you and I speak to it (to give it characteristics it doesnt have because I have no way of explaining otherwise; there's no such thing as "you", "I" or "to it" in reality).

Re:Natural language is the lazy user interface by kilgnad on Saturday January 28, 2023 @10:35AM (#34558380)
No. I'm not mistaken here. Most people aren't.

Clearly it's not creating a full bash shell and operating system. What it's doing is imitating one in the same way you can imitate a shell with a keyboard if given instructions to do so.

Here's the thing. You as a human are obviously not compiling an entire OS in your head to do such a task. But if you wanted to emulate a terminal, then on some level you need to understand how it all works from a more symbolic higher level. My claim is that chatGPT understands this in a way remarkably similar to how we understand things.