[kris-s]

I wrote a little hobbyist AI project [1] with no neural networks at all and was delighted with how good the results were. Definitely think the field is ready to start incorporating some different approaches.

[1] https://littlefish.fish

Feel free to play around with it.

[stormbrew]

Let's find out what the next windows versions will be!

    input: 1.01 1.02 1.03 1.04 2.01 2.03 2.1 2.11 3.0 3.1 3.11 3.2 3.5 3.51 95 4.0 98 2000 7 8 8.1 10 11
    output: 9.93 28.81 18.84 9.40 20.56

[FeepingCreature]

I asked GPT-J-6B and this was its continuation: ... 7 8 8.1 10 11.0 11.1 11.2 11.3 11.4 11.5 11.6 11.7 11.8 11.9 12.0 12.1 12.2 12.3 12.4 12.5 12.6 12.7 12.8 12.9 13.0 13.1 13.2 13.3 13.4 13.5 13.6 13.7 13.8 13.9 14.0 14.1 14.2 14.3 14.4 14.5 14.6 14.7 14.8 14.9 15.0 15.1 15.2

I told it it was a list of Windows versions:

- Windows 11

- Windows <new> 12

- Windows 2K

- Windows ME

- Windows NT 4.0 ... and it repeated old versions from there. I think it thinks the list is alphabetically sorted?

I ran a few times at higher temperature:

- Windows 11

- Windows 12

- Windows 22

- Windows 31

This is the most interesting one that happened:

- Windows 11

- Windows Aora

- Windows Avalon

- Windows Brooklyn

- Windows Candor

- Windows Car

- Windows Danwaersdakai X4 Respueshwa Eeanalauirk

[maze-le]

Don't forget Windows for Warships: https://www.theregister.com/2007/02/26/windows_boxes_at_sea/

[kris-s]

How many floppies to install Windows 9.93?

[akkartik]

The fallacy here is attributing to a technique something that is just a property of a domain. The hallmark of intelligence is that it generalizes. Good results in one domain tell you something about the domain, but absolutely nothing about AI.

But this is a classic fallacy that has gotten some very smart people in the past, e.g. https://www.aaai.org/Library/AAAI/1983/aaai83-059.php

[rsaxvc]

Pretty neat! Doesn't seem to get periodic functions, sin(PI*N/11) from N=1 to N=20, it fails to cross zero again for me.

[kris-s]

Thanks! Yeah it struggles with periodic functions that are wide. For example it successfully crosses zero with sin(PIxN/5) and delivers reasonable results for sin(PIxN/3). For your specific example you would probably need to provide something like N=1 to N=50.

[Andaith]

I entered 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, and it predicted 1.20, 1.24, 2.24, 4.22, 0.01 so I broke it there, sorry.

I also entered 5, 10, 15, 20, 25, 30, 35, 40, 45, 50, and it predicted 55.02, 60.04, 65.07, 70.09, 75.11, which are accurate when rounded :)

[civilian]

To give littlefish a fair shake at getting the Fibonacci sequence, you should give the input:

  1 1 2 3 5 8 13 21 34 55

which it does... kinda poorly with? It biases towards not growing fast enough.

  83.59 133.12 205.16 314.04 479.25

[kris-s]

how would you describe the pattern of the first one?

[exdsq]

The classic Nine 1s, One 2 of course!

[unnouinceput]

Feels like it's polynomial interpolation