Comment by yshrestha
4 years ago
Language models can generate a Python function that does the math perfectly.
I bet you would get better results if you tweaked the prompt to say "Generate a Python program that solves X math problem" and then just ran the resulting Python script.
It does not need to be AGI to be useful.
you can also tell the model that it doesnt know how to do math, and it respects that
https://twitter.com/goodside/status/1568448128495534081
This is pretty cool, although the "don't use outside the security sandbox" made me laugh: https://twitter.com/goodside/status/1568704302813700096/phot...
You mean "generate a Python function that calls a library that does math perfectly, right?
In the limit, it's going to design an AI to write some python to call a library that does the math perfectly.
Unlike 99.99% of human programmers, who can and often do implement everything in sympy/numpy from scratch ;-)
Exactly! Hey it gets the job done :)
Software is just a tall wedding cake of abstractions built on top of abstractions.
That could only generate constructivist [0] proofs, and there are many things done in modern maths which are not constructivist. Maybe a better approach would be to use Curry-Howard [1] correspondence to directly get proofs from generated programs
[0] https://en.wikipedia.org/wiki/Constructivism_(philosophy_of_...
[1] https://en.wikipedia.org/wiki/Curry%E2%80%93Howard_correspon...
Live demo of this you can run: https://twitter.com/sergeykarayev/status/1569377881440276481
That is also a very valid and interesting thing to do.
But it's also quite interesting to see how the model would do "by itself". All kinds of interesting lessons to be learned!
Yeah! It is interesting to try and figure out "what" the model is actually learning. It is a valid thread of scientific inquiry.
Exactly, we need computer-equipped neural nets. Models need to use traditional UIs (including programming languages) and then we can talk about how to stop them. :)