My biggest AI win so far was using ChatGPT as a transpiler to convert from vanilla JS code to GLSL. It took 7 prompts and about 1.5 hours, but without the AI, I would have been thrilled to have completed the project in a week.

Thanks for asking this - I had the same question.

For those unfamiliar, the name is based on the Kiki/Bouba effect: https://en.wikipedia.org/wiki/Bouba/kiki_effect

This must be about Kiki and Jiji by Miyazaki. https://en.wikipedia.org/wiki/Kiki%27s_Delivery_Service

https://fuzzygraph.com - aspires to be the most beautiful equation graphing app

It's interesting to consider that the same phenomenon may also hold true for humanity's psychological software.

I feel like the natural test to do is: do experiments, and see if different people see the same little people doing the same things. That would move the observations from subjective to objective perspective.

Testing the theory of whether psychedelics are just inside our heads or whether our consciousness travels somewhere objectively really is why this Tales From The Trip video is my favorite videos. Both men see the same blue woman which is very interesting! https://youtu.be/P_34oNWmNsc?si=_k2CG5b-TVuDaFvM

I just recently intentionally made the decision to keep the equation input in FuzzyGraph (https://fuzzygraph.com) plain text (instead of something like stylized latex like Desmos has) in order to make it easy to copy and paste equations.

Happy Christmas, and Merry New Year!

With LLMs, you should be able to just query in English and have LLMs transpile from English to SQL.

You should also be able to reliably generate working code with LLMs, but you can't. They aren't a good tool until they actually work when they are supposed to.

SQL largely is plain English, which is one of its design choices.