I recently wrote a small service to get a temperature LED panel on my computer case working. It required a proprietary program to pipe the sensor temps to the display, which only worked on Windows. Being on Linux (arch btw :P), there wouldn't be a way to get this to work. I had a lot of fun learning about how to reverse engineer the inputs/outputs the other software was doing and replicate it in Python.

It is interesting watching all these large companies essentially try to "start-up" these new products and absolutely fail.

It's really important to stay active on things outside yourself and to at least spend some time outside most days.

I found that Claude wasn't too great at first at it and returned a lot of hallucinated methods or methods that existed in Pandas but not Polars. I chalk this up to context blurring and that there's probably a lot less Polars code in the training corpus.

I found it most useful for quickly pointing me to the right documentation, where I'd learn the right implementation and then use it. It was terrible for the code, but helpful as a glorified doc search.

I see it with coworkers all the time. They'll ask ChatGPT to do an analysis and it'll output test results for a T-test. They don't know how to interpret it at all, and so it's ultimately meaningless to them. They're just using "stat sig" as a way to make a non-technical VP happy. In situations like this, I don't think a highly intelligent source, model or human, can make the recipient be more intelligent than they actually are.

Think of a lot of the inflammatory content on social media, how people have made whole careers and fortunes over outrage, and they have no shame over it.

It really does begin to look like having a good sense of shame isn't rewarded in the same way.