Why do anything at all?

Why even deploy such systems? I would support less for sure.

I loved it, I’ve never seen something like it

thank you!! this website was made loooong ago before gpt3 was even a thing lol (saying this because people thought it was vibecoded lol), the design of it brings me joy and i wouldn't change it for anything

This is enough to make me never use ars technica again

Brave

Yeah I don't see the utility in doing this hundreds of times back to back. A few iterations can tell us some things about how Claude optimizes code, but an open ended prompt to endlessly "improve" the code sounds like a bad boss making huge demands. I don't blame the AI for adding BS down the line.

I don't think the question "will the AI add BS" was what drove this experiment. The very first thing the author references is re-feeding and degrading the same image 100 times, which similarly is not about improving the image.

This was more about seeing in what interesting ways the LLM will "fail", to get a little glimpse into how the black-box "thinks".

I'm not a C++ programmer, but wouldn't your example be a fairly structured problem? You wanted to improve performance of a specific part of your code base.

You might like Cultish: The Language of Fanaticism by Amanda Montell. Very eye opening on how groups from religions to crossfit classes exploit humanity's tendency to form groups and follow charismatic leaders, even after the "cult" becomes toxic to the individual members.