[heresie-dabord]

> it is over-hyped because like any LLM, it requires a suitable human in the loop to keep the LLM on the straight and narrow, and then to weed through the inevitable false-positives and hallucinations.

"Suitable human" is a dry phrase indeed. ^_^

The hype is "gosh look at all the bad things this brilliant almost conscious tool found!"

The reality: an insecure toolchain for an insecure language with an insecure compiler produced a runnable but insecure binary for an insecure OS. We couldn't be arsed to address any of this before, but now we're being billed the full price of our laziness.

[andai]

Yeah, I was thinking earlier, the way things are going, software (and maybe the internet itself) might need to look a little different in a few years.

Ironically the AIs will probably help us produce higher quality software in the end, because "everything gets pwned" becomes the forcing function for software actually being correct.

In other words I think we are actually entering an age where correctness makes economic sense. (One can dream!) The cost of producing correctness is dropping, and the cost of not doing so is rising massively.