I do not understand why people keep building these anti-human LLM systems.

It just needs ca 5 seconds to realize "oh damn, I would not want to be at the receiving end of this" and conclude that it's probably a bad idea.

Why does this keep happening?

Especially since the idea of having such automated reviews probably isn't bad. But why mess up the execution like this basically every single time?

▲

throwawayffffas an hour ago | parent [-]

Because they are swamped and want to automate some of the process.

The way I see it the devs that put that in place are saying, listen before even reading your contribution I am going to feed it to a LLM with these instructions and see what it spits out. Now I will extricate my self from being the LLM proxy so you deal with this output and when it's okay I will look at it.

Same as "listen bud until it passes linting I won't even look at it." Just a much more flexible and fuzzy linter.

	▲	hypfer an hour ago \| parent \| next [-]
		Yes that is obvious, but I still do not understand it, the same way I do not understand why someone would crunch and do drugs just to attempt to meet a deadline and then still don't, instead of going "this isn't working, we will stop and pivot". It's just such an obviously terrible execution. Why would you throw it into production when doing literally anything else - and that includes just setting the whole server on fire - is less damaging. (Not hyperbole. Loss of trust and loss of trust in ones own judgement is the highest and harshest price in this industry)
	▲	InsidiousWombat an hour ago \| parent \| prev [-]
		If it was truly much more flexible the problem wouldn't be there because people wouldn't be swamped by LLM slop to sort thru