Do you ever actually think during this process? or could I train a monkey to do this same activity with the same outcomes?

Of course I think. I have 20 years of coding experience and knowledge of the codebase and business. That’s why I’m keenly aware of how strange the process is.

What I’d like to know is how you’d train a monkey to read and judge output from an llm on a pull request.

Here we go again

I read this as im "reviewing" a 100% claude generated ten page incident RCA report. It's mostly wrong but bringing that up is not useful so just rubber stamp and move on.

we as a culture will gradually find a resting place here in regards to "proof of work" but it will be a painful decade in the meantime.

I’m finding that companies are starting to be way less lenient to that.

Nobody wants to consume slop.

"Created the nuke" is the best framing. Detonated a WMD on the field of rigorous practice.

> The floor has been raised significantly as to what bad code can even look like

It's hard for me to disagree with this take more wow. LLM slop code is TERRIBLE and verbose.

I could not agree more. I feel the exact same, its just a ton of content here that might not necessarily be "worse" I just find it (LLMs) dreadfully boring uninteresting. Lobste.rs seems to be nicer so I lurk there a lot now as I can't post.

Thx claude

This is what I do for small stuff, debian vm, k3s on it for a nicer http based deployment api.

They are at least more tasteful about it, but they do have to keep getting VCs. And no one has ever accused VCs of being smart or technical.