Comment by abustamam

> People almost acting like no one has thought of it

Everyone at my job uses LLMs to code, all day long. People still ask me "why does this bug happen" and I use Claude to find out and the answer is almost always straightforward, and when its not I raise a discussion with the team. The calculus isn't "can I prompt an LLM to find out," it's "do I have a solid enough mental model of the part of the codebase to prompt an LLM specifically enough, and also understand if the LLM is hallucinating or not."

> How can someone serious even think that’s ok.

I think this is a culture issue. I think every org is different, but we had a similar ramp up at our company. First we trialed cursor. Then some people were committing slop. Then we were like "llms are no excuse for slop." Then we got our skills and context good enough to not require close review. And then everything became LLM driven and now we have become "meat proxies" where everyone asks LLMs to fix things that are part of unfamiliar parts of the codebase and then asks someone else familiar to review the fix. We're tending towards a solution to this because I dont think its a good usage of resources but every org will come up with their own culture and solution to this.