You can put a lot of thoughts while using LLMs.
You are equating manual coding with more thinking, which has proven to be not the case given that it is mostly automated.
It's possible to code thoughtfully with LLMs, but the process strongly encourages superficial signing-off on its activities.
If one person knows how to code, they don't need an LLM. I've tried using all of them on my job, and I will give them a second chance time by time (to see if the claims made by these big tech hold up) and ALL of the time I've didn't noticed any speedup compared to coding manually.
If you are an experienced programmer (not someone that did an online course and calls like this) with YEARS of experience in coding in multiple languages really, the only real limitation is the speed at which you can type on the keyboard, that is usually way faster than what the even good LLM is able to emit tokens.
This not considering token expense: if we see at the point of view of the company, it's way cheaper an experienced programmer, that in my country costs you 4000 a month tax included, than the tokens that an LLM would use to do the same job.
On top of that there is the environmental impact of all of this, and why they are almost making me not use my car because it's euro 5 and now there is euro 6, these AI companies are emitting tons of CO2 to do stuff that human beings can do with 1/1000 the energy that these AI companies use.
It sounds more like you are equating a totally-vibe coded product with no verified code, with a product thoughtfully written by a human with LLM assistance.
If the developer can't be bothered to not make it look vibecoded I assume there's a minimal amount of thought and effort put into it. And in that case I'm not going to bother using it.