I agree with you but perhaps I'm misread you, how else would you do autoresearch and loop engineering without LLMs?

you specify the goal. if the goal is achieved, it's achieved.

the code the LLM writes will be read and maintained and developed further by LLMs. so it doesn't really matter what it produces as long as all the tests are green and it achieves exactly what you want it to achieve.

depends on the implementation.

the claude loop/goal just decides it doesnt feel like doing it anymore and ends the loop or goal

in an other thread I've commented, but I use a benchmark - profile - verify - research - improve loop.

LLMs take shortcuts if allowed.

Humans do it ignorantly.

The LLMs will improve while average human IQ in the west dips closer and closer to the 80s on the global scale.