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.

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

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.

I've seen this several times now. Disturbing.

IMO, LLMs will be a dead end to anything close to AGI because of this and hallucinations.

We're missing something in the mix, which I suspect is some kind of advanced JEPA model.