[aurareturn]

Why can’t an LLM run experiments to synthesize new facts?

[tovej]

That's not what synthesis is.

But that small semantic note aside, if an LLM is used to trigger other tools to find new facts, then those other tools are modeling the "world" or a particular domain. Alternatively you could say that the system as a whole, that the LLM is a part of, models the "world" or a particular domain.

[aurareturn]

Does it matter how the new fact is acquired?

If an LLM uses a calculator to come up with an answer, does it make it worse than a model that can inference the answer without using a tool?