Comment by jibalt

As I noted elsewhere, a harness could be constructed that asks an LLM for something to do, then directs an agent to do it, and then repeat.

That's a computer program -- Turing completeness is very expansive. The LLM could even give a motive for selecting what to do, reflecting human motivations intrinsic to its training data. You seem emotionally wedded to a very narrow view of what computer programs can do ... I suspect religion is involved.