Non determinism does not imply non correctness. You can have the LLM do 10 different outputs, but maybe all 10 are valid solutions. Some might be more optimal in certain situations, and some might appeal to different people aesthetically.

▲

tjr 3 days ago | parent [-]

Nondeterminism indeed does not imply non-correctness.

All ten outputs might be valid. All ten will almost certainly be different -- though even that is not guaranteed.

The OP referred to the notion of there being no manual; we have to figure out how to use the tool ourselves.

A traditional programming tool manual would explain that you can provide input X and expect output Y. Do this, and that will happen. It is not so clear-cut with AI tools, because they are -- by default, in popular configurations -- nondeterministic.

▲

grim_io 3 days ago | parent [-]

We are one functional output guarantee away from them being optimizing compilers.

Of course, we maybe never get there :)

▲

tjr 3 days ago | parent [-]

Why would one opt to use an LLM-based AI tool as a compiler? It seems that would be extraordinarily complex over traditional compilers, but for what benefit?

▲

grim_io 3 days ago | parent [-]

It would be, in its ideal state a vague problem to concrete and robust implementation compiler.

A star trek replicator for software.

Obviously we are nowhere near that, and we may never arrive. But this is the big bet.

	▲	optimalsolver 19 hours ago \| parent [-]
		>A star trek replicator for software That's a very interesting way to put it.