How else does consistency work, then?

Only being half facetious here. Maybe you or someone else really has a better take.

What do you mean by consistency here?

Let me LLM-expand that for you…

Then there are almost no domain experts.

There’s at least one

https://en.wikipedia.org/wiki/Paul_Mockapetris

Ran into this, as well.

And they were really annoyed at being asked math questions.

Additional iterations are valuable, if and only if we learn from additional iterations. Otherwise we are just spinning our wheels.

No. AI sucks at formal languages and implications.

Lossy decompression probably won’t ever be really good at this. If it’s missing from the data, then it won’t be there.

The AI math proofs were probably already out there in tiny pieces and nobody got all of the pieces together. That is valuable. It’s different from making a piece that is missing. And the AI will just hallucinate.

Talking to CPAs never gets you to Pacioli groups.

Talking to engineers and mathematicians gets you there.

Working model suitable for an electronic computer.

Excellent example.

This is one of the few mistakes K&R made going from BCPL to C.