The ambiguity can be constrained by obeying precise syntactic constructs, but then, you have created a formal language

High-level PLs are more abstract than assembly, but equally formal. I think moving any kind of logic to natural language represents a different kind of leap than we took by moving from low-level PLs to high-level ones.

NL is inherently ambiguous. Even a word like ‘or’ can mean either OR or XOR

I’m very skeptical this can even happen. Formal logic and formal language in general relies on precise syntax

Indirectly related to LLMs, and good chance you’ve already read this, but I like Dijkstra’s essay: www.cs.utexas.edu/~EWD/transcr...

You can now find domain

The library will become the interpreter ;) and then bootstrap from there! Or that’s my plan anyway

Yes but other way! Hurtboxes take the damage

All hurtboxes are hitboxes, but not all hitboxes are hurtboxes.

Hurtboxes receive damage

Someone will write a generalized NtoN+1 based on induction and we’ll solve Python

Really cool

One more mystery down, hopefully not much more than one to go..

Aha, I got it :) you can perform such a shift arithmetically! An interesting thing is that right-shifting a transfinite expression reduces its order, so this operation is a rightshift on finites, but a rightshift plus a compensation on transfinites, to make up for the order decrement

It takes a lot of mental effort to consider but it doesn’t seem insurmountable either. You just have to preserve
1. Order (ordinality)
2. Sequence of cardinalities under ceiling division

I know that none of this makes sense without context but oh well