Recent big discussion on NATS. https://news.ycombinator.com/item?id=46196105 (3 months ago)

Explanation and summarization without visual interactables is so much harder to do. A person can talk to an interface but I don't know how many people would like natural language back.

Those two tasks are just very different. In one world you have provided a complete specification, such as 1 + 1, for which the calculator responds with some answer and both you and the machine have a decidable procedure for judging answers. In another world you have engaged in a declaration for which the are many right and wrong answers, and thus even the boundaries of error are in question.

It's equivalent to asking your friend to pick you up, and they arrive in a big vs small car. Maybe you needed a big car because you were going to move furniture, or maybe you don't care, oops either way.

Yes. That is the point I was making.

Calculators provide a deterministic solution to a well-defined task. LLMs don't.

Furthermore, it is possible to build a precise mathematical formula to produce a desired solution

It is not possible to be nearly as precise when describing a desired solution to an LLM, because natural languages are simply not capable of that level of precision... Which is the entire reason coding languages exist in the first place

But AI might actually get you there in terms of superior pedagogy. Personal Q&A where most individuals wouldn't have afforded it before.

I have a feeling we'll care less about untyped languages going forward as LLMs prototype faster than we do, and fast prototyping was a big reason why we cared about untyped languages.

Pedantic but Lisp is not "untyped". (Neither are JS or Python.) All data has a type you can query with the type-of function. The typing is strong, you'll get a type-error if you try to add an integer to a string. Types can be declared, and some implementations (like SBCL) can and do use that information to generate better assembly and provide some compilation-time type checks. (Those checks don't go all the way like a statically typed language would, but Lisp being a programmable programming language, you can go all the way to Haskell-style types if you want: https://coalton-lang.github.io/)

Javascript and Python have the most training data by far though, right?

It's not like state laws couldn't pertain to Pam Bondi, but the dominant framing around her is going to be federal officer exercising her powers, rightly or wrongly, over a federal office and while under the direction of the president.

If Claude can do it reasonably well then there’s another tier of technical skill that can reach.

I'm afraid this hits the credibility of the article for me, that's a pretty weird mistake to make. It's like paying for a Model 3 while thinking it comes from Ford.

Thank you for your feedback!

Could you show an example?

All the companies you’re thinking of are likely paying the Tolkien estate a very fat fee. This repo will likely have to rename.

Yeah. Unfortunately the people running the estate today appear to share ~none of the late Professor's values.