The strength of Lisps is in ability to define DSLs and then concisely express solutions for problems in that domain. Arguably no other programming language was able to exceed or even match that power until now.
The math behind transformers is deterministic, so LLMs could be treated as compilers (putting aside intentionally adding temperature and non-determinism due to current internal GPU scheduling). In the future I imagine we could be able to declare a dependency on a model, hash its weights in a lockfile and the prompt/spec itself will be the code, which corresponds to that insight.
> the prompt/spec itself will be the code, which corresponds to that insight.
What I've understood from discussions on HN is that LLMs are non-deterministic. Am I right? So the same prompt when executed again could produce a different answer, a different program every time.
That would mean the prompt is not a great 'highleve lanaguage", it would get compiled into a different Lisp-program depending on the time of the day?
The math behind transformers is deterministic, so LLMs could be treated as compilers (putting aside intentionally adding temperature and non-determinism due to current internal GPU scheduling). In the future I imagine we could be able to declare a dependency on a model, hash its weights in a lockfile and the prompt/spec itself will be the code, which corresponds to that insight.