Retire the Abstractions(hazyresearch.stanford.edu) |
Retire the Abstractions(hazyresearch.stanford.edu) |
No matter how intelligent the executor is, without knowledge of the relevant external context, specs will always have to be clearly defined and given.
A good abstraction is a single edged sword which simplifies the task. A mediocre abstraction is a double-edged sword. A bad abstraction is like a single edged sword with a restrictive handle and the sharp edge is facing towards you.
That is some seriously convoluted writing.
But we can't drop all abstractions. It's not physically possible. The AI agent is going to break logic up into files... The AI will create/impose an abstraction for each piece of logic whether we like it or not.
So saying "drop abstractions" is actually saying "let the AI decide what the abstractions should be" and unfortunately because LLMs are trained on average code, those abstractions are often pretty poor.
Coming up with the right abstractions is actually one of the main skills which AI hasn't automated and where the human brings the most value. It affects maintainability directly; including when using AI.
I've worked on projects with poor abstractions and ones with good abstractions using AI. The ones with poor abstractions require 10x to 100x more tokens and time to solve problems and implement new features. You're constantly fighting it to prevent it from coming up with nasty hacks and workarounds. Poor abstractions create the need for hacks and workarounds.
Djikstra has a great article as to why English language programming will always be second to a programming language. A "formal system" (edited from regular language) is the most precise way to specify things. An "abstraction" is basically a domain specific language.
The way I like to use LLMs is to build abstractions. I like to build mathematical code and ask the LLM to use it. I think that LLMs are very mathematical thinkers and they like it when they see Semigroup<T>. And it's not hifalutin either, I'm processing calculations along DAGs with a million+ nodes in milliseconds, thanks to abstractions
and today's agents increase codebase size and complexity much faster than humans do via traditional software engineering methods, so this is likely to hit a wall faster than if human software teams were to do this experiment.
I don't think raw machine code (not even assembly) is the best form to reason about program logic. It just takes too many steps to execute sophisticated processes to keep them all in your head at once - or keep them all in an LLM context at once.
But the reality is different. First of all LLM were trained on current data, with the abstractions we currently use.
Secondly they suffer they same problems we do, their context size is way too small to just simply ignore abstractions.
i would be shocked if a well designed framework were less efficient than "bespoke" clankercode for low-level work
Typically CS labs at universities contain people who have not spent a significant amount of time exposed to large industry codebases and the corresponding complexity. I think the post would have more credibility coming from e.g. the platforms team at a tech company with a monorepo.
cia boss: what did we learn, palmer? cia officer: i don't know, sir. cia boss: i don't fkin know either. i guess we learned not to do it again.
No.
The main problem with Python is that, if you’re not doing your work in highly optimized numeric libraries (which are usually written in C), then you’re paying terrible overheads to use the Python interpreter. Type checking doesn’t help with this because Python is dynamically typed but static types could in principle. Is that what you mean?
I don't have any ml experience with python only numerical libraries and I always have to be careful what I'm doing otherwise an experiment can go Kaput. Types stop that.
If a passerby told me this story I’d have the same guess though!