Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Programming as Theory Building (1985) [pdf]

pages.cs.wisc.edu

Post reply on HN
Print view View original

41–46 of 46 posts

Re: Programming as Theory Building (1985) [pdf]

#41

Post by rramadass »

szvsw wrote: post #32
noddybear wrote: post #30

Earlier quoted context omitted.

The DSL paradigm is generally how I go about using LLMs on new projects, I.e use the LLM to design a language that best represents the abstractions and concepts of the project - and once the language is defined, the LLM can express usecases with the DSL and ultimately convert them into an existing high level language like Python.

Do you have any repos or examples you can share? Would love to see an example of that in action!

I am not the person you asked the question of;

Earlier an HN user had given an example of using Prolog as an intermediate DSL in the prompt to an LLM so as to transform English declarative -> Imperative code - https://news.ycombinator.com/item?id=41549823

Re: Programming as Theory Building (1985) [pdf]

#42

Post by snikeris »

quick_brown_fox wrote: post #22
lolinder wrote: post #12

Earlier quoted context omitted.

What you're describing is the siren call of No Code, which has been tempting manager-types for decades and which has so far failed every single time. The trouble with No Code is that your first paragraph is already my job description: I plan out and document and refine the structure of a problem and its architectural solution while simultaneously developing the system itself. The "sufficient explanation of the goals/…

> The "sufficient explanation of the goals/problem" is the code—anything less is totally insufficient. somewhat in that spirit, I like Gerald Sussman's interpretation of software development as "problem solving by debugging-almost right plans", in e.g. https://www.youtube.com/watch?v=2MYzvQ1v8Ww

The point is also brought up a few times in SICP:

> First, we want to establish the idea that a computer language is not just a way of getting a computer to perform operations, but rather that it is a novel formal medium for expressing ideas about methodology. Thus, programs must be written for people to read, and only incidentally for machines to execute.

Re: Programming as Theory Building (1985) [pdf]

#43

Post by snikeris »

How good are LLMs at reducing code? For example, will they recognize a common problem and build an abstraction around it? I imagine that the solutions they produce tend to have a lot of repetition with small differences that could be improved by abstraction.

Re: Programming as Theory Building (1985) [pdf]

#44

Post by szvsw »

rramadass wrote: post #41
szvsw wrote: post #32

Earlier quoted context omitted.

Do you have any repos or examples you can share? Would love to see an example of that in action!

I am not the person you asked the question of; Earlier an HN user had given an example of using Prolog as an intermediate DSL in the prompt to an LLM so as to transform English declarative -> Imperative code - https://news.ycombinator.com/item?id=41549823

Yep, this makes a lot of sense.

In general, we already have plenty of mechanisms for specifying interfaces/api specs, tests, relationships, etc in a declarative but more formal manner than natural language which probably all work , and I can only imagine we will continue to see the development of more options tailored to this use case.

Re: Programming as Theory Building (1985) [pdf]

#45

Post by abtxu »

CoastalCoder wrote: post #14

Is there an OCR'd version of the provided paper?

Check this comment where you can find multiple versions of this pdf:

"I've seen this scan, what seems like a better digitized version of the same text, and this more formal-looking document, but they all refer to the essay in retrospect"

[Programming as Theory Building - Peter Naur](https://gist.github.com/onlurking/fc5c81d18cfce9ff81bc968a7f...)

Post reply on HN