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

Dijkstra On the foolishness of "natural language programming"

cs.utexas.edu

Post reply on HN
Print view View original

51–60 of 281 posts

Re: Dijkstra On the foolishness of "natural language programming"

#51

Post by robertlagrant »

delusional wrote: post #21
misja111 wrote: post #4

I somewhat disagree with this. In real life, say in some company, the inception of an idea for a new feature is made in the head of some business person. This person will not speak any formal language. So however you turn it, some translation from natural language to machine language will have to be done to implement the feature. Typically the first step, translation from natural to formal language, will be done by b…

I don't think youre fully comprehending Dijkstra's argument. He's not saying to not use tool to help with translation, he is saying that not thinking in terms of formal symbols HURTS THINKING. Your ideas are worse if you don't think in formal systems. If you don't treat your thoughts as formal things. In your example, he has no opinion on how to translate the idea of a "business person" because in his view the ideas…

If that's correct, then it's very falsifiable. If a businessperson says "there's a gap in the market - let's build X" they will be following a formalism at their level of detail. They see the market, the interactions between existing products and customers, and where things might be going.

Just because they can't spell it out to the nth degree doesn't matter. Their formalism is "this is what the market would like".

Having an LLM then tease out details - "what should happen in this case" would actually be pretty useful.

Re: Dijkstra On the foolishness of "natural language programming"

#52

Post by scribu »

soulofmischief wrote: post #47
01100011 wrote: post #24

People are sticking up for LLMs here and that's cool. I wonder, what if you did the opposite? Take a project of moderate complexity and convert it from code back to natural language using your favorite LLM. Does it provide you with a reasonable description of the behavior and requirements encoded in the source code without losing enough detail to recreate the program? Do you find the resulting natural language descri…

What you're describing is decontextualization. A sufficiently powerful transformer would theoretically be able recontextualize a sufficiently descriptive natural language specification. Likewise, the same or an equivalently powerful transformer should be able to fully capture the logic of a complicated program. We just don't have sufficient transformers yet. I don't see why a complete description of the program's des…

“Fill in the gaps by using context” is the hard part.

You can’t pre-bake the context into an LLM because it doesn’t exist yet. It gets created through the endless back-and-forth between programmers, designers, users etc.

Re: Dijkstra On the foolishness of "natural language programming"

#53

Post by sim7c00 »

drpixie wrote: post #45
01100011 wrote: post #24

People are sticking up for LLMs here and that's cool. I wonder, what if you did the opposite? Take a project of moderate complexity and convert it from code back to natural language using your favorite LLM. Does it provide you with a reasonable description of the behavior and requirements encoded in the source code without losing enough detail to recreate the program? Do you find the resulting natural language descri…

> Do you find the resulting natural language description is easier to reason about? An example from an different field - aviation weather forecasts and notices are published in a strongly abbreviated and codified form. For example, the weather at Sydney Australia now is: METAR YSSY 031000Z 08005KT CAVOK 22/13 Q1012 RMK RF00.0/000.0 It's almost universal that new pilots ask "why isn't this in words?". And, indeed, mos…

you guys are not wrong. explain any semi complez program, you will instantly resort to diagrams, tables, flow charts etc. etc.

ofcourse, you can get your LLM to be bit evil in its replies, to help you truly. rather than to spoon feed you an unhealthy diet.

i forbid my LLM to send me code and tell it to be harsh to me if i ask stupid things. stupid as in, lazy questions. send me the link to the manual/specs with an RTFM or something i can digest and better my undertanding. send links not mazes of words.

now i can feel myself grow again as a programmer.

as you said. you need to build expertise, not try to find ways around it.

with that expertise you can find _better_ ways. but for this, firstly, you need the expertise.

Re: Dijkstra On the foolishness of "natural language programming"

#54

Post by fluidcruft »

01100011 wrote: post #24

People are sticking up for LLMs here and that's cool. I wonder, what if you did the opposite? Take a project of moderate complexity and convert it from code back to natural language using your favorite LLM. Does it provide you with a reasonable description of the behavior and requirements encoded in the source code without losing enough detail to recreate the program? Do you find the resulting natural language descri…

I'm not so sure it's about precision rather than working memory. My presumption is people struggle to understand sufficiently large prose versions for the same reason a LLM would struggle working with larger prose versions: people have limited working memory. The time needed to reload info from prose is significant. People reading large text works will start highlighting and taking notes and inventing shorthand forms in their notes. Compact forms and abstractions help reduce demands for working memory and information search. So I'm not sure it's about language precision.

Re: Dijkstra On the foolishness of "natural language programming"

#55

Post by Dansvidania »

- some people found error messages they couldn't ignore more annoying than wrong results

I wonder if this is a static vs dynamic or compiled vs interpreted reference.

Anyway I love it. Made me giggle that we are still discussing this today, and just to be clear I love both sides, for different things.

Re: Dijkstra On the foolishness of "natural language programming"

#56

Post by WillAdams »

drpixie wrote: post #45
01100011 wrote: post #24

People are sticking up for LLMs here and that's cool. I wonder, what if you did the opposite? Take a project of moderate complexity and convert it from code back to natural language using your favorite LLM. Does it provide you with a reasonable description of the behavior and requirements encoded in the source code without losing enough detail to recreate the program? Do you find the resulting natural language descri…

> Do you find the resulting natural language description is easier to reason about? An example from an different field - aviation weather forecasts and notices are published in a strongly abbreviated and codified form. For example, the weather at Sydney Australia now is: METAR YSSY 031000Z 08005KT CAVOK 22/13 Q1012 RMK RF00.0/000.0 It's almost universal that new pilots ask "why isn't this in words?". And, indeed, mos…

Reading up on the history of mathematics really makes that clear as shown in

https://www.goodreads.com/book/show/1098132.Thomas_Harriot_s...

(ob. discl., I did the typesetting for that)

It shows at least one lengthy and quite wordy example of how an equation would have been stated, then contrasts it in the "new" symbolic representation (this was one of the first major works to make use of Robert Recorde's development of the equals sign).

Re: Dijkstra On the foolishness of "natural language programming"

#58

Post by card_zero »

fluidcruft wrote: post #54
01100011 wrote: post #24

People are sticking up for LLMs here and that's cool. I wonder, what if you did the opposite? Take a project of moderate complexity and convert it from code back to natural language using your favorite LLM. Does it provide you with a reasonable description of the behavior and requirements encoded in the source code without losing enough detail to recreate the program? Do you find the resulting natural language descri…

I'm not so sure it's about precision rather than working memory. My presumption is people struggle to understand sufficiently large prose versions for the same reason a LLM would struggle working with larger prose versions: people have limited working memory. The time needed to reload info from prose is significant. People reading large text works will start highlighting and taking notes and inventing shorthand forms…

So is more compact better? Does K&R's *d++ = *s++; get a pass now?

Re: Dijkstra On the foolishness of "natural language programming"

#59

Post by nsonha »

01100011 wrote: post #24

People are sticking up for LLMs here and that's cool. I wonder, what if you did the opposite? Take a project of moderate complexity and convert it from code back to natural language using your favorite LLM. Does it provide you with a reasonable description of the behavior and requirements encoded in the source code without losing enough detail to recreate the program? Do you find the resulting natural language descri…

isn't that just copilot "explain", one of the earliest copilot capabilities. It's definitely helpful to understand new codebases at a high level

> there is a reason why legalese is not plain English, and it goes beyond mere gatekeeping.

unfortunately they're not in any kind of formal language either

Re: Dijkstra On the foolishness of "natural language programming"

#60

Post by izabera »

soulofmischief wrote: post #47
01100011 wrote: post #24

People are sticking up for LLMs here and that's cool. I wonder, what if you did the opposite? Take a project of moderate complexity and convert it from code back to natural language using your favorite LLM. Does it provide you with a reasonable description of the behavior and requirements encoded in the source code without losing enough detail to recreate the program? Do you find the resulting natural language descri…

What you're describing is decontextualization. A sufficiently powerful transformer would theoretically be able recontextualize a sufficiently descriptive natural language specification. Likewise, the same or an equivalently powerful transformer should be able to fully capture the logic of a complicated program. We just don't have sufficient transformers yet. I don't see why a complete description of the program's des…

>sufficiently descriptive natural language specification https://www.commitstrip.com/en/2016/08/25/a-very-comprehensi...
Post reply on HN