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

Literate Development: AI-Enhanced Software Engineering

substack.com

Post reply on HN
Print view View original

11–20 of 24 posts

Re: Literate Development: AI-Enhanced Software Engineering

#11

Post by andy24 »

maga wrote: post #4
andy24 wrote: post #2

This article describes a method for LLM-assisted coding process but don’t provide anything of substance to back it up. It’s unclear whether the suggestions and techniques mentioned in the article came from personal experience or have otherwise been verified or experimented with with a real team and a real project.

> It’s unclear whether the suggestions and techniques mentioned in the article came from personal experience or have otherwise been verified or experimented with with a real team and a real project. Since it's not a New Yorker article, I was hoping to spare the audience a long personal life story and deliver a somewhat succinct list of suggestions that others might find useful. However, the question is valid, and yes…

Ehm, I’m kind of in a weird position now. Responding with “I didn’t ask for personal story” sounds rude and I have no way if asking for more details without this. Like, if I was writing an article about optimisasation of an algorithm, I’d include information on the problem before and after, as well as some details how it was measured (the most interesting part). Otherwise it’s hard to discuss anything.

Re: Literate Development: AI-Enhanced Software Engineering

#12

Post by satisfice »

btbuildem wrote: post #3

This is the most insightful article on the intersection of LLMs and software development I have read to date. There is zero fluff here -- every point is key, every observation relevant. In a time of paradigm shift, this is a fantastic guide on how to stay in the driver's seat, and most effectively leverage these tools. The inevitable shift here is upwards, away from the gritty detail of code. Documentation (as in "de…

Of course there's fluff! The LLM part is fluff. It's so much fluff it smothers everything else.

Re: Literate Development: AI-Enhanced Software Engineering

#13

Post by andy24 »

jgilias wrote: post #9
andy24 wrote: post #2

This article describes a method for LLM-assisted coding process but don’t provide anything of substance to back it up. It’s unclear whether the suggestions and techniques mentioned in the article came from personal experience or have otherwise been verified or experimented with with a real team and a real project.

Just try it then. I upvoted it because it aligns with my own findings working on real projects. Especially the bits about needing to “ground” the LLM in appropriate context, and being mindful of the sliding context window.

Can’t use AI at my day job unfortunately. I tried LLMs for code reviews and “opinions” in personal projects, it does pick up things I didn’t know about that I then explore myself, but these are small projects where I practice specific things rather than product development.

Re: Literate Development: AI-Enhanced Software Engineering

#14

Post by jamil7 »

I’ve landed on a few similar techniques and have been using unit tests quite a bit as a guardrail for LLMs. One thing that’s useful when using aider is alternating between the /add and /read-only contexts so that it can only edit the tests or the code but “see” both.

Re: Literate Development: AI-Enhanced Software Engineering

#15

Post by btown »

A rule of thumb I’ve started using is: “if your function name and arguments aren’t good enough to have Copilot tab completion make a cogent attempt at implementing the full behavior, you need more comments/docstrings and/or you need to create utility methods that break down the complexity.”

Alternatively: “if you tab complete a docstring and it doesn’t match what you expect, your code can be clearer and you should add comments and rename variables accordingly.”

This isn’t hard and fast. Sometimes it risks yak shaving. But if an LLM can’t understand your intent, there’s a good chance a colleague or even your future self might similarly struggle.

Re: Literate Development: AI-Enhanced Software Engineering

#16

Post by siquick »

My strategy is generally to have a back and forward on the requirements with the LLM for 3/4 prompts, then get it write a summary, and then a plan. Then get it to convert the plan to a low level todo list and write it to TODO.md.

Then I get it to go through each section of the todo list and check each item off as it completes it. Generally results in completed tasks that stay on track but also means that I can stop half way through and go back to the tasks without having to prompt from the start again.

Re: Literate Development: AI-Enhanced Software Engineering

#18

Post by Etheryte »

btown wrote: post #15

A rule of thumb I’ve started using is: “if your function name and arguments aren’t good enough to have Copilot tab completion make a cogent attempt at implementing the full behavior, you need more comments/docstrings and/or you need to create utility methods that break down the complexity.” Alternatively: “if you tab complete a docstring and it doesn’t match what you expect, your code can be clearer and you should ad…

This only really makes sense for boilerplate code, if Copilot can consistently tab complete everything you were about to write, maybe you should be working on something new, not rebuilding things that probably already exist as a library.

Re: Literate Development: AI-Enhanced Software Engineering

#19

Post by danielbln »

MoonGhost wrote: post #17

Regardless, are there any good examples of projects generated by LLMs? There was a game like Angry Birds. But that was long time ago. I did some simple 'games'. If it's easy there should be a lot of open source projects, right?

Who says it's easy? It's deceptively easy, but LLM assisted, especially agentic coding actually has a fairly involved learning curve and many pitfalls and foot guns.

Re: Literate Development: AI-Enhanced Software Engineering

#20

Post by cma »

MoonGhost wrote: post #17

Regardless, are there any good examples of projects generated by LLMs? There was a game like Angry Birds. But that was long time ago. I did some simple 'games'. If it's easy there should be a lot of open source projects, right?

This one was supposedly done by the new Gemini: https://codepen.io/thaakeno/pen/vEYaRgK
Post reply on HN