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

Automating myself out of development

thoughtfultechnologist.com

Post reply on HN
Print view View original

11–20 of 97 posts

Re: Automating myself out of development

#11

Post by MonstraG »

davidcann wrote: post #8
noelwelsh wrote: post #2

I wish people would describe in more detail the tasks they use LLMs to code. My experience is that simple components in an existing architecture are fine, but anything requiring architectural considerations quickly becomes a mess. On my projects (e.g. a ui framework), running multiple agents in parallel would just increase the speed at which it can stuff up the project.

I built this with 94% written by coding agents: https://buildermark.dev/ The complete log of all prompts and commits is here: https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN

It seems that pages 2-5 on

https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN/...

still show content of page 1

Re: Automating myself out of development

#13

Post by ryanackley »

properbrew wrote: post #5
noelwelsh wrote: post #2

I wish people would describe in more detail the tasks they use LLMs to code. My experience is that simple components in an existing architecture are fine, but anything requiring architectural considerations quickly becomes a mess. On my projects (e.g. a ui framework), running multiple agents in parallel would just increase the speed at which it can stuff up the project.

I used LLMs to develop Whistle Enterprise ( https://whistle-enterprise.com ) from the ground up, from scratch. It's taken _a lot_ of time and effort, but this is an example of what can be developed using LLMs alone. You have to have dedication and a goal to reach, but you can absolutely build anything if you're building with the right foundations in mind.

I think the relevant question isn’t what can be built but the amount of effort in comparison to doing this the old fashioned way.

What do you think the productivity gain was from using an LLM? This question assumes you’re already an experienced developer.

Re: Automating myself out of development

#14

Post by davidcann »

MonstraG wrote: post #11
davidcann wrote: post #8

Earlier quoted context omitted.

I built this with 94% written by coding agents: https://buildermark.dev/ The complete log of all prompts and commits is here: https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN

It seems that pages 2-5 on https://demo.buildermark.dev/projects/u020uhEFtuWwPei6z6nbN/... still show content of page 1

Thanks for the report. I messed up the CDN settings. It looks fixed now.

Re: Automating myself out of development

#16

Post by gnunicorn »

Interestingly, despite it being much more detailed and a lot more process and procedure than what I currently do - which is more akin to the version 0 described, but in parallel - we come up at the same final problem: reviews and quality assurance.

I sign off the code I merged, part of company policy but also just to be sure it is actually decent. But reviewing has become the real draining bottleneck: even stacked PRs, if that total 5-6k lines is not a 5min job. Even if I brainstormed and set the plan, that's really the part that doesn't scale right now for me in this. But the author is very shy about that: either the changes arent that big in the end or they trust the process enough to review in a more casual manner. Being equally untrusting I can't do that ...

Re: Automating myself out of development

#17

Post by strogonoff »

gnunicorn wrote: post #16

Interestingly, despite it being much more detailed and a lot more process and procedure than what I currently do - which is more akin to the version 0 described, but in parallel - we come up at the same final problem: reviews and quality assurance. I sign off the code I merged, part of company policy but also just to be sure it is actually decent. But reviewing has become the real draining bottleneck: even stacked PR…

Proper review should take longer than writing it yourself, because you need to know the correct solution, understand the proposed solution, and evaluate the difference between the two. When designing it yourself, you just need to know the correct solution and write it, and with modern high-level languages and IDEs with autocomplete writing it is hardly a bottleneck.

Re: Automating myself out of development

#18

Post by thi2 »

yieldcrv wrote: post #3

I don't know if I’m overly critical but there’s gotta be a middle ground between totally AI pilled people that otherwise have no talents, and control freak veteran developers who cant let go My current process is also using Github projects in a normal scrum style way, with many tickets written or fleshed out and state managed by the LLM, and it doubling as the memory system Completely leapfrogging all these other ope…

There are tons of people, those are just not as vocal.

Re: Automating myself out of development

#19

Post by nisabek »

gnunicorn wrote: post #16

Interestingly, despite it being much more detailed and a lot more process and procedure than what I currently do - which is more akin to the version 0 described, but in parallel - we come up at the same final problem: reviews and quality assurance. I sign off the code I merged, part of company policy but also just to be sure it is actually decent. But reviewing has become the real draining bottleneck: even stacked PR…

If I'm attentive during spec/plan creation I sort of build this "expectation" of what the actual PR will look like, the mental model of it. Then it's somewhat easier to review. But the mental load is brutal tbh, and still not sure if it's "worth it"

Re: Automating myself out of development

#20

Post by nisabek »

yieldcrv wrote: post #3

I don't know if I’m overly critical but there’s gotta be a middle ground between totally AI pilled people that otherwise have no talents, and control freak veteran developers who cant let go My current process is also using Github projects in a normal scrum style way, with many tickets written or fleshed out and state managed by the LLM, and it doubling as the memory system Completely leapfrogging all these other ope…

Could be (the overcomplicating part), I'm just not yet comfortable loosing the mental model of the final application. At least not in all types of tickets. Are you not seeing that?..
Post reply on HN