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

LLMs can be exhausting

tomjohnell.com

Post reply on HN
Print view View original

71–80 of 232 posts

Re: LLMs can be exhausting

#71

Post by sarchertech »

anonzzzies wrote: post #43
sarchertech wrote: post #36

Earlier quoted context omitted.

I currently work at one of the biggest tech companies. I’ve been doing this for over 20 years, and I’ve worked at scrappy startups, unicorns, and medium size companies. I’ve certainly seen my share of what I call slot driven development where a developer just throws things at the wall until something mostly works. And plenty if cut and paste development. But it’s far from the majority. It’s usually the same few devel…

Tech companies. How about massive non software tech companies. I don't know where it is not the norm and I have been in very many of them as supplier for the past 30 years. Tech companies are a bit different as they usually have leadership that prioritizes these things.

None tech companies too. You can’t build large scale software with everyone merging PRs like that. My guess is that if you’re a supplier your are getting a pretty severe sampling bias.

Re: LLMs can be exhausting

#72

Post by owentbrown »

I really appreciate the author for writing this.

I learned years ago that I when I write code after 10 PM, I'm go backward instead of forward. It was easy to see, because the test just wouldn't pass, or I'd introduce several bugs that each took 30 minutes to fix.

I'm learning now that it's no different, working with agents.

Re: LLMs can be exhausting

#73

Post by flir »

stainlu wrote: post #62

[flagged]

I've always preferred brownfield work. In the past I've said "it's easier to be an editor than an author" to describe why. I think you're on to something. For me the new structure's cognitively easier, but it's not faster. Might even be slightly slower.

Re: LLMs can be exhausting

#74

Post by orbisvicis »

jeremyjh wrote: post #15
SchemaLoad wrote: post #9

Earlier quoted context omitted.

I've found writing the code massively helps your understanding of the problem and what you actually need or want. Most times I go into a task with a certain idea of how it should work, and then reevaluate having started. While an LLM will just do what you ask without questing, leaving you with none of the learnings you would have gained having done it. The LLM certainly didn't learn or remember anything from it.

In some cases, yes. But I’ve been doing this awhile now and there is a lot of code that has to be written that I will not learn anything from. And now, I have a choice to not write it.

Ehh, I find that the most tedious code is also the most sensitive to errors, stuff that blurs the divide between code and data.

Re: LLMs can be exhausting

#75

Post by zahlman »

flir wrote: post #73
stainlu wrote: post #62

[flagged]

I've always preferred brownfield work. In the past I've said "it's easier to be an editor than an author" to describe why. I think you're on to something. For me the new structure's cognitively easier, but it's not faster. Might even be slightly slower.

It takes all kinds, I suppose.

Re: LLMs can be exhausting

#76

Post by jeremyjh »

orbisvicis wrote: post #74
jeremyjh wrote: post #15

Earlier quoted context omitted.

In some cases, yes. But I’ve been doing this awhile now and there is a lot of code that has to be written that I will not learn anything from. And now, I have a choice to not write it.

Ehh, I find that the most tedious code is also the most sensitive to errors, stuff that blurs the divide between code and data.

I doubt if we're talking about the same sort of things at all. I'm talking about stuff like generic web crud. Too custom to be generated deterministically but recent models crush it and make fewer errors than I do. But that is not even all they can do. But yes, once you get into a large complicated code base its not always worth it, but even there one benefit is it to develop more test cases - and more complicated ones - than I would realistically bother with.

Re: LLMs can be exhausting

#78

Post by cgh »

j3k3 wrote: post #67
stainlu wrote: post #62

[flagged]

Great post. So the people who are claiming huge jumps in productivity in the workplace, how are they dealing with this 'review fatigue'?

What we once called “vibe coding” is increasingly known as just coding. There’s no reasonable way to review thousands of lines of code a day and many organizations simply aren’t. No review fatigue there! Just a black box of probable spaghetti.

Re: LLMs can be exhausting

#80

Post by jeremyjh »

stavros wrote: post #57
SchemaLoad wrote: post #9

Earlier quoted context omitted.

I've found writing the code massively helps your understanding of the problem and what you actually need or want. Most times I go into a task with a certain idea of how it should work, and then reevaluate having started. While an LLM will just do what you ask without questing, leaving you with none of the learnings you would have gained having done it. The LLM certainly didn't learn or remember anything from it.

It depends on how you use them. In my workflow, I work with the LLM to get the desired result, and I'm familiar with the system architecture without writing any of the code. I've written it up here, including the transcript of an actual real session: https://www.stavros.io/posts/how-i-write-software-with-llms/

Thanks for writing this up.

I just woke up recently myself and found out these tools were actually becoming really, really good. I use a similar prompt system, but not as much focus on review - I've found the review bots to be really good already but it is more efficient to work locally.

One question I have since you mention using lots of different models - is do you ever have to tweak prompts for a specific model, or are these things pretty universal?

Post reply on HN