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

LLM=True

blog.codemine.be

Post reply on HN
Print view View original

11–20 of 155 posts

Re: LLM=True

#11

Post by thrdbndndn »

Something related to this article, but not related to AI:

As someone who loves coding pet projects but is not a software engineer by profession, I find the paradigm of maintaining all these config files and environment variables exhausting, and there seem to be more and more of them for any non-trivial projects.

Not only do I find it hard to remember which is which or to locate any specific setting, their mechanisms often feel mysterious too: I often have to manually test them to see if they actually work or how exactly. This is not the case for actual code, where I can understand the logic just by reading it, since it has a clearer flow.

And I just can’t make myself blindly copy other people's config/env files without knowing what each switch is doing. This makes building projects, and especially copying or imitating other people's projects, a frustrating experience.

How do you deal with this better, my fellow professionals?

Re: LLM=True

#12

Post by block_dagger »

Interesting idea but bad tspec. A better approach would be a single env var (DEV_MODE perhaps) with “agent” and “human” as values (and maybe “ci”).

Re: LLM=True

#13

Post by troethe »

On a lot of linux distros there is the `moreutils` package, which contains a command called `chronic`. Originally intended to be used in crontabs, it executes a command and only outputs its output if it fails. I think this could find another use case here.

Re: LLM=True

#14

Post by jascha_eng »

I noticed this on my spring boot side project. Successful test runs produce thousands of log lines in default mode because I like to e.g. log every executed SQL statement during development. It gives me visibility into what my orm is actually doing (yeh yeh I know I should just write SQL myself). For me it's just a bit of scrolling and cmd+f if I need to find something specific but Claude actually struggles a lot with this massive output. Especially when it then tries to debug things finding the actual error message in the haystack of logs is suddenly very hard for the LLM. So I spent some time cleaning up my logs locally to improve the "agentic ergonomics" so to say.

In general I think good DevEx needs to be dialed to 11 for successful agentic coding. Clean software architecture and interfaces, good docs, etc. are all extremely valuable for LLMs because any bit of confusion, weird patterns or inconsistency can be learned by a human over time as a "quirk" of the code base. But for LLMs that don't have memory they are utterly confusing and will lead the agent down the wrong path eventually.

Re: LLM=True

#15

Post by Bishonen88 »

noname120 wrote: post #9
dizzy3gg wrote: post #6

Earlier quoted context omitted.

That would achieve 1 of the 3 wins.

Probably the main one, people mostly complain about context window management rather than token usage

Dunno about that. Having used the $20 claude plan, I ran out of tokens within 30 minutes if running 3-4 agents at the same time. Often times, all 3-4 will run a build command at the end to confirm that the changes are successful. Thus the loss of tokens quickly gets out of hand.

Edit: Just remembered that sometimes, I see claude running the build step in two terminals, side-by-side at nearly the same time :D

Re: LLM=True

#16

Post by canto »

vorticalbox wrote: post #4

could we not instruct the LLM to run build commands in a sub agents which could then just return a summary of what happened? this avoids having to update everything to support LLM=true and keep your current context window free of noise.

q() { local output output=$("$@" 2>&1) local ec=$? echo "$output" | tail -5 return $ec }

There :)

Re: LLM=True

#17

Post by syhol »

thrdbndndn wrote: post #11

Something related to this article, but not related to AI: As someone who loves coding pet projects but is not a software engineer by profession, I find the paradigm of maintaining all these config files and environment variables exhausting, and there seem to be more and more of them for any non-trivial projects. Not only do I find it hard to remember which is which or to locate any specific setting, their mechanisms…

You start with the cleanest most minimal config you can get away with, but over the years you keep adding small additions and tweaks until it becomes a massive behemoth that only you will ever understand the reasoning behind.

Re: LLM=True

#18

Post by pelasaco »

`Humans=True`

The best friend isn't a dog, but the family that you build. Wife/Husband/kids. Those are going to be your best friends for life.

Re: LLM=True

#19

Post by ehnto »

thrdbndndn wrote: post #11

Something related to this article, but not related to AI: As someone who loves coding pet projects but is not a software engineer by profession, I find the paradigm of maintaining all these config files and environment variables exhausting, and there seem to be more and more of them for any non-trivial projects. Not only do I find it hard to remember which is which or to locate any specific setting, their mechanisms…

Simplify your tools and build processes to as few as possible, and pick tools with fewer (or no) config files.

It could depend on what you're doing, but if it's not for work the config hell is probably optional.

Re: LLM=True

#20

Post by jen729w »

canto wrote: post #7

This is merely scratching the surface. LLMs (Claude Code in particular) will explicitly create token intensive steps, plans and responses - "just to be sure" - "need to check" - "verify no leftovers", will do git diff even tho not asked for, create python scripts for simple tasks, etc. Absolutely no cache (except the memory which is meh) nor indexing whatsoever. Pro plan for 20 bucks per month is essentially worthles…

And yet when my $100 CC Pro renewed last month my instinctive thought was wow is that all?
Post reply on HN