[dead]
LLM=True
41–50 of 155 posts
Re: LLM=True
#42could 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.
That would achieve 1 of the 3 wins.
If you use a smaller model for the sub agent you get all three
Of course you can combine both approaches for even greater gains. But Claude Code and like five alternatives gaining an efficient tool-calling paradigm where console output is interpreted by Haiku instead of Opus seems like a much quicker win than adding an LLM env flag to every cli tool under the sun
Re: LLM=True
#43Something 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…
> 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
Then don’t.
> How do you deal with this better, my fellow professionals?
By not doing it.
Look, it’s your project. Why are you frustrating yourself? What you do is you set up your environment, your configuration, what you need/understand/prefer and that’s it. You’ll find out what those are as you go along. If you need, document each line as you add it. Don’t complicate it.
Re: LLM=True
#44Earlier quoted context omitted.
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.
Right, and then when you don't work on it for 6 or 12 months, you come back and find that now you don't understand it either.
Part of doing it well is adding comments as you add options. When I used vim, every line or block in the config had an accompanying comment explaining what it did, except if the config’s name was so obvious that a comment would just repeat it.
Re: LLM=True
#45So frequently beginners in linux command lines complain about the irregularity or redundance in command line tool conventions (sometimes actual command parameters -h --help or /h ? other times: man vs info; etc...) When the first transformers that did more than poetry or rough translation appeared everybody noticed their flaws, but I observed that a dumb enough (or smart enough to be dangerous?) LLM could be useful i…
Ah yes, the vaunted ffmpeg-llm --"take these jpegs and turn them into an mp4 and use music.mp3 as the soundtrack" command.
Re: LLM=True
#46We’ve got a long way to go in optimising our environments for these models. Our perception of a terminal is much closer to feeding a video into Gemini than reading a textbook of logs. But we don’t make that ax affordance at the moment.
I wrote a small game for my dev team to experience what it’s like interacting through these painful interfaces over the summer www.youareanagent.app
Jump to the agentic coding level or the mcp level to experience true frustration (call it empathy). I also wrote up a lot more thinking here www.robkopel.me/field-notes/ax-agent-experience/
Re: LLM=True
#47Also an acceptable solution - create a "runner" subagent on a cheap model, that's tasked with running a command and relaying the important parts to the main agent.
Re: LLM=True
#48Huh. I've noticed CC running build or test steps piped into greps, to cull useless chatter. It did this all by itself, without my explicit instructions. Also, I just restart when the context window starts filling up. Small focused changes work better anyway IMO than single god-prompts that try do do everything but eventually exceed context and capability...
[dead]
Re: LLM=True
#49Can we just instruct the agents to redirect output streams to files, and then use grep to retrieve the necessary lines?
Re: LLM=True
#50This 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?
That can be read in two ways:
1) It's only $100, well worth the money.
2) Surprisingly little value was provide for all that money.