> It's so sad that we're the ones who have to tell the agent how to improve by extending agent.md or whatever.
Your improvement is someone else's code smell. There's no absolute right or wrong way to write code, and that's coming from someone who definitely thinks there's a right way. But it's my right way.
Anyway, I don't know why you'd expect it to write code the way you like after it's been trained on the whole of the Internet & the the RLHF labelers' preferences and the reward model.
Putting some words in AGENTS.md hardly seems like the most annoying thing.
tip: Add a /fix command that tells it to fix $1 and then update AGENTS.md with the text that'd stop it from making that mistake in the future. Use your nearest LLM to tweak that prompt. It's a good timesaver.
[Edit: I may have been replying to another comment in my head as now I re-read it and I'm not sure I've said the same thing as you have. Oh well.]
I agree. This is how I see it too. It's more like a shortcut to an end result that's very similar (or much better) than I would've reached through typing it myself.
The other day I did realise that I'm using my experience to steer it away from bad decisions a lot more than I noticed. It feels like it does all the real work, but I have to remember it's my/our (decades of) experience writing code playing a part also.
I'm genuinely confused when people come in at this point and say that it's impossible to do this and produce good output and end results.
The problem with replying to the proof-demanders is that they'll always pick it apart and find some reason it doesn't fit their definition. You must be familiar with that at this point.
> This often comes up in discussions about jargon. Jargon is a way to increase the density of communication. This is often perceived as a loss of clarity, but the question again is, clarity for who? For two experts, discussing complex things in their field of expertise, jargon can increase clarity, by referring to shared context. Higher bandwidth communication allows for more discussion of more complex topics, because you're not wasting time and mental energy re-explaining things from first principles.
> Put another way, there is always some shared context going on; that's what language actually is in the first place. I have used a number of words in writing this comment, but I haven't set out any definitions; that's because I'm assuming that you know English in order to read my comment. If I were trying to communicate to a child, I wouldn't be using all of the words that I'm using here, because it is too complicated for them to comprehend. But, trying to explain the topic of this comment to that child would take much longer, and be much more difficult.
Thanks for this. I always struggle to articulate it.