robbyrussell, creator of oh-my-zsh?

1. thank you for omz, it's great

2. how is it possible you've been on HN for over 15 years and have just 254 karma?

Lurkers abound.

> "My ideal software has a well designed and thought through user interface for the primary interactions, allowing me to think about the goal I'm trying to achieve"

Yes, this is the crux of the whole discussion. The paradigm is called "Intent-based UX".

You'll want to strongly consider rebranding with a different name. Way too easily confused.

It's not impossible (and I'd substitute "evolved" for "designed").

Yes, wanting "More" [time, money, love, status] is pretty firmly ingrained as an advantageous trait. But you can override your instincts (e.g. declining a drink when thirsty, if you learn the glass of water contains poison). And it is possible to learn to want what you already have.

How? Practice three things: Compassion, Attention, and Gratitude. (Pick any two, and the third will follow almost automatically.)

That's the central thesis of an excellent book, "How to Want What You Have" by Dr Timothy Miller. It changed my life.

The title of that book is marvelous and packs a lot into just 6 words.

Split the difference and say “designed by evolution?” I think designed captures something important and doesn’t have to imply a non-materialist view.

"Let's eat, grandma!" vs "Let's eat grandma!"

You might be interested in smolvm microvms from https://smolmachines.com - which (unlike Docker) provide kernel-level isolation (among other benefits). No affiliation, just a happy user.

I'm not the person you replied to, but your response misses their point: rollout issue aside, the approach is flawed by design. The feature author didn't address that at all.

The person had something else before they edited. They were overly negative, saying (from my memory) that it was inexcusable, and they had enough, pointing to malice.

The response as it is now sounds fair. Before that it was not.

Ah, thanks for clarifying. (And shame on the GP.)

My only edit was to continue refuting at the beginning of the sentence that Claude Code's use of remote control to control agent.md is still incorrect. The rest is identical to the original, and my attitude before and after has not changed.

As for whatever "had enough" he mentioned, I'm not sure whether he said it on purpose or genuinely misremembered.

Since that's how he remembers it, so be it. I can't be bothered to explain anymore.

I must have misremembered. I wish you kept the original though.

Because "Even if this was an honest rollout mistake" this is a new addition, changes meaning quite a bit.

I disagree with what you wrote now partially (your comment on claude), but it does sound fair, and i wouldn't have written what i wrote.

With apologies for not just testing this myself (currently AFK), doesn't it still work to have a CLAUDE.md file containing just `@AGENTS.md`?

Such a society would pay a whole lot more attention to white-collar financial and environmental crimes than to anything all the motivated junkies in the country could wreak.

> "Codex's compaction is very good, fwiw, but it happens so frequently that..."

I appreciate and follow Matt Pocock's advice: avoid autocompaction. Compaction is lossy, which is ok when you're managing it at phase boundaries, but autocompact is lossy at the most inopportune times, firing mid-task and leading to agents going off the rails.

Bad advice, compaction is why Codex is so fantastic.

My conversations compact hundreds of times. By the time it has done a dozen or so compactions, it fully understands the work I want it to do (and how). It's almost like having a fine-tuned Astra model.

10/10, would recommend.

I'm not sure I follow; how is autocompaction (lossy summarization), applied at random times (vs strategically, between workflow phases), helpful to ensuring clarity of intent? Maybe you're saying that just plowing ahead and living with the signal loss along the way works well enough for your purposes. In which case, ok, YMMV, different strokes.... but paying attention to context quality and being deliberate about when to compact vs handoff vs delegate to subagents is most definitely not "bad advice".

I agree with @erichocean on this. In theory, compaction is bad. But in practice I found the model is smart enough to write critical details down somewhere, and post-compaction the model doesn't make assumptions. A small amount of time is lost reading materials, but the benefit is that you can operate unbounded vs doing small controlled chunks, which is what I used to do with Opus back in the day. Now I just give it as big a task as I can think of.

This approach got good with Sol. With 5.5 I'd break tasks up, record planning docs, etc.

Now with Sol I rarely bother. It's really good at remembering the salient details. Its also great at continuing a pattern I setup, like commit after finishing each feature block, etc.

not my experience at all. compaction during a task is fatal since you lose all of the details of edits and progress halfway through. compacting after task completion is fine though.