Please can you link to a video of it being used?

Yes. I will upload after some days

Wow, I wrote a system very similar to the author that seems to becoming the defacto for ground-up multi-agent terminal workflows. git worktrees + tmux + claude hooks

To put an economic spin on this (that no one asked for), this is also the capitalist nirvana. I don't have an immediate citation but from my experience software engineer salary is usually one of the biggest items on a P&L which prevents the capitalist approaching the singularity: limitless profit margin. Obviously this is unachievable but one of the major obstacles to this is in the process of being destablised and disrupted.

in the most profitable / high margin software industry, what other major costs are there?

Sam Altman’s real job is pushing AI hopium on execs who will believe anything in pursuit of that nirvana.

Which is hilarious, because AI is making it easier and easier to bring a good idea to market with much less external financing than usual.

You can argue about security, reliability, and edge cases, but it's not as if human devs have a perfect record there.

Or even a particularly good one.

What are those execs bringing to the table, beyond entitlement and self-belief?

> What are those execs bringing to the table, beyond entitlement and self-belief?

The status quo, which always require an order of magnitude more effort to overcome. There's also a substantial portion of the population that needs well-defined power hierarchies to feel psychologically secure.

I am going to give a predictable rebuttal. Many of these articles come from a place of fear and uncertainty, which is completely understandable. We ascribe value to the things we love, we love coding and therefore coding is valuable. But if it's commoditized how can it be valuable anymore? This alone is enough to shake the tree of rationality and most articles, including this one, set out with a mission of bashing a force they don't really understand. One signature of these articles, as I have noticed, is that they talk about AI writing code fairly reasonably but then insist that without a clear mental view of it, how could it ever be understood, or debugged, or optimised? This simply illuminates the lack of experience with the tools. Anyone who's used Ralph or Taches skills will understand this is a non-problem because well-attuned, AI-first codebases are actually very good at debugging, optimising, and will happily relay to you the model they've used, so that your grey matter can understand it.

Thanks! I agree with you to some extent. I _do_ need to get better with these tools but I remain suspicious for reasons like skill atrophy and the fact that I'm perhaps experienced enough to know how much I don't know. Using AI to plug gaps in my own skillset feels like setting a dangerous precedent on the one hand, but on the other hand, if it works then what's the problem? People just want things that work at the end of the day.

Just to check that I've got it right by the way, are you referring to the Ralph Wiggum loops? And are these Taches? https://github.com/glittercowboy/taches-cc-resources

I'm definitely keen to dive into these tools.

A message that I maybe didn't land in my post is that it is a little bit ridiculous to demand or only deliver "Artisanal Code". It's more labour intensive and the end product is virtually the same at the end of the day.

I appreciate your response, and I will confess to a certain bias as at some point I think I made the leap of acceptance of AI, in the sense of "this is how it's going to be from now on so I better get on board with it".

Spot on. These are the exact tools I was referring to. They seem a little un-magical but the real value is the boilerplate they provide for context management. Essentially allowing coding agents to perform at their beat. For what it's worth, Taches is my tool of choice.

We are optimising for reducing loneliness, remember.

I am of course aware of that.

But reducing loneliness is just a means to an end. My point is that there exist a lot of rewarding things that you can do alone at home, which may give you a hapiness malus because of the loneliness, but also a happiness bonus because you like the activity.

If a solution to reducing loneliness shall be sustainable, it better increases the happiness or rewardingness overall, too. Otherwise you see loneliness as a problem, but see the alternatives as being the worse options, i.e. by rational choice, the loneliness will not be reduced.

You can be happy, well maybe content, but still lonely. It sounds like you're just trying to optimise your happiness, which is fine for you.

Is this your first-hand experience?

This is a bit too "plugged in" for my liking. If I am in line for coffee, it's usually respite away from work, not an opportunity to do more. However, I do love the tmux + worktree + claude setup. I use this now and I know a few peers who do too and it's very enabling. This is what work feels like these days: cycling through agents, each working on a task, checking their work, unblocking them.

this is my workflow as well

This comment is harmfully lazy. Is your position that a three word prompt is equivalent to armchair trolls goi g through the funnel - finding a way to obtain DRM-controlled software, learning that software to sufficient levels to understand the tools required of how to perform something akin to a deep fake, and then somehow gaining the art talent and experience required to put it into practice? Did I just get baited?

What do you mean by "no understanding of the text"?