I've been testing using AI coding agents by asking an AI acting as a software designer to build a set of kanban style cards as .md files in a directory, designing the work we talked about into cards for AI developers.
It works quite well, and then you can review the cards (as files) and then ask another AI agent running as whatever role is suitable for that card, to pick up the card by name and do the work.
But there is no kanban board, it's just .md files in a folder.
I am continuing to test this, as transfer of context between AI sessions is an interesting challenge, and leveraging md files as if they are kanban / agile style cards, is interesting.
But degrading an other is ok? From the very beginning tech was about making jobs easier, and now it’s easier to make jobs easier, including our own. So I think it’s ethically consistent to be happy about both, even if our own jobs are at risk.
My rational as to why this is a good thing in general was and remains a focus on generating consumer surplus, it’s this surplus which we as a people derive our wealth. The hope was that the surplus would be sufficient to cover the loss of those that lost their jobs, either in wealth redistribution or in new opportunities.
What’s different this time is productivity increases are not being met with an increase in demand. This will drastically increase inequality and to a lesser extent civil unrest, and I think both are destructive. I think financialization of the economy did greater damage, and the combination of both is going to really suck. I would prefer we keep productivity improvements and reverse the financialization even if that means pensions are decimated - they are probably going to be decimated anyway. Better to do it in a way that causes less damage.
AI is just a tool, it's no more useful than a non-complaining junior dev that constantly needs direction, but it sure can cut out a lot of repetitive work.
I am more productive using it, but that is just me.
I use ai myself as stack exchange but this sentiment is extremely common on HN where you have people trying to force ai to do things it's clearly shit for. Not to mention the rust your brain gathers by not doing these little 'mundane' things. LLMS are a useless dead end anyway all these billion dollar corpos building over it, even worse hype than crypto.
Without making generalisations, I'm trying to leverage LLM as much as possible to see how they can help.
I know there is a lot of hype about LLM's and I'm genuinely interested in the niches that they can fill, and where they definitely shouldn't be involved in the software development process.
I would say I'm an expert level programmer in the small field that I work in, and have set up development teams in the past.
I think that is an advantage to working with integrating LLMs into a dev cycle as I have experience in providing structure with developers, something that LLMs 100% require, without a shred of doubt.
As the capability of LLMs continues to grow, having some framework around where they are 'almost good enough' will help re-evalutate them as they improve.
I'm not trying to prove anything to anyone else, just build a reference point for where we are now.
It works quite well, and then you can review the cards (as files) and then ask another AI agent running as whatever role is suitable for that card, to pick up the card by name and do the work.
But there is no kanban board, it's just .md files in a folder.
I am continuing to test this, as transfer of context between AI sessions is an interesting challenge, and leveraging md files as if they are kanban / agile style cards, is interesting.