When I'm using genai to write some code for me, I lose the internal mental state of what my code is doing.
As such, when I do have to debug problems myself, or dream up ideas of improvements, I no longer can do this properly due to lack of internal mental state.
Wonder how people who have used genai coding successfully get around this?
I use Claude and there's a couple things I'd suggest.
1) You need to be the boss with the AI being your assistant. You are now a project manager coming up with strict requirements of what you'd like done. Your developer (AI) needs context, constraints and needs to be told exactly what you'd like created without necessarily diving into the technical details.
2) Planning - you need to have a high level plan of roughly how you'd like to structure your code. Think of it like you're drawing the outline and AI is filling in the gaps.
3) Separation of concerns - use software principles to drive your code design. Break problems down into separate components, AI is good at filling in components that are well defined.
Once you change your thinking to a higher level, then you can maintain flow state. Of course the AI isn't perfect and will make mistakes - you do need to question it as you go. The more creative you become with a solution the harder time the AI will have and sometimes you'll have to break out and fix things up yourself.
Go over the code again and again like you would if you'd written it yourself. Keep iterating on the code yourself without having the AI generate everything. In a current project I have everything internalised because I'm constantly going through the code and improving upon it myself (and using the AI to do boilerplate), even though much of it was initially generated. I'll still have the AI generate code in plenty of places, but I don't let it take over the thinking for me unless I'm unsure about something, then I ask it for possible solutions and ideas, then I go over those solutions myself.
Focus on one side project and one side project only - I think the concept of trying to create 12 products in 12 months is probably counterproductive (for me)
the latter is definitely the long term vision. Today we do capture the elements, but do some sort of 'automated' (tree traversal) to produce the video. Would definitely love to give future users even more fine grained control
let's definitely give it a try :) what's ur app name, I'll build a demo of it and send it over (also feel free to email me the app name at hello@minidemo.app instead)
I have this exact problem! About a year ago I built https://fetcher.page which fetches updates for me every 10 minutes or so, filters the ones I've already seen, and then notifies me of new updates.
It's not perfect, but at least I thought reopen 5 websites like 50 times a day.
I rebranded it as a social listening platform a couple months ago, but one can still use it for its initial purpose. Let me know if you find this useful, can grant free access.
Slightly tangential, but here's a viz of how sprawled out London's bus network is https://youtu.be/xAnCD_Czwxw?t=648. Quite amazing how well the bus system works.
Even more tangential, but setting up a truly proper bus system in Cities XL is usually the task the runs me into a brick wall and leads me to stepping away from the game for a bit.
Makes me all the more in awe of London's bus network despite the occasional tardiness.
I've not played Cities, but interested to know the usual stumbling blocks to build such a system. Too large a city to cover, and too expensive to cover extensively?
It's funny because I believe if a person was to study my gameplay in Cities XL and then also watch me function throughout a day, they would find very clear similarities in my frantic disorganization in general.
I believe, probably, it is mostly a 'me' problem. Maybe not, though. I just find it incredibly overwhelming when you get to the point where your citizens are demanding bus stops everywhere. There is already such a massive, established road network at that point and I have no idea where to begin. The funds are not an issue at that point (usually) because the city is large enough that money is kind of rolling in. It is more just the size of the city. It will need A LOT of bus stops, which makes sense... so I guess it is more just the overwhelming nature of the task.
Would it perhaps make more sense and be much less overwhelming if I were to be placing at least some bus stops as I progress through the earlier half of the game? Of course it would. Now, there are times where it wouldn't be as economically feasible, of course. Money flows much more freely in the later game, I have noticed. But, it would definitely ease the burden later in the game as far as having such a large city to cover. Then there is the question of 'is this bus stop too close/too far from the last one?'
I think it is really just the scale at which I have to place them and lack of preparation on my part (which is my life in general with pretty terrible ADHD).
Highly suggest giving that game a try, though. It's pretty incredible.
What you need to do is get over the intuition that a transit network is supposed to be random access and point to point. Its not. Some places are more important and more likely than others. Don't fall for the trap of compulsively filling in lines until there's spaghetti everywhere and everything that could meet at the ends does. Have core structures, basic sorts of routes. Be neither radial nor mesh, but rather federated with ample chances to make transfers. Think of it as a plumbing problem. Your primary people flow is between cheap rent and good jobs. Other people flows exists, but its ok to use smaller pipes on that.
> Think of it as a plumbing problem. Your primary people flow is between cheap rent and good jobs.
That's an interesting idea. Just thinking out loud, I wonder how one affects the other. I.e cheap rent -> create better transport links -> increased rent -> etc etc.
I know this is true with tube stations raising the cost of certain areas in London.
As such, when I do have to debug problems myself, or dream up ideas of improvements, I no longer can do this properly due to lack of internal mental state.
Wonder how people who have used genai coding successfully get around this?