Live data from Hacker News

Ask HN: How do you get into a flow state when using AI to code?

news.ycombinator.com

71–80 of 140 posts

Re: Ask HN: How do you get into a flow state when using AI to code?

#72

Earlier quoted context omitted.

Interesting. I still don't get what that means. Ironically, he suggests you just watch his YouTube.

Not sure what the OP or the person in the videos means but a direct, fast way I have found to “drop in” is to stop thinking and intensify my awareness of everything. Takes about 5-10 seconds to transition into a nonthinking timeless presence. Attention is on the full body, and the field of perception, then field of awareness, all at the same time. A bit like shavasana practice, but instead of scanning part by part, e…

Yes this would be one “provisional” method among many, maybe hundreds of techniques but they all seem to lead to the same place as one gets familiar. In Buddhist Vajrayana schools this is called “non-meditation”. The ultimate instruction is to simply do nothing, but this requires a bit of initiation (and paradoxically, concentration) to get right.

Michael Taft has many different guided approaches to this on his channel but there are many other teachers as well, e.g. Adyashanti, Angelo Dillulo, Loch Kelly, Shinzen Young (specifically his Do Nothing and Auto Focus techniques) and expanding the gamut to traditional Vajrayana teachers, Lama Lena, Mingyur Rinpoche, Lama Dawai Gocha, all with accessible online teachings. Also Sayadaw U Tejaniya and Christopher Wallis who are less conventional, so to speak.

Re: Ask HN: How do you get into a flow state when using AI to code?

#73
post #3

Short answer is I don’t and it adversely affects my job satisfaction. I’m quite sure I’ve left money on the table over the years as a result of my reluctance to manage and mentor junior developers. Disappointing that I’ve ended up managing junior AI developers who won’t even grow as a result of the time I’m putting into them.

Oh they'll grow, but mostly to the benefit of someone else.

Re: Ask HN: How do you get into a flow state when using AI to code?

#74

While I don't have the answer, I will leave my thoughts here, maybe my comment helps you or some of the responses might... I was thinking about this when I tried a faster model (Cursor released something fast about a month ago?). It was such a joy to use (well, at least compared to other models, where you wait 5-10 mins for even simpler tasks), and I noticed I felt much closer to the problems, and I got closer to a "…

Yes, and I'm hoping we get there soon. I do much better locked in and focused on one thing. I HATE multitasking. I feel like using AI is:

a) making me not think at all

b) giving me weird adhd brain (I never struggled before with this)

Re: Ask HN: How do you get into a flow state when using AI to code?

#75
You need to saturate your attention span with running so many agents at once that when you issue the last prompt to the last agent, the first one is already finished. This way you need to continuously concentrate, so flow is achievable.

The difficulty is to break down the task in a way that multiple agents can work on it.

I usually spin two or three major issues with 10-12 agents in total.

Re: Ask HN: How do you get into a flow state when using AI to code?

#76
I genuinely have a lot of fun coding with AI, possibly more than I used to have coding normally. It’s true that I don’t spend hours on a single problem any more, but I instead spend a lot of time thinking and researching higher level issues like architecture and design. I find this work to be very rewarding because I very much enjoy learning new things. I don’t know if I would call it a flow state in the same way that coding was a flow state, but I definitely have a lot of fun learning. For instance, yesterday I was learning a lot about AWS infra, which I found very enjoyable. Before that I was learning about Fly Sprites, which it turns out are a little broken, but it was still interesting to learn about them. Pre-AI I think coding was slow enough that I would be able to learn a new thing like this once every couple of weeks, because then you'd have to go spend a ton of time on the implementation work. Now the implementation work has compressed and I get to learn new things more often, which is fun.

When I send one agent off to do work I usually begin thinking about some other unrelated problem I also want done, and then I try to spin up a parallel agent to do that as well. The thinking itself is where a lot of the deep work happens for me IMO. I probably spend like 80% of my time thinking, researching and reviewing plans. The other 20% is actually promoting.

I see a lot of people saying that agents trivialize work now - like you just push a button and an answer comes out. This is so far from my experience I actually don’t know how to bridge the gap. If you are not spending a lot of time researching you are likely going to be asking the agent to do things that don’t really make sense.

Re: Ask HN: How do you get into a flow state when using AI to code?

#77
I have converged on a workflow that is just what I was doing before, but use LLMs just for boring or tedios parts. General guidelines are: only single agent at a time, small targeted queries, understand what you are building, if something would seem like a fun task, do it yourself. I use LLMs for bug hunting, to trace the flow, to build quick visualizatios (paste csv, ask to generate visualization), to search in the code of the dependencies using github mcp, to write 100 line scripts (deno + ts + zx was a game changer for me). Even "dumber" opensource models are good for this kind workflow, more tokens per second is generally more benefitial than plain intelligence. I would use LLMs more or less, sometimes even full vibecoding if the task is something like quick tooling web app and the flow is just firing of the next LLM query every 30 seconds. But, depending on the type of task or domain that you work in, YMMV

Re: Ask HN: How do you get into a flow state when using AI to code?

#78
I know it isn't the original flow state but I get lost in conversations with Claude even when slow.

I have a couple of terminals open and work on at max 3 things.

A main task, an exploration task and another prompt/skill improvement or documenting an issue (or a proposal)

Re: Ask HN: How do you get into a flow state when using AI to code?

#80
Flow comes from continuous engagement with the problem. Agentic coding often turns programming into project management.

The more time I spend waiting for an AI to think, the less flow I experience. Fast autocomplete-style AI boosts flow. Slow autonomous agents usually break it.

My workaround is to stay in the loop: AI handles the typing, I handle the thinking.

Post reply on HN