Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

news.ycombinator.com

Post reply on HN
Print view View original

31–40 of 140 posts

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

#31

Post by nonethewiser »

bad_username wrote: post #27

I use "comment-driven development" by building out the skeleton manually, writing comments instead of code, and letting the agent fill the code in (and then repeat, until done). It is a "lower level" of AI usage, compared say to full-vibe mode, spec-driven development, whatever. But I feel that it's even easier to stay in the flow, because I do not get bored by boilerplate or mundane implementation details. "Higher l…

This sounds good except when you need to cross multiple files. I feel like a significant part of the value of AI is that it can just find things instantly instead of me having to navigate some menu or enter any commands. At least in my experience changing 1 thing requires traversing a large slice.

I guess to take it a step further you could just write everything in a single file with enough context to let the LLM figure out location but this is quite literally just a prompt.

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

#32

Post by nonethewiser »

rushabh wrote: post #26

I try and make very small and deterministic steps. I do the planning (in flow state) and let the model to the execution. When the model is executing, I follow the "thinking" and keep seeing the diff like I would when I was coding.

I never really got into flow state from planning. Too much brain power, dead ends, etc. I reached flow state from the "busy work." Knowing what needed to be built and implementing it.

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

#33

Post by igorzij »

igorzij wrote: post #30

im finding it way way more "flowy" than pre-ai. all the boring trivia is gone, i can focus on what i actually care about - the shape of what i am building, tradeoffs, second- and third-order consequences of decisions. the trick to get it uninterrupted is "selective multitasking". i don't like having too many Claudes / Codexes in parallel on auto-pilot; this way im finding i'm getting _something_ that is perfectly pla…

also forgot to mention that 90% of the work (and time) is bouncing markdown files back and forth until the design is clear and I feel happy about it. design docs, working docs, etc. implementing then is where I can engage way less and switch to a different tab in cmux to drive it

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

#34

Post by andrei_says_ »

kilroy123 wrote: post #22
kranner wrote: post #14

Earlier quoted context omitted.

Meditation teacher Michael Taft recommends "dropping into awake awareness" whenever you're waiting for a response. [1] It's the opposite of watching YouTube, pretty much. [1] https://x.com/OortCloudAtlas/status/2062208343192769004

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, expand presence to everything.

The thinking analytical mind stops, the nonthinking mind activates and softly intensifies.

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

#35

Post by chipsrafferty »

marmarama wrote: post #13

Here's the neat thing: you don't. I've tried, and I feel like I've got closer with faster models, but ultimately the agentic loop excludes you. Even if you're asking the agent to do simple short tasks, it's still: prompt, wait, wait, wait, check, and you never really feel like you're the one in control. The problem with faster models is also that they're more stupid, so that additionally breaks your flow when you hav…

I want something that works in the background, checking my work as I code, running tests and making suggestions... Without being obstrusive. Like a pair programmer.

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

#37

Post by munk-a »

I think if you find that your coding style is disrupting your productivity or job satisfaction then you're misapplying the tool to your particular working style. We're all different in how we approach problems and tools should support our preferred approach (assuming that approach isn't unacceptable from a working performance perspective which, to defeat your imposter syndrome, I absolutely guarantee you isn't the case if your performance hasn't majorly shifted since the introduction of AI).

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

#39

Post by munk-a »

chipsrafferty wrote: post #35
marmarama wrote: post #13

Here's the neat thing: you don't. I've tried, and I feel like I've got closer with faster models, but ultimately the agentic loop excludes you. Even if you're asking the agent to do simple short tasks, it's still: prompt, wait, wait, wait, check, and you never really feel like you're the one in control. The problem with faster models is also that they're more stupid, so that additionally breaks your flow when you hav…

I want something that works in the background, checking my work as I code, running tests and making suggestions... Without being obstrusive. Like a pair programmer.

I've found AI code reviews as a first pass on PRs to be quite non-obstructive to my workflow and the AI code reviewer (while not instantaneous) is certainly faster on a response than the human pass will be.

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

#40

Post by jlos »

(1) Spending time building a plan. I have lots of artifacts like diagrams, tables, web pages that help me think through all the details quickly. Get code snippets to reduce uncertainty, get options for architectural decisions, flesh out assumptions.

Main thing is (1) how do I verify the agent hits the happy path and (2) how can I elicit and clarify assumptions it might make.

Then follow up the build with exploring and refactoring.

(2) prioritized context switching (like playing an RTS) I have several tasks going at once, while one works I hop onto other tasks.

I usually have one or two “core” goals I’m trying to accomplish that take deeper thinking and get priority. The other tasks are smaller and require less thinking.

A lot of times I’ll have the secondary agents build research docs I can review in detail later.

Post reply on HN