Open 16 windows, that's the flow state, non-stop bot mode.
Ask HN: How do you get into a flow state when using AI to code?
91–100 of 140 posts
Re: Ask HN: How do you get into a flow state when using AI to code?
#92A couple of things to consider:
Start with a set of work that's well specified and reasonably chunked to sizes that make it so that the review parts fit in the gaps of the working chunk and interleave (1-4 tasks of this). While the agent is working on the A task, you're reading the B task, only add a 3rd task if you're waiting on the agent excessively. Give yourself some slack on this to think about side quests (maintenance / tech debt / planning future work to your system etc.)
Make sure the handoffs are reasonably detailed (prompts / AGENTS.md instructions) - make your agents provide more context than normal - make them assume that you don't read all the text they spit out and need to be handed succinct summaries with information that helps reduce cognitive burdens (what I was doing, how I did it, what's next etc.)
It's reasonable to regularly ask the agent what things you've worked on choices made, options considered and discarded, context rehydrating. There's a lot of small tweaks you do when interactive prompting that get lost in a drift rather than captured as a neat single list. Make the agent help track that stuff. (at least prior to shipping, but often in intermediate steps.
Write flows that keep software in a buildable state so you can run it and queue up changes based on what you see. Avoid long periods of broken refactoring (caller code written before callee, deletion before add in a move etc.) Run quick checks (e.g. rust's cargo check) after each change, not at the end.
Correction of agent errors should end up as future steering. If the agent makes a mistake once it's the agents fault, twice it's your fault.
Leave time to stop and evaluate the current state regularly (where are we on the work). It's easy to mistake momentum for progress when you're the human part of an agentic loop.
Re: Ask HN: How do you get into a flow state when using AI to code?
#93My experience has been that I can't.
I've just started up a new gig where I'm swearing off any agents, I'm even not looking up answers with an LLM. There's nothing so crazy I'm doing SO still doesn't have the answer.
So far, I'm having a great time. I'm progressing quickly, understanding the domain better.
I'm also finishing an older job at the moment, which has been almost 100 percent agent-driven. Real brain-dead drudge work, there's no flow to get into with these things. I'm not sure it's been any quicker than the old-fashioned way. Certainly a lot less fun.
Re: Ask HN: How do you get into a flow state when using AI to code?
#94(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 an…
I can't believe "prioritise context switching" is now advice being doled out on HN.
Re: Ask HN: How do you get into a flow state when using AI to code?
#95I like to bounce around between a few different things at once.
Normally, I work on my core work plus something tangentially related (e.g. 20% projects). The 20% projects keep my attention while the core work is LLM'ing.
Re: Ask HN: How do you get into a flow state when using AI to code?
#96ctrl-f Csikszentmihalyi ... nothing.
Flow = high talent/skill + high challenge
It's hard as yet for me to feel skilled in interacting with AI agents when coding, and the challenges I face are more interaction with agents, and less around the object of the coding.
Today I fall more into:
Anxiety (high challenge level, low skill level) Arousal (high challenge level, medium skill level)
Re: Ask HN: How do you get into a flow state when using AI to code?
#97Read the blog posts from Peter Steinberget blog steipete.me about his setup. Many AI builders converged on using the terminal with multiple panes. When a prompt is running if you don't have anything to do add another pane and start another prompt. Little by little you might have 1-6 prompts in parallel at some point. The flow state with AI is managing productively several prompts in parallel.
It's interesting that the guy providing an actual answer gets downvoted, and everyone saying "it's impossible" got upvoted.
In my experience switching contexts breaks flow
I don't believe that multi tasking and flow can happen at the same time
Re: Ask HN: How do you get into a flow state when using AI to code?
#98at least four entirely separate trains of though works for me!
git worktrees and sidequests
Re: Ask HN: How do you get into a flow state when using AI to code?
#99The planning part is the flow state now. Coding is done by AI while I eat and set the domain vision
Re: Ask HN: How do you get into a flow state when using AI to code?
#100You can't, "agents" and "agentic coding" are incompatible with the deep understanding of your code that getting into the flow state requires. By definition, prompting a tool to do your job for you means giving up the depth of control that comes with actually writing the code.
Some people can work like that, some very few people may even produce acceptable results like that. I cannot and I am not interested in doing so.
The closest you can get to agentic coding while still actually being in the control loop is something like intellisense - where it just fills out the implementation of small chunks of code, one block at a time and only when you specifically request it.