Live data from Hacker News

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

news.ycombinator.com

81–90 of 140 posts

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

#82
post #63

What works for me is: - Use a fast model like DeepSeek Flash V4 on high (it's Sonnet level, but fast and cheap). - While the LLM is working, start writting your next prompt. A good prompt usually takes between 1 and 10 minutes to write anyway. Doing this should keep you busy enough to never leave flow. But it is intense and demanding when the LLM is fast, I'll tell you that.

How does that work if you depend on the output of the first prompt?

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

#83
Why would you try?

Just give it a zillion linters - including ones you wrote yourself - and make it write its own tests (red/green) so it doesn’t need to stop until it’s made working software with nothing dumb in it.

Then get into a flow state when you write your weekly update emails and respond to customers.

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

#86

Do something better with your life. Honestly, not /s. Your brain is trying to tell you something.

When I'm running for exercise, my brain is telling me to stop running, would it be better for me long-term to stop running or continue, regardless of what that pesky voice is telling me?

I don't know, I get runner's high and want to go running again a couple of days later.

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

#87

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 feel like I'm missing a mode that works more like a pair programmer. Perhaps a multimodal model that can talk to you about what you're writing, as you write it, and offer suggestions rather than trying to take over and do everything for you.

This is exactly what I have also been thinking and wanting for a while now. A realtime agent that I can share a screen and mouse / keyboard with. and we can just work together at times. I think it will probably come at some point but we might be a few years away from it.

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

#88
post #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 tha…

Exactly my experience.

Literally every task/feature now involves me learning or thinking through an architecture. I enjoy it because that was always my favorite part pre ai thinking through and designing the system.

It is actually more mentally taxing I think because now all I do is work through complex architectures and thr fact that code comes near instant means the scale and volume at designing the architecture is 10x now.

Top models are so good at not messing up code whenever there's lots of bugs it actually means my design and testing methodology was poor which is also a much harder problem.

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

#89
Assuming you're like me and flow means learning interesting things and being engaged with the results...

Run tons of experiments. Turn yourself into a researcher. If you don't have a constant interface to the latest interesting experiment results to engage with/learn novel things/see novel solutions, you aren't running enough experiments.

Running an experiment means you don't already know the result, and you've looked at the prior art so you are doing genuinely new things. Establishing this prerequisite is completely trivial with modern agents.

Hopefully the answer is interesting and impactful enough that it will be useful in your work. This is honestly easier than it sounds; if you're a smart person working in a field where people are willing to pay money for impactful results, you can do this.

Anything that's not running experiments -- including debugging -- is grunt work that you should automate away, and you increasingly can if you set up your harnesses correctly. Make a pipeline so that the novel results of your experiments are polished, packaged, and shipped by your agents. How to do this obviously varies by domain but it's increasingly possible for most things.

And if your job is not doing the above, I have bad news for you: your job is going away fast. So you might want to set up a day on the weekend to give this approach a try; it'll be good for your flow and your career.

Post reply on HN