For me the best part about AI is that when I'm feeling lazy, I can tell the AI to do it. Whether it gives me gold or gives me shit, it doesn't matter, because I have now started my work.
It's the white page problem, that LLMs solve handily. Instead of facing the daunting task of building back up a complex mental model, I can ask the machine "yo, what were we doing? what's this thing? ok, how about you give it a spin and show me" and all of the sudden I'm back in it and can get cracking. That, and rubber ducking, and speeding up yak shaving to the nth degree really make this thing very useful to me. I also have various data sources hooked up (slack, notion, linear) so it's also a task management and project management tool for me.
Re: the "white page problem", that is just known as motivation inertia. You can overcome it by training yourself to agree with yourself to "just do it" for 5 minutes, even if you really, really don't want to. If you're still demotivated after that, fine. But 9 out of 10 times, once you've started, it's surprisingly easy to keep the momentum up. This is also great for going to the gym or cleaning up your home, where an LLM can't come to the rescue :)
Re: usage of LLMs, that is honestly the way I like to use LLMs. That and auto-complete.
It's great for creating a bird's-eye view of a project because that is very fuzzy and no granular details are needed yet. And it's great at being fancy autocomplete, with its stochastic bones. But the middle part where all the complexity and edge cases are is where LLMs still fail a lot. I shudder for the teams that have to PR review devs that jubilantly declare they have "5x'ed" their output with LLMs, senior or not.
What is even more worrisome is that the brain is a muscle. We have to exercise it with thinking, hence why puzzlers stay sharp at old age. The more you outsource your code (or creative writing) thinking, the worse you get at it, and the more your brain atrophies. You're already seeing it with Claude Code, where devs panic when they hit the limit because they just might have to code unassisted.
Maybe there is a reason why is your brain hesitating (e.g. low energy) and pushing it with LLMs would blow it up at some point in the future if the cause was not fixed in the meantime? Covid showed me (in a very accentuated way) that many of the times I was procrastinating was instead brain throttling due to low energy, protecting itself.
I think for me the hesitation is in that to get started on task XYZ, the first step is often some extremely boring task ABC that is only tangentially related to the "real" task.
For example, the other day I needed to find which hook to use in a 2300 loc file of hooks. AI found me the hook in 5 seconds and showed me how to use it. This is a pure win - now that I have the name of the hook I can go read it in 30 seconds and verify it's what I wanted. If it's not, I can ask again. There's zero risk here.
I thought this as well, but I just got burned in a way that caused me to lose so much time: I was feeling lazy and allowed AI to write some code for me. It looked good and compiled so I committed and pushed it. Weeks later I experienced a crash that I couldn't pinpoint. After hours of debugging, I eventually realized the culprit was that bit of code created by AI from weeks ago; it used a function that was defined in my code in a way that wasn't intended, causing a panic sometimes and weird off-by-one errors other times. The offending function was only a few lines of code. Had I not been lazy and just took 10 minutes to write it, I would have saved myself a whole afternoon of frustrating debugging.
Lesson learned: being lazy with AI has a hidden cost.
At the end of the day when I'd be thrashing or reverting as much as I write, I can let Jesus take the wheel for a bit to refresh.
On small issues it's usually just a glance over the diff, on harder issues it's not challenging to scold it into a good path once something starts coming together, as long as it's a localized edit with a problem I understand. I'll often take over when it's 40-60% there, which is only possible b/c it does a good job of following todo lists.
I've moved into a good daily workflow that emphasizes my own crafting during the times I'm sharp like mornings, and lets AI do the overtime and grunt work while I prepare for tomorrow or do more thoughtful writing and design.
So glad I've found someone else who has this workflow.
I spend probably 70% of my active coding time coding. The rest is using LLMs to keep making progress but give my brain a bit of a break while I recharge, being more supervisory with what's happening, and then taking over if necessary or after the 10-15 minutes it takes for me to start caring again.
Even if I want to do it myself, I'll ask it to write it a plan and toss it in a markdown file.
It gave me a shit plan today. Basically I asked it to refactor a block of prototype code that consisted of 40 files or so. It went the wrong way and tried to demolish it from the bottom up instead of making it 100% backwards compatible. If it made a mistake we would have taken forever to debug it.
But yeah, it gave me something to attack. And the plan was fixed within an hour. If I tried to make one myself, I would have frozen from the complexity or gone in circles documenting it.
I've had great success using AI to translate my thoughts into actual words on a page (not just for software development, but also amateur writing). Bridging the vocabulary gap.
Yes, it helps a lot overcome that initial momentum. I also find it helps at the end of the day when I’m tired. I can just tell it to do the work a little bit at a time and review/fix the output. Takes less out of me.
When you say progress, I wonder at what cost. The apparatus for original thought isn't used and pushing through a problem and deriving the satisfaction of doing that doesn't happen. That leads to the wrong motivational cues. The brain is lazy and likes to take the easy route. Eventually you become merely a machine operator, which is something a lot of my colleagues are starting to do. And it's very worrying.
The biased behaviour towards just asking for a solution both devalues you and leads to any innovative outcomes disappearing before they had a chance to exist.
I've ended up being the company ideas man not because I'm good but everyone else stopped thinking.
> So, a boring task - off to the LLM you go - interesting - it’s mine, all mine!
Yes! And hell, checking out how the machine solved a boring thing can still be a source of interest in itself, so the dopamine squeezing novelty keeps on flowing all day long.
The only time I ever wrote a program on paper was when I was 10 years old, a few months before my 11th birthday when I got my first computer. And that was in the late 1970s.
I agree and this is a risk. There is a balance to be found where the AI is power tool, not a black box.
The best use cases for me have been when I know the solution and what it should look like but don't want to write it all by hand myself. The AI can make the code just appear and I can verify it is up to spec.
People most likely pay you to do valuable work, not quality work. One doesn’t necessarily mean the other.
If your coworkers can get into the groove faster than you (for whatever reason), you’ll continue to do quality work, not look busy, and no longer be paid for it.
Looking at my salary, which is at least twice as much as my coworkers in the past 15 years at various companies, because I ship quality solutions, companies seem to think that quality is quite valuable.
No you don't understand, this person writes quality code in an intellectually honest way because they use machines in a very specific way, just enough but not too much. Everyone else is just slinging shitcode. Good luck finding someone as good as this random person online you've never heard of!
I don't mean to attack this person specifically but it's a frankly pretty bad mindset that is far too prevalent in our profession - the way I do things in the Right Way, I write Good Code, very few other people write Good Code, and because I do things the way they were done 5, 10, 25 years ago means that my way is better than yours.
