Completely agree. LLMs are amazing for side projects.
The other place they are amazing is in working with legacy code bases. I mean, the kind the dev team always wants to throw away. First, even if you do want to throw it away, you can first find out what it does and realize it does more than you think it does. You can also create integrations to more modern components which can be used to extend it. You can also create a pretty decent test suite if you do not have one. And, once the behaviour has good test coverage, you can re-write it into something more modern. You can even completely change the architecture while ensuring compatible external behaviour. Remember, this is all in place of “throw it away and start over from scratch, only to discover that the scope is much larger than expected”.
You could already do all of that. Like, none of that is infeasible to achieve on a scale of weeks in most cases.
It’ll still take weeks with AI in the picture, but for some reason management is more willing to plan it when they also have the additional token bills to pay.
It was often not organizationally feasible because you needed permission to spend those weeks up front, instead of working on something else, just to get to where you knew enough to give approval to finish the work.
Now, you can make enough progress with one developer’s quiet afternoon to be confident and finishing the work also takes less time.
The technical grasp of the legacy codebase was a factor, but often not the largest.
I’m so burnt out by being swapped with so much work from AI at my day job that I don’t even want to look at anything with a screen when I’m off anymore.
I despise AI but the thought of doing something the “old way” just makes me wince at how long it would take me to do anything that would take minutes with agents that I despise.
There's this joke like "I used to have 5 unfinished side projects, but AI changed everything. Now I have 30 unfinished side projects". And in my case it's not even a joke
Well ai made it extremely easy to finish things. Projects are usually left unfinished because the last mile is filled with boring and tedious tasks we do not like to do. AI loves those tasks. I have finished everything I bothered to, most of the time I still wrote stuff by hand, the AI just fixed tests for me (usually OS specific stuff that I can’t test locally which is a pain), told me what I was doing wrong so it was trivial for me to fix it, and checked my documentation which invariably got out of date.
I've definitely found that while "AI makes getting from 0-80 done much easier than the 80-100" holds true, it is much easier to get my work to a quality bar that I'm excited to share with my peers...
The definition of "finished" has changed for me also.
More and more, I am using half finished as a polished product, but pragmatically very useful software I have built myself.
More importantly, I see no reason to polish this into a product. It is more useful in this half finished, easily moldable state.
Like it use to make sense to bake the clay and sell the hardened output but now I want to keep the soft clay so it can be molded to my changing needs. I keep adding to a collection of these moldable states.
It's always been easier to start a project than finish it, and LLMs make starting a project roughly free. I'm not sure they change how much work it is to finish it all that much.
I mean, I have finished more side projects than before. So they do change it. Just not as dramatically.
Of course you can. LLMs take you from 0 to 80 instantly. They are then completely incapable of getting from 80 to 100 and making something worth shipping to production. They are the ultimate unfinished side project generator.
It is great. I just had claude yolo a human in the loop image segmentation pipeline last night. It cut weeks of work down to an evening like 4h. Segment Anything 3.1 + Napari final touch.
Completely agree. LLMs are amazing for side projects.
The other place they are amazing is in working with legacy code bases. I mean, the kind the dev team always wants to throw away. First, even if you do want to throw it away, you can first find out what it does and realize it does more than you think it does. You can also create integrations to more modern components which can be used to extend it. You can also create a pretty decent test suite if you do not have one. And, once the behaviour has good test coverage, you can re-write it into something more modern. You can even completely change the architecture while ensuring compatible external behaviour. Remember, this is all in place of “throw it away and start over from scratch, only to discover that the scope is much larger than expected”.
You could already do all of that. Like, none of that is infeasible to achieve on a scale of weeks in most cases.
It’ll still take weeks with AI in the picture, but for some reason management is more willing to plan it when they also have the additional token bills to pay.
It was often not organizationally feasible because you needed permission to spend those weeks up front, instead of working on something else, just to get to where you knew enough to give approval to finish the work.
Now, you can make enough progress with one developer’s quiet afternoon to be confident and finishing the work also takes less time.
The technical grasp of the legacy codebase was a factor, but often not the largest.
I’m so burnt out by being swapped with so much work from AI at my day job that I don’t even want to look at anything with a screen when I’m off anymore.
I despise AI but the thought of doing something the “old way” just makes me wince at how long it would take me to do anything that would take minutes with agents that I despise.
I touch grass whenever I can now.
There's this joke like "I used to have 5 unfinished side projects, but AI changed everything. Now I have 30 unfinished side projects". And in my case it's not even a joke
Well ai made it extremely easy to finish things. Projects are usually left unfinished because the last mile is filled with boring and tedious tasks we do not like to do. AI loves those tasks. I have finished everything I bothered to, most of the time I still wrote stuff by hand, the AI just fixed tests for me (usually OS specific stuff that I can’t test locally which is a pain), told me what I was doing wrong so it was trivial for me to fix it, and checked my documentation which invariably got out of date.
I've definitely found that while "AI makes getting from 0-80 done much easier than the 80-100" holds true, it is much easier to get my work to a quality bar that I'm excited to share with my peers...
There's still a lot of effort required to move something from "good idea, loads to do" to "really finished and really works and I've proved it".
But its a lot less effort that when we didn't have LLM's.
Interestingly it does seem that it's still enough effort to prevent most folks from making that step though.
So relatable. But I have some finished projects now and some of them I use daily.
The definition of "finished" has changed for me also.
More and more, I am using half finished as a polished product, but pragmatically very useful software I have built myself.
More importantly, I see no reason to polish this into a product. It is more useful in this half finished, easily moldable state.
Like it use to make sense to bake the clay and sell the hardened output but now I want to keep the soft clay so it can be molded to my changing needs. I keep adding to a collection of these moldable states.
Can't really blame AI for that though.
They aren't blaming AI, they are just backing up the "not much has changed" idea.
It's always been easier to start a project than finish it, and LLMs make starting a project roughly free. I'm not sure they change how much work it is to finish it all that much.
I mean, I have finished more side projects than before. So they do change it. Just not as dramatically.
Of course you can. LLMs take you from 0 to 80 instantly. They are then completely incapable of getting from 80 to 100 and making something worth shipping to production. They are the ultimate unfinished side project generator.
17 replies →
Skill issue. I had 30 unfinished side projects even before AI. Just raw talent.
No idea what you're talking about. I'm using AI to help me on my paperclip production side project, and it's going great!
Yeah, when there is no code review requirements and no pesky production database you can't just yolo :)
At work, they mostly let me increase quality, because it's easy to say find all parsers in my code base and fuzz them.
It is great. I just had claude yolo a human in the loop image segmentation pipeline last night. It cut weeks of work down to an evening like 4h. Segment Anything 3.1 + Napari final touch.
I'd also say: when you really understand a domain well and you're a one-(wo)man show, you can just fly!
Of course, you can make a giant pile of doggy-doo-doo, but that was always true, just you can now make an epic Giza-sized pile.
> but that was always true
Yeah but were more likely to learn how bad your code was in the process. I see people oblivious to their slop putting pressure on others to merge it.