I think yes because there are people who prefer picking up something rather than building their tool. Recreating just everything from scratch or make custom solutions are not the one way to go. I do not want to create editor/IDE because it is not in my interests. I choose VS Code, Kate, Notepad++, Nano instead. If I have paid LLMs I will use them different way than reinventing editor lol.
Also keep in mind that it is software which requires a little bit maintenance from time to time. And access to LLM (mostly paid) and (or - depends on if we want to understand something) domain knowledge (in this case how to build editor, how to do parsing etc.).
However if somebody wants to do custom things then let him/her do it. And yeah first editor, then programming language, then... OS and so on.
I mean no one is arguing that it is the best or even an OK format for serious data storage. Other solutions exist for a reason. But it’s evergreen and won’t go away precisely because of its simplicity. You will be able to use a CSV more or less identically in 2050, no questions asked.
It’s inherently universal because it’s text-based, and I think you underrate the occasional need to inspect it yourself. And when you do, it’s nicer to view than JSON to throw out an example (arguably JSON and variants need their own bespoke file viewer!)
It’s like saying markdown should be abandoned because text editors do all the formatting for you anyways and different markdown parsers exist and don’t always play nice. Or like saying txt should be abandoned in favor of rtf, even. Okay, sure, not invalid points. But in practice? Simplicity is often a virtue.
I think Spec-Driven Development is similar to waterfall but it is not like that. It is more agile oriented and for fast iterations. The idea is simple and can be vibecoded too - quick chatting, planning and so on.
The main things I don't like about LLM is that frontier models are paid (so no unlimited "tokens"), subscribtion based payments, local models are "not ready yet".
Can you understand that there is a lot of DIFFERENT people than YOU who can use AI tools? My team leader (he is also director of department) can use Claude/Codex (or other LLM/AI tools) and create faster, better things than doing it manually. You would not say that he is going down - he is even better with it.
Privacy, no need to pay for tokens, offline usage, endless possibilities - you do not have to pay for tokens (subscribtion payment), so you can do more. The big issue is that local models are not "ready yet" compared to frontier and paid services. It is hard to run decent model without decent hardware. And to be honest even if you can buy hq hardware and spend a lot of money then it is not the same quality.
So start creating quality, convenient and easy to use tools for native development and then create that quality software. You can use free/paid LLMs/agents/AI or don't use any AI. If something feels wrong then change it via next agent iteration on manually by hand. People complain but do opposite things or nothing at all :(
I like idea about removing too many ways to do something. I do not like that programming languages can be too complex becausd there could be few ways to just write simple thing. So thanks for reducing complexity.
Also I really like that somebody said that Rust syntax is complex and too hard to learn. So many unreadble things. However Rust did good think about fn keyword - it fits better than fun, func, function keywords. I hope you will not choose path where every 2nd word is abbreviated.
Currently, I have 3 main issues with AI, LLMs and so on. Generally speaking I am happy that I can use Claude Code and Codex to help building, fixing and maintaining software in my job. To be honest it is so helpful, I am less stressed bacause most of the time I can "find out" solution without asking collegues for help or I do not have spend a lot of time struggling myself. Yeah, if you understand what feeling it is that you know you can't solve problem then you will know what I am writing about.
But...
There are exceptions which make me bad feeling about AI, LLMs and so on:
1. Paid, subscribtion based payment model - you have to pay for tokens.
2. Local models are not "ready yet". You still have to own decent hardware and it will not be the same level of frontier models. I am big fan of local first, offline and "unlimited usage" compared to paid solutions. But probably I have to wait few or several years to get to that point.
3. Feeling "I did not do it myself". This is the most what could make bad feel. You "cheated". You did not write this great app or solve problem alone. You just did modern "copy and paste". You did not write or design this class, function alone by hand. And you know you probably could not do it without help of AI, LLM.
2. Local models are not "ready yet". You still have to own decent hardware and it will not be the same level of frontier models. I am big fan of local first, offline and "unlimited usage" compared to paid solutions. But probably I have to wait few or several years to get to that point.
This is why tech companies are working hard to make sure you can never build your own computer again.
The third point, on its own, doesn't bother me so much. What does bother me is the "clean it up for publication/PR/etc." phase. It was never especially fun in the first place, but cleaning up my own mess is something I can contend with, and you get a sense of satisfaction once you're done.
Cleaning up the slop from a faceless machine is just... not something I want to do. And even if you do get it done, the sense of satisfaction at the end is reduced.
I think the only way I can be truly "productive" with AI is to drop my bar for quality. For some cases that's easy (e.g. run-once-and-throw-away scripts), but for everything else I just can't do it.
Because a large portion of people are in this industry for the high salaries only, and always disliked the actual job of programming. Those people welcome LLM coding with open arms.
Also keep in mind that it is software which requires a little bit maintenance from time to time. And access to LLM (mostly paid) and (or - depends on if we want to understand something) domain knowledge (in this case how to build editor, how to do parsing etc.).
However if somebody wants to do custom things then let him/her do it. And yeah first editor, then programming language, then... OS and so on.
reply