Too early in my career to not give a shit and retire, but too late be excited about these things and eager to learn. What a time...
One thing I’ve noticed though that actually coding (without the use of AI; maybe a bit of tab auto-complete) is that I’m actually way faster when working in my domain than I am when using AI tools.
Everytime I use AI tools in my domain-expertise area, I find it ends up slowing me down. Introducing subtle bugs, me having to provide insane amount of context and details (at which point it becomes way faster to do it myself)
Just code and chill man - having spent the last 6 months really trying everything (all these context engineering strategies, agents, CLAUDE.md files on every directory, et, etc). It really easy still more productive to just code yourself if you know what you’re doing.
The thing I love most though - is having discussions with an LLM about an implementation, having it write some quick unit tests and performance tests for certain base cases, having it write a quick shell script, etc. things like this, it’s Amazing and makes me really enjoy programming since I save time and can focus on doing the actual fun stuff
But it's like you said, I like using LLMs for completing smaller parts or asking specific kind of help or having conversations about solutions, but for anything larger, it just feels like banging my head to a wall.
It feels like just writing my own code but at 50% higher wpm. Especially if I can limit it to only suggest a single row; it prevents it from effecting my thought process or approach.
This is how the original GitHub copilot worked until it switched to a chat based more agentic behavior. I set it up locally with an old llama on my laptop and it's plenty useful for bash and c, and amazing for python. I ideally want a model trained only for code and not conversational at all, closer to the raw model trained to next-token predict on code.
I think this style just doesn't chew enough tokens to make tech CEOs happy. It doesn't benefit from a massive model and almost drains more networking than compute to run in the cloud.
LLMs are not useful in this workflow, because they are too verbose. Their answers are generic and handle scenarios you don't even support yet. What's useful is good documentation (as in truthful) and the code if it's open.
This approach has worked really well in my career. It gives me KISS and YAGNI for free. And every line of code is purposeful and have a reason to be there.
I’ve been actively using the first tier paid version of:
- GPT - Claude - Gemini
Usually it’s via the cli tool. (Codex, Claude code, Gemini cli)
I have a bunch of scripts setup that write to the tmux pane that has these chats open - so I’ll visually highlight something nvim and pipe that into either of the panes that have one of these tools open and start a discussion.
If I want it to read the full file, I’ll just use the TUIs search (they all use the @ prefix to search for files) and then discuss. If I want to pipe a few files, I’ll add the files I want to nvim quickfix list of literally pipe the files I want to a markdown file (with a full path) and discuss.
So yes - the chat interface in these cli tools mostly. I’m one of those devs that don’t leave the terminal much lol
I also have a personal rule that I will try something for at least 4 months actively before making my decision about it (programming language, new tools, or in this case AI assisted coding)
I made the claim that in my area of expertise - I have found that *most of the time it is faster to write something myself than I write out really detailed md file / prompt. It becomes more tedious to express myself via natural language then it is with code when I want something very specific done.
In these types of cases - writing the code myself, allows me to express the thing I want faster. Also, I like to code with the AI auto complete but still while this can be useful I sometimes disable it because it’s distracting and consistently incorrect with its predictions)
Cue: "the tools are so much better now", "the people in the study didn't know how to use Cursor", etc. Regardless if one takes issue with this study, there are enough others of its kind to suggest skepticism regarding how much these tools really create speed benefits when employed at scale. The maintenance cliff is always nigh...
There are definitely ways in which LLMs, and agentic coding tools scaffolded in top, help with aspects of development. But to say anyone who claims otherwise is either being disingenuous or doesn't know what they are doing, is not an informed take.
Ditto. And we still can.
I've yet to use an "agent", and still use a chat UI to an LLM in Emacs. I rely on these tools for design discussion, rough prototyping, and quick reference, but they still waste my time roughly a quarter of the time I use them. They have gotten better in the last year, though, and I've been able to broaden my reach into stacks and codebases I wouldn't have felt comfortable with before, which is good.
I just have no interest in "agents". I don't want to give these companies more access to my system and data, and I want to review every thing these tools generate. If this makes me slower than a vibe coder, that's intentional. Thankfully, there are still sane people and companies willing to pay me for this type of work, so I'm not worried about being displaced any time soon. Once that happens, I'll probably close up shop, figure out an alternative income stream, and continue coding as a hobby.
This just feels... a little too dystopian. Companies hoovered up the entirety more or less of all of our collective thoughts and writings and output and now want to sell it back to us- and I fear that cost is going to be extremely steep.
It's impressive, but at the same time, just feels like its going to somehow be a net detractor to society, and yet I feel I need to keep up with each new iteration or potentially get washed over and left behind by the wave.
I am somewhat fortunate to be towards the top of the pyramid and also in a position where I could theoretically ride off into the sunset, but I fear the societal implications and the pain that is going to come for vast numbers of people.
The very last thing I want is to be "elevated to a manager of agents," as they so smugly say in the video.
Ability to code within an IDE will not make shareholders happy while shoving AI down developers' throats most definitely will.
