The POV of the author I understand quite well because it was mine. Its really only in the last 6 months or so that my perspective has changed. The author still sounds like they are in the "black box that I toss wishes into and is dumb as fuck" phase. It also sounds like they are resistant to learning how to make the most of it which is a shame. If you take the time to learn the techniques that make this stuff tick you'll be amazed at what it can do. I mean maybe I am a total idiot and this stuff will get good enough that I am no longer necessary. Right now though? I see it as an augmentation. An amplification of me and what I am capable of.
This perspective was mine 6 months ago. And god damn, I do miss the feeling of crafting something truly beautiful in code sometimes. But then, as I've been pushed into this new world we're living in, I've come to realize a couple things:
Nothing I've ever built has lasted more than a few years. Either the company went under, or I left and someone else showed up and rewrote it to suit their ideals. Most of us are doing sand art. The tide comes in and its gone.
Code in and of itself should never have been the goal. I realized that I was thinking of the things I build and the problems I selected to work on from the angle of code quality nearly always. Code quality is important! But so is solving actual problems with it. I personally realized that I was motivated more by the shape of the code I was writing than the actual problems it was written to solve.
Basically the entire way I think about things has changed now. I'm building systems to build systems. Thats really fun. Do I sometimes miss the feeling of looking at a piece of code and feeling a sense of satisfaction of how well made it is? Sure. That era of software is done now sadly. We've exited the craftsman era and entered into the Ikea era of software development.
I’ve been building a lot of agent workflows at my day job. Something that I’ve found a lot of success with when deciding on an orchestration strategy is to ask the agent what they recommend as part of the planning for phase. This technique of using the agent to help you improve its performance has been a game changer for me in leveraging this tech effectively. YMMV of course. I mostly use Claude code so who knows with the others.
“Don’t let your work self, be your best self.” Is a turn of phrase my boss said to me one time. He was describing his own father’s total inability to be present at home while over achieving at work. That really stuck with me. And is a mantra I repeat to myself quite often.
The struggle is real. Therapy helps. Meds might be worth checking out too as this sounds like ADHD.
I worked in health care tech for about 5 years. AI driven before it was cool. Took processes that normally took years down to a couple hours. Cutting edge stuff.
What struck me over the years was the open hostility we faced from the staff. The admins would buy our product, then have us come do trainings. The clinicians seemed to resent every second of it and would just never use the tool.
Towards the end of my tenure there, a PM said to me “the last thing these people want is to have to learn yet another workflow”. Which is when the penny dropped for me that our tool was just one of a bazillion being force fed to these poor people. They want to spend their time with patients not a screen.
Despite it being the most mission driven I have ever felt about a product (we were literally trying to help cure cancer lol). I’ll never work in health care again. Like education, it’s a quagmire.
I've developed the following methodology with LLM's and "agentic" (what a dumb fucking word...) workflows:
I will use an LLM/agent if
- I need to get a bunch of coding done and I keep getting booked into meetings. I'll give it a task on my todo list and see how it did when I get done with said meeting(s). Maybe 40% of the time it will have done something I'll keep or just need to do a few tweaks to. YMMV though.
- I need to write up a bunch of dumb boilerplatey code. I've got my rules tuned so that it generally gets this kind of thing right.
- I need a stupid one off script or a little application to help me with a specific problem and I don't care about code quality or maintainability.
- Stack overflow replacement.
- I need to do something annoying but well understood. An XML serializer in Java for example.
- Unit tests. I'm questioning if this ones a good idea though outside of maybe doing some of the setup work though. I find I generally come to understand my code better through the exercise of writing up tests. Sometimes you're in a hurry though so...<shrug>
With any of the above, if it doesn't get me close to what I want within 2 or 3 tries, I just back off and do the work. I also avoid building things I don't fully understand. I'm not going to waste 3 hours to save 1 hour of coding.
I will not use an LLM if I need to do anything involving business logic and/or need to solve a novel problem. I also don't bother if I am working with novel tech. You'll get way more usable answers asking about Python then you will asking about Elm.
TL;DR - use your brain. Understand how this tech works, its limitations, AND its strengths.
I live in LA and have been here for almost 30 years now. This stunt is a provocation designed to get a reaction. He wants an excuse to crack heads in a city he hates and that hates him back. He probably also wants us to forget about Musk outing him on the Epstein files.
Watching this unfold here is reminding me strongly of the Ghorman plotline in Andor S2: "You need a resistance you can count on to do the wrong thing at the right time."
I’ve warmed to this tech a bit, but christ would I like to hear more takes from dudes who aren’t running a fucking AI company. It’s impossible to take anything they say as anything other than a god damn ad.
Because nothing matters. Just wait out the outrage cycle. In a week or two the general public will have moved on. Signalgate, the president being convicted of numerous felonies, etc being a few examples that pop into my head. None of this should be status quo but we live in interesting times as they say.
I started writing python professionally a few years ago. Coming from Kotlin and TypeScript, I found the language approachable but I was struggling to build things in an idiomatic fashion that achieved the loose coupling and testability that I was used to. I bought this book after a colleague recommended it and read it cover to cover. It really helped me get my head around ways to manage complexity in non trivial Python codebases. I don’t follow every pattern it recommends, but it opened my eyes to what’s possible and how to apply my experience in other paradigms to Python without it becoming “Java guy does Python”.
> This...doesn't seem to support your case at all?
Hm ok well I am not sure what you mean but its the internet so... <shrug>
What I am saying here is that you would be shocked at how far you can get with a simpler architecture. Distributed systems have massive trade offs and are the kind of thing you shouldn't do unless you are FORCED to.