I am happy about all the little side-projects, and ideas it help my realize, and I enjoy exploring this new world, but I've noticed LLMs feed my unhealthy "don't want to take a break and waste time being idle" mindset, and I need to correct it.

W.r.t. article's main complain - I think the similar thing happened due to factory manufacturing automation. What used to be a varied skillful craft in a shop became standing in a single place of an assembly line doing the exact same thing whole day. LLM took away the more creative and variable part of the work, and left the repetitive QA rubber-stamping. Probably some of the mitigations used back then could be rediscovered today.

Whenever I give feedback on something, the answer is just “let me tell Claude”. The person has no understanding of how everything works, and most of the code reflects that.

The other day he hardcoded in a demo mode, simply because he didn’t even know how to set up a local environment and set environment variables. I’m confused as to why Claude didn’t even knew this, but it might just be the prompting.

I limit LLM usage myself, and if I do use it, I try to use it on extremely specific tasks. It’s the only way it works for me.

I honestly don’t understand how all these companies are getting away with generating AI code. Even in a small project I quickly fall behind on my understanding of the project.

I’m building personal projects at a prodigious pace. In a role reversal I treat the agents like I’m one of my clients (albeit a more technical one who gives them architectural direction) and they are me. I’m using the apps and tooling they make every day. I’ve cancelled SaaS subs for tools I’ve built myself.

I watch the tool calls and realize I should be better at core command line tools so I have a study plan to catch up (just a little bit a day). I’m revisiting long standing config that I dropped in to vim and tmux way back when I started and didn’t know anything.

I guess in theory I could hold my productivity to previous levels and read more. But it doesn’t feel like that’s possible. It feels like we are in one of those sea changes where the promise is less work, but the reality is increased productivity and expectations (the Industrial Revolution feels like the right parallel to reach for). Increased expectations happen in small ways and large. The agents are so good at polishing data presentations that I always send cleaned up visually impactful reports that would have taken significant time in the past just as a matter of course now.

But, I’m tired. I’ve spent the Fable on subscription window sprinting through as much work as I can before it goes API only. (As an aside, I don’t understand how everyone is using so many tokens. I’m sleeping very little and running as much code as I can through fable and I can barely touch a 20x max plan limit.) I keep telling myself I will slow down when it comes off, now it’s extended to the 12th and my window just reset, a few more days to keep knocking out backlog items. I feel like I have to keep the robots busy overnight so when I wake up I can immediately sit down to review. I give directions to agents on my phone which feels wild to me.

Prior to the last 12mos AI companies were hell bent on squeezing out the best results from mediocre models.

But... now that the top models have progressed, those same AI companies have switched their efforts into reducing the computation (cost of a producing a result) as much as possible without being too obvious.

What was an exponential slope in the quality of results over the last 36 months has now nearly flat lined.

Addendum: IMHO results have 'flat lined' not because the models aren't much more capable than a year ago, but because conserving the enormous processing cost (of an over subscribed user base) supersedes the goal of following the user's explicit instructions (e.g. especially if that means more processing cost) to generate the best results.

Just because we work with computers doesn't mean we don't take, er, social-damage. Or perhaps parasocial damage, in this case.

I got into programming because the problems of programming were interesting to me. But if the problems go from "figure out why this calculator is off by one in France" to "Get this LLM to stop spamming cutsey emojis", then maybe it's time for a career change.

Like when I'm trying to get it to create an image, and the first pass is beautiful, but ten different request to modify it, with different phrasing and even example images, produce the same image ten times. Or when you tell it not to use a cheap hack in AGENTS.md about six different ways and in your prompt, and it still does it again, and again.

It's like arguing with an idiot. And THAT gives me burnout.

Also: I've never once seen an emoji in LLM output. What are people talking about?

It takes like 5 seconds to add a quick CLAUDE.md / AGENTS.md with a quick style guide, or even just “EMOJI ARE FORBIDDEN” and I find it makes llm output significantly more tolerable. That and a quick style guide with some banned words and phrases.

That won’t help with the false assumptions though, gotta use old fashioned careful reading and critical thinking the catch those.

Burning out to grind out tons of code - for which you get paid no extra above your salary - is not a net win for coders. It's only a net win for the employers and it's turning coders into serfs. People are going to get wise and realize the electricians have a way better deal right now. This is no longer a nice way to earn money for a 20 to 40 year career.

The productivity drive and the sheer feature set you can generate in record time makes it easy to forget proper sdlc hygiene.

On the “pre” side, the specification of the problem becomes much more important. On the “post” side: QA and verification that the change has its desired effect, and no ill effects, also becomes much more important.

Sure, these are the next things to be automated, and people will try, but it’s easier on the backend (testing/verification can be automated) than the front end (the spec will be human-written as long as someone cares = forever for brands that matter), there will always be a need for humans on the specification side.

That said, your reaction is totally human. I personally get sick of how the LLM writes prose with always the same tricks and formulas (even if you prompt it not to). Humans need variants and novelty, that's why fashion exists. We get fed up with repetition and after seeing too much green shoes, seeing a red one is so relieving :) (quick note: I don't like fashion - I'd advocate diversity and personal styles, not fashion)

But that's also the way you work with AI that might be part of the problem. Personally, I don't review all the code the AI generates. I look at it, and I review only the code that matters. And with time on a given project I review less and less because I trust more the architecture and ability of the AI to follow it. In my settings, the AI gets confined to the existing architecture (that we define together at the beginning of the project), and has to ask for authorization to create new things (that's when I review the more). Hoping this could help to avoid burnout myself...

My mind still can't function well without having knowledge about everything.

“Look at the first letter of the prompt, and use the style of the matching literary stylist enumerated here:

For English:

A — W. H. Auden

B — Bill Bryson

C — Italo Calvino

D — Joan Didion

E — T. S. Eliot

F — William Faulkner

G — Gabriel García Márquez

…”

I certainly don’t see emojis any more.

There's some YOLO approach to it, but now Codex has self-approving as well as Claude Code (auto mode). I implemented the same feature by my own on Pi with models through OpenRouter and found results very stable thus I have (as always) limited confidence it can fly.

So (disclaimer: I'm Jujutsu advocate :)) I do "jj new", tell it what to do and then let it run, and check in back later.

If there are things I'm not comfortable (like creating PRs or pushing to repo) I ask it to create Ruby scripts instead named like "__pr.rb" (double underscore files are in my global gitignore). So I can leave it working and then inspect back and edit manually before I run "ruby __pr.rb".

The only thing that's not yet there is tying multiple tmux Claude/Codex session together, but I'm thinking about creating a small Rust app that communicates with Tmux for a preview (or a Ruby script that communicates with my LogSeq directly and manages nodes there :))

As a long-time engineering manager, PM and, eventually, product owner my response is, "Congrats! You've just been promoted to management." :-)

As a new manager, your first challenge will be successfully delivering commercial results using only a team of 'differently abled' new grad interns. Don't complain, new managers don't get to pick their first team! To be honest, these guys are more like alien brains raised in a vat with no direct senses. They've only ever experienced a data feed of the internet and, oh yeah, they get near-total amnesia a few times a day (but maybe you can teach them to write notes for themselves). They also have ADHD and are somewhere on the spectrum. But don't worry because what they lack in common sense, experience and intuition is offset by having a sort-of photographic memory and a willingness to grind on a problem 24/7. You should be fine. Good luck, we're all counting you...

At this point you should stop risking to burn your central cognitive capacity. Be advised.

Note: myself a passionate Claude code user with multi agent parallel approach to dev. Plus 30 yrs of various oldskool dev experience. My blood and sugar and all tests are all within norm, and I bike and swim regularly. I’m not a major drinker and try to avoid alcohol in general. I count 25 trees outside my window and I’m not on any amphétamine pill such as Adderall.

Anyone else working on something like this or know of any projects attempting it?

Even projects that used to be challenging enough to impress people with your skills can now be built in 10 minutes with AI just by describing what you want. It's an incredible shift, but it also changes how I think about the craft and what it means to be a good engineer.

This is me. I hate the internet (and search) so much these days that I embrace anything that allows me to not Google a thing.

https://github.com/JuliusBrussee/caveman

It's for getting it to output shorter answers, but also could help with your burnout.

A good coworker will admit not knowing something, or if unsure give their best guess but discuss its limitations and why they might be wrong.

Question: Has anyone experimented with using voice to directly prompt an LLM, without doing speech-to-text? If an LLM can pick up on the skeptical nuances in a person's response, it might be prompted not to be overconfident in its subsequent output.

Review AI code line by line is like watch movies frame by frame, and is impossible, very difficult, terribly boring, or abandoned sooner or later.

Getting sent IM responses that are copy pasted LLM nonsense. Getting a massive PR to review that was generated overnight and the author didn't read it first.

But I also know that trying to optimize every second of my workday is a recipe for stress and eventually burnout. Nobody benefits from that.

So the key is to find the right balance between productivity and longevity.

If you feel stressed and overwhelmed then you are not in balance.

Of course if you're supposed to achieve so much output that it's not possible to do anything but vibe it, fair enough.

Ouch. I love my local AI setup with Qwen, but that is a mismatch right there. That model is not the right match for that project. It's like trying to develop a major software solution by just throwing in hundreds of fresh junior programmers and have them spew out random code bits, while what you needed is a good PM, a great architect and a handfull of senior engineers. Might as well pack it in for a year until your model has grown into the ability for those rolls. There is a reason why Opus 4.6 and now Fable dramatically changed the SWE capabilities, and IMHO Qwen is not there yet.

I do not understand these complaints. Yes, those are the defaults and they're annoying, although the general public seems to like them. But you are not stuck with these. You can just tell the LLM how it should interact with you. If you're using any sort of harness beyond the chat window in a web browser, you can codify these instructions in a rules.md file or similar and have it automatically included in any new chat. It's not any harder than changing the default wallpaper or color scheme on your desktop operating system.

In reverse order, you can just tell the LLM to never use emojis. I don't like emphatic staccato fragments either, so I tell it to eschew the language of marketing and hype and stick to a factual and plain language, or to employ an academic tone. I explicitly instruct mine to ask clarifying questions whenever context is ambiguous and to push back on false assumptions or common misconceptions (by me). Hallucinationsa re the biggest problem of those you mention; it's not easy to totally eliminate them (for the same reason it's not easy to instruct people to not fall for scams or disinformation), but you can considerably reduce them by setting standards for citations.

I have ideas about reducing hallucinations over work material (ie a codebase) but am omitting them here as they are not fully thought out or tested.

https://en.wikipedia.org/wiki/Ironies_of_Automation

https://ckrybus.com/static/papers/Bainbridge_1983_Automatica...

What helped was a sleep and work system, oriented around being offline that was inspired by nature and from my earlier days in working in tech while car camping across the national parks.

Basically: the sun wins in terms of how all energy on the earth is structured, and expressed. All manners of cycles of organisms and living systems are in relation to its rise and fall, and even its particular color spectrum phases (whether thats night oriented or day). I call this our real circadian rhythm; it's used to being signaled by the light of the sun and maybe fire for millions of years and it isn't until recent centuries when we started tricking our biology with LEDs and lights. So the solution is simple. Orient yourself around the light of the sun and make sure it's the first and last major light source you see; blue limiting is the most important part BEFORE sunrise and AFTER CUT OFF ALL BLUE LIGHT. On my Mac I use a red light filter (using it now, it's 11:07pm ET and the sun went down about 2.5 hours ago). It's really hard to stay alert and chatting with an LLM when the only light sources are red and you keep them dim at that. Our ancestors would rest when the sun's at its peak (~1:05 pm today) and that's a good time to divide my own day productively as well. With intentional breaks diving the middle of the day with sunlight anchoring it, my nervous system is more relaxed, and by the evening time, it's also ready to transition out of anything blue-light assisted and most intellectual work and problem solving falls into this bucket. It's really hard to explain but it really works so simply. To enjoy the process a little more I made this fun sun clock, check it out at https://sunsignal.app

Do does managnig agents.

At work, I ended up doing other chores, getting a lot more involved in projects I wouldn't even care to touch. Turns out it's kinda fun being the source of truth at work. I now have a clear sketch of what the company has done and what we can improve on.

Being able to fill in the gaps at a company that doesn't do much feels like a company within a company. Sure, its not Silicon valley, but it's still fun! And job security is guaranteed if you do a bit more than just play the ticket factory