Thank you. Sometimes I get to like -4 or even -7 before it starts going up. It might be nice to graph it at some point to see my most varied comments. I'm at -2 right now
23 minutes later I'm at +2
6 minutes after, +5 +4min now +6, another 20 minutes +8. I think I'm in the clear
I just stopped caring about votes. It's often driven by inertia, and it can't differentiate a vote from someone who doesn't know anything vs a domain expert. Life is better once you stop caring about karma points.
speaking of claude code in Ghostty, I’ve noticed I can’t drag and drop images into the prompt when the session is within a tmux pane. I miss that, coming from the mac terminal app, which allowed me to do so. I’d be willing to look into this myself, but mention it in case someone already knows where to start looking.
I like using AI for visualizations because it is one-time use throwaway code, so the quality doesn't matter at all (above not being TOTALLY stupid), it doesn't need to be maintained. I review the end result carefully for correctness because it's on a topic I'm an expert of.
I produce non-reusable diagrams namespaced by blog post (so they're never used by any other post). I just sanity check that the implementation isn't like... mining bitcoin or leaking secrets (my personal site has no secrets to build) or something. After that, I don't care at all about that quality.
The information is conveys is the critical part, and diagrams like this make it so much more consumable for people.
That's really cool. I was looking at them and thinking "I could probably make these with vanilla html/css but it'd be pretty tedious." Perfect use case for AI. I need to work on developing a reflex for it.
I've also started doing this, and it's surprisingly enjoyable to both do and even to read. The end result is often more readable to me than using a 3rd-party JS visualization library, because I only need to know standard HTML/CSS concepts to understand what's going on. And a side benefit is smaller pages with less bitrot due to being able to skip the dependencies.
i think no one can stop that from happening.. you have electricity, you have apps. people will have more thinking on the child thing. and more time on the internet and less time on the home.
With regard to AI, why not throw this whole article in an .md file and point CLAUDE.md to it? Codex is better at following rules so maybe you’d have more luck with that. But yeah, AI won’t code your way by default. People expect way too much out of the interns, they need direction.
You either have the case that tech moves on and the LLM is out of date on anything new, so adoption slows or you have tech slowing down because it doesn't work with LLMs so innovation slows.
Either way, it's great if you're working on legacy in known technologies, but anything new and you have issues.
Can I write a spec or doc or add some context MCP? Sure, but these are bandaids.
Interesting to see all the people in this thread who had a stroke. I had a mild and then moderate cerebellar stroke within a 7 day span about two years ago. I remember being on the stroke neurology floor of the hospital with a lot of bed ridden people who had also suffered them. I know because, within 24 hours, I was doing hourly walking laps with my nurses because I was bored. In other words, I was one of the lucky ones. Within a week I was back at work — not because I felt pressured to by them, they were completely understanding, but because I had no more symptoms that were experienced simply because I was sitting down to work.
I also see some advice about listening to your body after the fact, which I fully agree with. In my case, without going into too much detail, the stroke might not have happened if I had listened to my body beforehand, as it was caused by an injury I could have prevented.
So if I could give any advice from this place of experience it would be to listen to your body, and try to hear it when your fears and ego are shouting.
As I understand it, post-COVID a lot more people are having strokes at younger ages, primarily from PFOs. 10–15% of us are walking around with a small pathway between the atria of our hearts, and if a clot happens to form, it can pop into the other side of your heart and get pumped straight to your brain.
I was exceedingly lucky in that it cleared up on its own after about an hour. I was unable to speak and unable to move so much as a finger or toe on the right half of my body. I was completely incapacitated. They had me in the CT when it cleared up, and I immediately was back to my original self with no lasting defects.
I know a vascular neurologist who says that the average age of his patients has dropped by nearly a decade in the last five years. Many more "young" (<60) men with minor strokes, and more frequent serious strokes in the 40s for both sexes. He's treated as many under 30 y/o stroke patients in the last two years than he did in the first two decades of his career. He's a few years from retirement and basically completely rattled by this sudden shift.
I have an out-there hypothesis I’d want to test. Much of the population has one or more MTHFR mutations, which can increase homocysteine if left untreated and that’s been linked to increased risk in stroke. Treatment includes more B vitamins. I wonder if the declining nutrition in foods and lack of B vitamins has anything to do with this.
Lol this person talks about easing into LLMs again two weeks after quitting cold turkey. The addiction is real. I laugh because I’m in the same situation, and see no way out other than to switch professions and/or take up programming as a hobby in which I purposefully subject myself to hard mode. I’m too productive with it in my profession to scale back and do things by hand — the cat is out of the bag and I’ve set a race pace at work that I can’t reasonably retract from without raising eyebrows. So I agree with the author’s referenced post that finding ways to still utilize it while maintaining a mental map of the code base and limiting its blast radius is a good middle ground, but damn it requires a lot of discipline.
In my defense, I wrote the blog post about quitting a good while after I've already quit cold turkey -- but you're spot on. :)
Especially when surrounded by people who swear LLMs can really be gamechanging on certain tasks, it's really hard to just keep doing things by hand (especially if you have the gut feeling that an LLM can probably do rote pretty well, based on past experience).
What kind of works for me now is what a colleague of mine calls "letting it write the leaf nodes in the code tree". So long as you take on the architecture, high level planning, schemas, and all the important bits that require thinking - chances are it can execute writing code successfully by following your idiot-proof blueprint. It's still a lot of toll and tedium, but perhaps still beats mechanical labor.
It started as a mix of self-imposed pressure and actually enjoying marking tasks as complete. Now I feel resistant to relaxing things. And no, I definitely don’t get paid more.
cat out of the bag is disautomation. the speed in the timetable is an illusion if the supervision requires blast radius retention. this is more like an early video game assembly line than a structured skilled industry
reply