121–130 of 329 posts
This intensification is really a symptom of the race to the bottom. It only feels 'exhausting' for people who don't want to lose their job or business to an agent; for everyone else, the AI is just an excuse to do less.
Edit: Not to mention, this is what you get for not unionizing earlier. Get good or get cut.
Earlier quoted context omitted.
I just build a programming language in couple of hours, complete with interpreter with claude code. I know nothing about designing and implementing programming languages: https://github.com/m-o/MoonShot .
Yes, my point is that it was possible to build it before AI and in much less effort than people imagine. People in college build an interpreter in the less than couple weeks anyway and that probably has more utility. Consider two scenarios: 1) I try to build an interpreter. I go and read some books, understand the process, build it in 2 weeks. Results: I have a toy interpreter. I understand said toy interpreter. I le…
I think there will be a lot of slop and a lot of usefull stuff. But also, what i did was just an experiment to see if it is possible, i don't think it is usable, nor do i have any plans to make it into new language. And it was done in less than 3 hours total time.
So for example, if you want to try new language features. Like let's say total immutability, or nullability as a type. Then you can build small language and try to write a code in it. Instead of writing it for weeks, you can do it in hours.
Earlier quoted context omitted.
What kills me personally is that I'm constantly 80% there, but the remaining 20% can be just insurmountable. It's really like gambling: Just one more round and it'll be useful, OK, not quite, just one more, for hours.
If you think it's getting 80% right on its own, you're a victim of Anthropic and OpenAI's propaganda.
Sometimes it looks like some of that comes from AI generally being very very sure of its initial idea "The issue is actually very simple, it's because..." and then it starts running around in circles once it tries and fails, you can pull it out with a bit more prompting, but it's tough. The thing is, it is sometimes actually right, from the very beginning, but if it isn't...
This is just my own perspective after working with these agents for some time, I've definitely heard of people having different experiences.
> the productivity boost these things can provide is exhausting . What I personally find exhausting is Simon¹ constantly discovering the obvious. Time after time after time it’s just “insights” every person who smoked one blunt in college has arrived at. Stop for a minute! You don’t have to keep churning out multiple blog posts a day, every day. Just stop and reflect . Sit back in your chair and let your mind rest. W…
How do you know that? You don't think he's being paid for all this marketing work?
People keep on making the same naive assumption that the total amount of work is a constant when you mess with the cost of that work. The reality is that if you make something cheaper, people will want more of it. And it adds up to way more than what was asked before.
That's why I'm not worried about losing my job. The whole notion is based on a closed world assumption, which is always a bad assumption.
If you look at the history of computers and software engineering including compilers, ci/cd, frameworks/modules/etc. functional and OO programming paradigms, type inference, etc. There's something new every few years. Every time we make something easier and cheaper, demand goes up and the amount of programmers increases.
And every time you have people being afraid to lose their jobs. Sometimes jobs indeed disappear because that particular job ceases to exist because technique X got replaced with technique Y. But mostly people just keep their jobs and learn the new thing on the job. Or they change jobs and skill up as they go. People generally only lose their jobs when companies fail or start shrinking. It's more tied to economical cycles than to technology. And some companies just fail to adapt. AI is going to be similar. Lots of companies are flirting with it but aren't taking it seriously yet. Adoption cycles are always longer than people seem to think.
AI prompting is just a form of higher level programming and being able to program is a non optional skill to be able to prompt effectively. I'd use the word meta programming but of course that's one of those improvements we already had.
Had a similar experience recently, set up Claude code, wrote plans, CLAUDE.md etc. The plan was to end up with a nice looking hugo/bootstrap/ website. Long story short, it was ugly and didn't really work as I wanted. So I'm learning Hugo myself now... The whole experience was kind of frustrating tbh. When I finally settled in en did some hours of manual work I felt much better because of it. I did benefit from my pla…
Had a similar experience recently, set up Claude code, wrote plans, CLAUDE.md etc. The plan was to end up with a nice looking hugo/bootstrap/ website. Long story short, it was ugly and didn't really work as I wanted. So I'm learning Hugo myself now... The whole experience was kind of frustrating tbh. When I finally settled in en did some hours of manual work I felt much better because of it. I did benefit from my pla…
Now that you get accustomed with Hugo, I wonder if the way you plan & prompting now will produce better result or not
Previous discussion of the original article: https://news.ycombinator.com/item?id=46945755