The thing I miss most about programming is flow, and the constant bouncing between terminal tabs sucks. I’d love to do one thing at a time, with Fable, quickly.
An ide open with 20 tabs open each file a component, a class or an interface We also use to hold entire codebases in our brain.
I'm struggling to scale myself even further. This tech is unreal and I have so many things I can do.
For the first time, tech feels like the 90's-00's again. Everything is greenfield and exciting and big tech is struggling to figure out what to do about it.
People are just hacking all kinds of stuff, and it's awesome. Feels like techno utopia.
The barrier and time between idea and usable implementation is almost zero now. I don't have to imagine. I can just write something and see it work before making larger decisions. I really like this. Many of my ideas were abandoned because I needed to study some obscure library. Now, I can learn the parts that I find interesting and just have the AI chew through the grunt parts easily. That's the good.
I started coding with a line editor on a small Casio handheld "computer" and used to keep programs in my head. I more or less knew what happened on each line without seeing the line. With larger programs, I had a mental model of what was going on where and a big part of the input to that was the effort of writing everything by hand. That's gone. It's not really important as far as the output of usable programs is concerned but there's a certain feeling of satisfaction that came with digesting a larger codebase and having it surrender it's secrets to you that's missing.
It feels like the opposite of 90s - 00s: they were filled with periods where a person could self-study technology and get a job using those skills that few others had.
Where we are going (according to the AI-proponents) is children being able to replace you.
In brief; the 90s - 00s were a skill-valuation time, now we are looking at a skill devaluation time.
Unless you meant to say "Just like how any kid who could write broken HTML t put up a webpage could pretend to be a skilled professional, that's where we are now"...
Then they hit you with hourly and weekly limits, you are wondering when you are going to get cut off. Since LLM at probabilistic it often feels like pulling the lever of a slot machine, hoping our prompt is the jackpot. To make sure we win, we come up with systems, convoluted agents, context pipelines, rags to load . It feels like it's working, then bam you reach weekly limits.
(Just pay more if you want to keep winning).
I think developers need to wake up.
I myself started to use AI like a fancy debugger ,explainer. I make it walk me though every single line of code it writes.
I notice that i run into limits less, if i get cutoff, i can still make changes
But for instance I used to work in 1-2 client projects at a time and they take months now I can do 4-5 at once and they take a month. That’s a huge improvement
I don't dispute that your tasks are taking less time, but I suspect that to be temporary. This is a forum of AI frontrunners and early adopters, so I expect it's a matter until people catch on, and recalibrate their expectations for amount of output a programmer can produce in a given timeframe.
What I dispute is that this increased output amounts to actual value. There may very well be a HN-wide 10x productivity boost, if HN measures productivity in Jira tickets per day. But if that's the only measurable result, we should expect the only long term change to be a 10x increase in Jira tickets once orgs catch on.
My skepticism is we're not getting that because the world mostly doesn't need more software and it doesn't need all software to be ultra-personalized to each user, either. There are plenty of valuable problems that may be solved via computation, but thus far, it seems we're getting the software equivalent of movie theaters disappearing and being replaced with people watching TikTok from bed. It re-routes the monetary value extraction from consumers of audio-visual entertainment, and TikTok probably has at bare minimum 1000x the content-length of the Criterion Collection, but it isn't making the world 10x better for anyone but the owners of TikTok.
It reminds me of my best friend from college, who was bipolar. His goal in life was to become a writer and he eventually did become an Emmy winner, but back in school, he's go into manic episodes in which he'd stay up all night five nights in a rows and churn out thousands upon thousands of pages of free-form text that incorporate prose, poetry, play scripts. It was definitely more than 10x the output of a non-manic period, and there were nuggets here and there of intensely evocative single phrases, snippets of dialogue that looked like they could come from a more compelling story, but they were ultimately sketches and drafts, not anything publishable that another person would want to read.
Would we call him 10x as productive when he was writing more total output as measured by number of words or when we was writing much less but in a form that millions of other people enjoyed and remembered?
If we purely mean economic productivity, that is pretty straightforward in a case like yours. If you were previously completing 4 projects every 3 months and now you're completing 42 every 3 months, are you earning 14x as much money as you used to?
heh this is funny because this reaction was all the rage in the 90s early 00s too. You'd put together something you thought was cool and then post a link on a forum only to be told how it wasn't even "remotely impressive". I'm glad people didn't give up back then and i hope no one gives up now.
Things just moved up on the abstraction-ladder, but it's still there, hidden beneath all the TUI sessions instead.
Even a year ago when i was trying to do a hugo template manually with the help of the documentatin /tutorial, it was shit. The LLM at that time, was better helping me than the documentation.
I had some helpful people helping me on IRC / Quakenet.
But the hugo example i found very interesting because it was the latest hugo ducumentation and I don't think I was able to find a tutorial. I tried it without an LLM first.