I feel I've upskilled in so many directions (not just "ability to prompt LLMs") since going all in on LLM coding. So many tools, techniques, systems, and new areas of research I'd never have had the time to fully learn in the past.
I have a hard time believing any tenured developer is not actually learning things when using LLMs to build. They make interesting choices that are repeatable (new CLIs I didn't even know existed, writing scripts to churn through tricky data, using specific languages for specific tasks like Go for concurrently working through large numerous tasks, etc.)
Anyone not learning things via LLM coding right now either doesn't care at all about the underlying code/systems, or they had no foundational knowledge or interest in programming to begin with (which is also a valid way to use these tools, but they don't work very well without guidance for too long [yet]).
Learning calculus by watching the professor solve integrals on the board for an hour doesn't result in the same level and depth of understanding as working through homeworks every week for a semester. If you ran off to your TA to solve every problem in your homework, you just won't learn calculus.
I've vibe coded plenty. I mostly don't look at the crap coming out. Don't want to. When I do I absorb a tiny bit, but not enough to recreate the thing from scratch. I might have a modicum more surface-level knowledge, but I don't have deep understanding and I don't have skills. To the extent that I've fixed or tweaked AI-generated code, it's not been to restructure, rearchitecture, or refactor. If this is all I did day in and day out, my entire skillset would atrophy.
This is pretty much my point. I use LLMs to code _and_ to learn. I read everything that comes out. Half of it is wrong or incomplete. The other half saved me a bunch of time and taught me things.
This. I never had patience to figure how to build a from-scratch iOS app because it required too much boilerplate work. Now i do, and i got to enjoy Swift as a language, and learned a lot of iOS (and Mac) APIs.
If you build a house from scratch but you didn't mill the lumber, did you build it from scratch?
If you make a pizza from scratch but you used canned sauce was it from scratch? What if you used store bought dough? What if you made the sauce and the dough but you didn't grow the tomato?
I vividly remember understanding how calculus works after watching some 3blue1brown videos on youtube, but once I looked at some exercises I quickly realized I was not able to solve them.
Similar thing happens with LLMs and programming. Sure I understand the code but I'm not intimately familiar with it like if I programmed it "old school".
So yes, I do learn more but I can't shake the feeling that there is some dunning kruger effect going on. In essence I think that "banging my head against the wall" while learning is a key part of the learning process. Or maybe it's just me :D
It's not just you. I feel the same thing, and I saw it in practice helping my son study for a chemistry test just last night. He had worked through a bunch of problems by following the steps in his notes and got the right answers, but couldn't solve them without the notes because his comprehension of why he was taking all the steps wasn't solid.
Once we addressed that, he did great solo. Working the mechanics of the problems with the notes helped, but it was getting independent understanding of the reason for each step that put everything together for him.
> Anyone not learning things via LLM coding right now either doesn't care at all about the underlying code/systems
How many bytes is a pointer in C? How many bytes is a shared pointer in C++? What does sysctl do? What about fsync?
What is a mutex lock? How is it different from a spin lock?
You want to find the n nearest points to a given point on a 2-D Cartesian plane. Could you write the code to solve that on your own?
Can you answer any of these questions without searching for the answer?
I don't use LLMs and I learn things fine. Always have. For several decades. I care deeply about the underlying code and systems. It annoys me when people say they do and they cannot even understand how the computer works. I'm fine with people having domain-specific knowledge of programming: maybe you've only been interested in web development and scripting DOM elements. But don't pretend that your expertise in that area means you understand how to write an operating system.
Or worse: that it prevents you from learning how to write an operating system.
You can do that without an LLM. There's no royal road. You have to understand the theory, read the books, read the code, write the code, make mistakes, fix mistakes, read papers, talk to other people with more experience than you... and just write code. And rewrite it. And do it all again.
I find the opposite is true: those who use LLM coding exclusively never enjoyed programming to begin with, only learned as much as they needed to, and want the end results.
Agree with pretty much everything you wrote here, I guess with the addendum that LLMs can be a part of the learning experience you're describing. It's as easy as telling the LLM "don't write a single line of code nor command, I want to do everything, your goal is to help me understand what we're doing here."
There are always going to be people who just want the end result. The only difference now is that LLM tools allow them to get much closer to the end result than they previously were able to. And on the other side, there are always going to be people who want to _understand_ what's happening, and LLMs can help accelerate that. I use LLMs as a personalized guide to learning new things.
I know it sounds extreme to dismiss that workflow, but I don't think people are talking enough about the subtle psychological consequences of LLM writing for this kind of thing.
In the same way that googling for an SEO article's superficial answer ends up meaning you never really bother to memorize it, "ask chat" seems to lead to never really bothering to think hard about it.
Of course I google things, but maybe I should be trying to learn in a way that minimizes the need. Maybe its important to learn how to learn in way that minimizes exposure to sycophantic average-blog-speak.
To those reading this thread though, be wary of the answers LLMs generate: they're plausible sounding and the LLM's are designed to be sycophants. Be wary, double check their answers to your queries against credible sources.
What do you mean by "LLM coding"? That's not a very meaningful term, it covers everything from 100% vibe coded projects, to using the LLM to gradually flesh out a careful initial design and then verifying that the implementation is done correctly at every step with meticulous human review and checking.
Ah, thanks! Looks like that was long enough ago that my submission didn't auto-redirect me to the existing conversation (which was what I was trying to do, haha).
me neither, but that's because I used to be a bookkeeper. There's accountants though who have data entry people under them who they market as "bookkeepers," and they are now being replaced by AI. Most small business owners in particular dont care.
If your corp is large enough to use a full-sized ERP system it will no longer be your choice to make. The whole software industry is desperately trying to fit AI functions into every pore of their software, ERP vendors being no exception.
Is it their original launch edition keyboard, or the later refined version? The launch edition one I have is like you describe, but I hope they have improved things since then.
Yeah I think I have the original, and reading this again seems like these new ones are more "touch sensitive". It's a neat idea if they can nail the haptics.
CarPlay and affordability. I was totally smitten last year with the R1S during a test drive. I'm not a car person but felt that spark people must feel when they obsess over their vehicles.
But it wasn't pushing-six-figures smitten, which is where you're at when you get a new one with customizations.
Electric cars are supposed to be simple. Give me something in a shape of a Civic, with the engine replaced with a motor and a battery good for 150 miles, and sell it for $10-12k new. Don't even need an entertainment cluster, give me a place to put a tablet or a phone and just have a bluetooth speaker.
Instead, we are getting these boutique, expensive vehicles packed full of tech, but in the end, they still fundamentally suck as cars compared to gas alternatives, especially hybrid. I got a Prius Prime for my wife last year, the car is way better than any EV on the market in terms of usability. Driving to work and back can all be done in EV mode easily, and then when you wanna go somewhere, you can keep the car above 80 mph easily and get there faster without worrying about where to charge.
The only part an EV doesn't have is the engine and gearbox. Admittedly, these are pretty major components, but it's a technology mature enough to be extremely reliable if the manufacturer cares to make it so.
But what an EV has instead is a massive battery, charging electronics, a DC-DC converter keeping the 12V battery charged, and various electric motors and actuators for the air conditioning and coolant loops. These are significant more reliable than oily engines in lab environments, but the automotive environment tests the mettle of seemingly resilient components.
> Electric cars are supposed to be simple. Give me something in a shape of a Civic, with the engine replaced with a motor and a battery good for 150 miles, and sell it for $10-12k new. Don't even need an entertainment cluster, give me a place to put a tablet or a phone and just have a bluetooth speaker.
I think this is more or less the pitch behind Slate (https://www.slate.auto/en), though it's more of a truck/SUV form factor.
> still fundamentally suck as cars compared to gas alternatives
i can assure you my expensive EV does not suck as a car compared to gas alternatives, its better in almost every way. insane performance compared to any gas car, superb handling, way better driving UX tech, silent, clean. & 400mil range is just fine for me thanks. Yes it cost a lot.
The cost of the entertainment cluster comes from the integration work. If it was just a backup camera and a carplay/aa head unit and absolutely nothing else then maybe it could be OEMed from the same companies who sell aftermarket systems for $100 or so.
Yep. I certainly wanted an R1S, but ended up in an EV9 due to CarPlay plus huge lease incentives. No regrets, and will probably get another after this lease is up.
Cars used to compete on distinctions between driving experience/fuel economy/reliability/etc. In comparison, differences between electric cars is mostly superfluous. They're very interchangeable.
For the next generation of car buyers, infotainment and features are going to be the main features. And if you are handing all of that away to the tech companies, your entire company is going to just become another captive hardware partner of the tech giants.
I don't know. I would argue that driving experience and reliability are still very much going to be things in the electric car market. I'm an EV9 owner and we have issues w/ the suspension making it feel sloppy over some bumps. There's going to be a ton of nuance in terms of how all of these different electric vehicles drive, ride, and are experienced. And those are all going to come down to the vehicle manufacturers themselves, not just the technology partner for screens.
It's maddening that $100k purchases get totally nerfed by bad software. Absolutely crazy to me that I can go out find a super nice car I want and have to walk away because of bad software or no carplay support.
I hear this a lot and it's surprising to me. We have three cars in our family (two with carplay and the Rivian) and carplay always feels like such a downgraded experience compared to that of the Rivian.
I have a plex server and use Prologue for audio books. What would my experience on Rivian be like? I am guessing I would have to connect to the infotainment system as a bluetooth speaker? Would I be able to easily skip forward/backward and see the current chapter?
I've been using car play for the better part of the past decade and don't know what it looks like in vehicles without it.
This might be an unpopular opinion, but I'll take a car infotainment system that doesn't need CarPlay/AndroidAuto to be usable (and lacks it) over one that requires a phone attached via CarPlay/AndroidAuto to be usable.
I use Android Auto on rental cars all the time.
My daily driver is a Tesla (Model S /w MCU v2) that doesn't have it. And doesn't need it to provide a usable experience.
If the software has the same library as your phone, then I could why you see it as on par.
Android Automotive has a much smaller library than Android Auto, so the selection for audio apps, such as podcasts and music, are much more limited. The options for map software is smaller too. Also Android Automotive doesn't necessarily use your phone's existing internet connection. Depending on the maker, you have to subscribe to a separate data plan.
I've only rented Teslas but I can see how most people would consider CP/AA to be unnecessary given the quality of their integrated software. But for me, the two things Tesla can't do (and CP/AA can) is
Thanks! Can definitely do that, but GAC is faster than calling claude or another agent as they will take multiple api calls to look at git status, git diffs, etc. vs a single api call with GAC. Plus, GAC won't eat up your weekly limits! ;)
I run a design agency and I've invested a lot of time and energy into a general design prompt that puts out some decently unique looking sites.
We offer this as our "Mini" package at a very affordable price ($99/mo, no setup fee) for clients who don't want (or need) a fully custom design.
I'm not sure you can call this "vibe coding" as much as "vibe engineering" because the resulting code closely models the heavily customized components and styling patterns of our other 60+ custom websites, but the following website designs were very heavily "vibe-derived", from a design sense:
Not exclusively - we have a few clients outside of our region, but most of our marketing is centered around local businesses in our area, and probably 80% of our client base are located within a 50 mile radius.
i hate when a midsize restaurant doesn't even have a website, let alone so many don't have uptodate menu... and i understand, when simple websites are priced >5k upfront, that those restaurants don't do it ; vibe-derived could hopefully be a fair-priced solution
Yep! I built the whole business around slightly higher monthly fees with no (or much lower than typical firms) setup fees. It makes a lot more sense for smaller locally owned businesses.
Yep. Self-reviewing your own PRs is a large boost to both yourself and the team, and often one of the first things I encourage new-ish developers to do.
- 90% of the time when you self-review your own PR, you're going to spot a bug or some incorrect assumption you made along the way. Or you'll see an opportunity to clean things up / make it better.
- Self-reviewing and annotating your reasons/thought process gives much more context to the actual reviewer, who likely only has a surface level understanding of what you're trying to do.
- It also signals to your team that you've taken the time to check your assumptions and verify you're solving the problem you say you are in the PR description.
I always review my own PR before I expect someone else to, but I generally don't add comments. I just look it over and if I see something I want to fix I fix it. Adding comments for things I specifically want feedback on or am unsure about seems like a nice addition to the process though. I might start doing that too.
I have a hard time believing any tenured developer is not actually learning things when using LLMs to build. They make interesting choices that are repeatable (new CLIs I didn't even know existed, writing scripts to churn through tricky data, using specific languages for specific tasks like Go for concurrently working through large numerous tasks, etc.)
Anyone not learning things via LLM coding right now either doesn't care at all about the underlying code/systems, or they had no foundational knowledge or interest in programming to begin with (which is also a valid way to use these tools, but they don't work very well without guidance for too long [yet]).
reply