scuff3d

The biggest reason is I don't like being locked into an ecosystem. I can use whatever I want with OpenCode, not so much with Codex and Claude Code. Right now I'm only using GPT with it, but I like the option.

CC I have the least experience with. It just seemed buggy and unpolished to me. Codex was fine, but there was something about it that just didn't feel right. It seemed fined for code tasks but just as often I want to do research or discuss the code base, and for whatever reason I seemed to get terse less useful answers using Codex even when it's backed by the same model.

OpenCode works well, I haven't had any issues with bugs or things breaking, and it just felt comfortable to use right from the jump.

Drives me nuts that we have TUIs written in friggin TS now.

That being said, I do prefer OpenCode to Codex and Claude Code.

I kept YouTube as well, but I tend to use it more as a podcast app then a video app. I try to only listen to it when I'm doing other stuff like doing dishes or walking the dog.

That's interesting that you have problems with notifications. I'm on Android and if I turn them off they've pretty reliably stayed off. I don't even get notifications for emails. Just calls, texts, and a few important ones like my credit cards notifying me when they're used.

I quit all social media (unless you count hackernews I guess), killed all notifications except calls and text messages, and regularly leave my phone in another room while I'm working or doing anything that requires prolonged attention. Helped a lot.

They're kids... Even in some dystopian ass scifi future we all have implants in our eyes or some shit, we aren't doing that to kids...

We're talking about kids, not adults. You ban cell phones for the same we weren't allowed to play our Gameboy during class when I was a kid. They lack the self control and decision making capabilities to forgo something fun for the sake of something important.

Not to mention we have plenty of studies that show even a silent phone sitting quietly in your pocket or on your desk can be an attention drain, as you're subconsciously waiting for a notification to go off.

I'm amazed it took this long for the schools to finally ban the damn things.

My wife and I always go in with a list of exactly what we need and stick to it. If you give into the impulse buys it kills any savings you would get from shopping there.

Good luck with that. I haven't been successful at convincing anyone to move away from it. I'm so fucking sick of writing Python at work lol

That's kind of like saying Cargo is a small part of the Rust ecosystem.

It's not there yet, but it's getting there.

That's not really my point.

If you use it that way fine, but in general I'm talking about the idea that can you plan throughly enough in advance to get it to produce tens of thousands of lines of quality working code.

Like the author of the article points out, that takes so much effort by the time your done you may as well have just written the code.

I recently left this comment on another thread. At the time I was focused on planning mode, but it applies here.

Plan mode is a trap. It makes you feel like you're actually engineering a solution. Like you're making measured choices about implementation details. You're not, your just vibe coding with extra steps. I come from an electrical engineering background originally, and I've worked in aerospace most of my career. Most software devs don't know what planning is. The mechanical, electrical, and aerospace engineering teams plan for literal years. Countless reviews and re-reviews, trade studies, down selects, requirement derivations, MBSE diagrams, and God knows what else before anything that will end up in the final product is built. It's meticulous, detailed, time consuming work, and bloody expensive.

That's the world software engineering has been trying to leave behind for at least two decades, and now with LLMs people think they can move back to it with a weekend of "planning", answering a handful of questions, and a task list.

Even if LLMs could actually execute on a spec to the degree people claim (they can't), it would take as long to properly define as it would to just write it with AI assistance in the first place.

Oh boy, if anyone thought productivity hacks, ultra optimized workflows, and "personal knowledge management" systems could get ridiculous, they haven't seen anything yet. This is gonna be the new thing people waste time on now instead of their NeoVim config.

It's not that simple, some markets are slowing down and others are accelerating.

Two of Honda's biggest markets are Japan and the US. The US is cooling on EVs with incentives and regulation changes making adoption less urgent. Japan already has an extremely low adoption rate. So the incentives for Honda to invest heavily just aren't there right now.

Other manufacturers are also pulling back. Ford is cutting way back on the Lightning for example.

But it's not really increasing anymore, and the increase has been almost entirely tied to subsidies. When Germany and America pulled back on EV subsidies, sales dropped significantly.

The adoption curve hasn't been nearly as steep as predicted, and the political landscape is unstable. Other manufacturers are also pulling back on their EV investments.

I'm not saying Honda isn't overdoing it, but a retreat from EVs isn't surprising.

Yeah I agree that it's not copy/pasted the way a dev would, but I think the end result is the same. The more it needlessly duplicates code, the more brittle things will become. Changes will get harder and harder to implement as the number of sites that have to change increases.

On the other hand, I think driving down the need for external dependencies can be a net win. In my experience you usually need a very tiny slice of what a dependency actually offers, and often you settle for making design compromises to fit the dependency into your system, because the cost of writing it yourself is too high. LLMs definitely change that calculus.

I've found agent.md files are more a bandaid then anything. I've seen agents routinely ignore/forget them, and the larger the code base/number of changes they're making the more frequently they forget.

Code duplication is normally referring to duplicate code within the same code base, not writing something yourself instead of using a library.

To add to the person who quotes the relevant part of the study, they also point that the velocity increase disappears after a month or two.

I work in an extremely security minded industry. There are strict guidelines about what we can and can't use. JetBrains isn't excluded for technical reasons, but geopolitical ones.

The AI models we use are all internally hosted, and any software we use has to go through an extensive security review.

Can't use JetBrains products at work. I also unfortunately do most of my coding at work in Python, which I think can confound things since not everything is typed

Yeah, it usually gets the required args right based on various pieces of context. It have a big variation though between extension. If the extension can't pull context from the entire project (or at least parts of it) it becomes almost useless.

I've gone back and forth on it a lot myself, but lately I've been more optimistic, for a couple of reasons.

While the final impact LLMs will have is yet to be determined (the hype cycle has to calm down, we need time to see impacts in production software, and there is inevitably going to be some kind of collapse in the market at some point), its undoubtable that it will improve overall productivity (though I think it's going to be far more nuanced then most people think). But with that productivity improvement will come a substantial increase in complexity and demand for work. We see this playout every single time some tool comes along and makes engineers in any field more productive. Those changes will also take time, but I suspect we're going to see a larger number of smaller teams working on more projects.

And ultimately, this change is coming for basically all industries. The only industries that might remain totally unaffected are ones that rely entirely on manual labor, but even then the actual business side of the business will also be impacted. At the end of the day I think it's better to be in a position to understand and (even to a small degree) influence the way things are going, instead of just being along for the ride.

If the only value someone brings is the ability to take a spec from someone else and churn out a module/component/class/whatever, they should be very very worried right now. But that doesn't describe a single software engineer I know.

The only part AI auto complete I found I really like is when I have a function call that takes like a dozen arguments, and the auto complete can just shove it all together for me. Such a nice little improvement.

Unfortunately, there is a fairly large part of the population who disagrees with that.

Right, because the same people who vibe coded their applications are the same people who take the time to setup robust infrastructure to allow for easy roll backs.

No languages are perfect, they all make tradeoffs. I just like a lot of the ones Go made.

Go and Rust try to solve very different problems. Rust takes on a lot of complexity to provide memory safety without a garbage collector, which is fine, but also unnecessary for a lot of problems.

Yeah that bothers me too, but it's damn hard to get away from these days. Most language projects have significant corporate involvement one way or the other.

Go is criminally underrated in my opinion. It ticks so many boxes I'm surprised it hasn't seen more adoption.

Can you imagine the absolute mayhem at Fox News if Obama had declared himself the greatest president of all time.

Or declared a US company a supply chain risk after trying to weasel out of a contract.

Or, you know, incited a terrorist attack on the US Capitol...

Go and Java/C# (if you forgo all the OOP nonsense) aren't much harder to write than Python, and you get far better performance. Not all the way to Rust level, bur close enough for most things with far less complexity.

We're 6 months away from some company's app/infrastructure/whatever going down and staying down, because literally nobody knows how the 500,000 line code base works and Claude is stuck in a loop.

Figures, gotta keep that grift going somehow...