You also have your book and a wealth of online resources, which also don't require interacting with someone, and which have the same information the AI is trained on. Fundamentally nothing is different. We don't see positive outcomes from students using AI as an aid even if hypothetically it could be possible.
>For most uses the truck is better than the horse.
I think you're talking past the author here, who says:
>By not leaning into LLMs I’ve given myself the room to specialise in a smaller set of skills. So far that conscious decision is working out well, and I remain confident about my job security.
"Most uses" might mean boilerplate and simple frontend work that LLMs can do easily because it's formulaic and doesn't require much creativity. OP is simply not doing that type of work.
I don't think anyone sane is really claiming 100x or 1000x speedups anymore. Most people I talk to who use LLMs are closer to 1.5 or 2. Because their job is not mostly boilerplate, there is simply not that much room to be improved.
It’s not about speed-ups, it’s the fact that I’ll attempt a project far more ambitious than I would have in the past.
Over the past two months I’ve built out a very complex web app for a client. Without the aid of AI it would be far smaller, simpler and less capable. And honestly I probably wouldn’t have agreed to take on the job in the first place.
Sure, in the same way that nano is better than Microsoft Word.
Unfortunately, sometimes nano is not enough.
In the case of this client project, we are only now getting to enough functionality to be generally useful. The complexity that exists in the project is necessary complexity. A lot of coders are simply wrong about complexity, and feel it can always be reduced.
I think that the software world ought to fear and dread complexity, the same way that the Unix designers feared and dreaded verbosity.
«
Note the obsessive use of abbreviations and avoidance of capital letters; this is a system invented by people to whom repetitive stress disorder is what black lung is to miners. Long names get worn down to three-letter nubbins, like stones smoothed by a river.
»
there's no real difference between an excess of boilerplate and slop.
if your job is just writing boilerplate you're probably doing it badly.
if your app is so simple that really all you need to do is sling boilerplate then it might suffice but it's probably still the most unreliable way to develop that software.
if flakiness, bugginess and unreliability are all fine then yea, boilerplate away.
The "contributor poker" made by someone on the Zig core team is a good one. You're thinking from the perspective like yourself and how they might be affected negatively by this policy. The org is thinking about what's happening at scale and what policy is going to improve outcomes overall for them.
Are there some potential contributors who might be discouraged because of this policy? Probably. Will maintainers have less time wasted by obvious low effort changes and engagement? Also probably. A user of AI is, in the experience of many maintainers, way more likely to be lazy than engaged.
From a marketing perspective, I do not agree. The competitors can claim 100 more features than your "lean" code. That by itself makes you lose customers.
What kind of evidence do you expect beyond "random claims" here?
This post is incredibly obviously AI generated, to the extent that I doubt a human author edited it at all. Not "written with AI assistance" but full on "give Claude some bullets and hit publish." It contains tons of tropes that show up in all AI writing and which people are highlighting here.
As a comparison point, someone decided to try to fix the issues in the Zig original and is now claiming sub-second build times, plus fixed bugs, by modernizing the codebase and sticking with best practices - indicating that all of the issues that justified the rewrite were self-inflicted and addressable.
I have no skin in this game, and the Zig version is also using LLMs if that helps take the culture war out of it. But, it has always been true in my experience that someone who really understands a problem space can outcompete someone who just throws resources (in hundreds of thousands of dollars of token spend) at it.
> indicating that all of the issues that justified the rewrite were self-inflicted and addressable
The main issue that justified the rewrite were memory bugs, especially related to interaction with GC managed Javascript objects. There is no fully general way to prevent those bugs in Zig, and I don't see any claims that they did so in Buz.
They also complained about build times, and in fact the Rust rewrite started immediately after some other drama about Bun being unable to contribute back LLM-written changes to the Zig compiler to improve build times, and the Zig team rejecting them in principle. So while memory issues did become the focus later, I don't think it was the entire story.
Migrating to Rust in a one-to-one translation with unsafe blocks does not make the code any more safe initially. It might provide tools to do a significant refactor that solves lifetime issues with Rust's help, but I haven't seen evidence that they've done that either. They're also embedding a large C++ codebase, JavaScriptCore, so there are always going to be unsafe areas and touchpoints where memory issues could live, and Rust won't magically solve them.
It wasn’t just on principle that those changes were rejected, they also stated the bun changes were not actually that great or general enough to upstream.
> Bun is the quintessential AI slop project at this point. Inheriting that is no easy task. I don’t think any human should sacrifice their sanity untangling this mess of 600K lines of slop code. For that reason, I will not be accepting any human-coded contributions until I deem the project to be in a sane enough shape. It will likely require most subsystems to be rewritten.
They're refusing to accept human-authored contributions. They're using LLMs to do the work. The author says they'll use LLMs to de-slop what they think is slop, and humans are banned from contributing.
You're not making all the decisions in that case. You're making approvals and steering but the agent is making decisions and is framing what is even available to you to approve. When you build something by hand, you make decisions as you go in a way that the agent is now replacing.
