A lot of these systems optimize for control, but not for behavior.
Once you introduce constraints (cost, limited context), the system starts behaving very differently — more like an economy than a pipeline.
The Zig project's rationale for their anti-AI contribution policy
301–310 of 496 posts
Re: The Zig project's rationale for their anti-AI contribution policy
#302Earlier quoted context omitted.
> Engineers who refuse to, or can't, or won't utilize the benefits that LLMs bring will be left behind. It's just the way it is. I'm already seeing it happening. Any examples how you see some engineers being left behind?
> Any examples how you see some engineers being left behind? I don't know where you live, but around where I live in Denmark you'd fail for not using AI at a senior interview in a lot of places. Even places which aren't exactly AI fans use AI to some extend. The biggest challenge we face right now is figuring out how you create developers who have enough experience to know how to use the AI tools in a critical manner…
Around here on your southern neighbour, everyone is supposed to be doing AI and being evaluated by this, yet in many projects if clients don't sign off on the use of AI tools, there is no AI to use anyway.
Additionally there are the AI targets set by C suites based on what everyone is saying on TV, and what we can actually deliver based on the available data sets, integration points, and naturally those sign offs for data governance, and hallucinations guardrails.
Re: The Zig project's rationale for their anti-AI contribution policy
#303Earlier quoted context omitted.
This mindset is fine (it's mine essentially too). But it absolutely has to be combined with verification/testing at the same speed as code production.
I generally do have that mindset, but over the past 1y of Claude code I do notice that I’m clearly losing my understanding of the internals of projects. I do review LLM generated code, understand it, no problem reading/following through. But then someone asks me a question, and I’m like… wait, I actually don’t know. I remember the instructions I gave and reviewing the code but don’t actually have a fine-details model…
I do think that this is natural. When you use LLM coding tools, you're becoming a lot more like an architect/staff/manager, rather than the direct coder. You're setting out the spec, coming up with the design, and coming up with the high level structure of the project.
However, this comes at the cost of losing track of the minute details of the implementation because you didn't write it yourself. I find it a bit analogous to code I've reviewed vs code I've written.
However, I've found using AI for code structure summary and questioning tends to be a good way to get around it. I might forget faster, but I also pick it up faster.
Re: The Zig project's rationale for their anti-AI contribution policy
#304Earlier quoted context omitted.
If that happens and we have a way of reliably knowing if some code is produced to that high quality, then I think we probably can accept that AI coding is the only sensible option. We definitely are not close to that point though and it's unclear if/when we will get there.
It seems to me that people might be arguing from conflicting hidden premises here. "AI Coding" is a spectrum that could mean something as simple as letting the LLM proofread your changes and then act on those with your own human brain, or it could mean just telling the agent what you want and let it rip and tear until it is done. If I do the latter and submit a PR to something like Zig, I'll be certainly caught doing…
Blanket banning all of these seems like a bad idea to me. It actively gates people like myself from contributing
in my projects i will reject any contribution that i do not understand. even if the contribution is handwritten by an expert developer. that developer will have to earn my trust like anyone else, like you would have too.
LLM contributions are non-deterministic, which means they can never be trusted.
therefore, if you use LLM to contribute, you can not earn my trust. if you believe that you can not create a meaningful contribution without the use of LLM then you are realizing that you are not skilled enough to understand the code that you contribute. because if you could understand it, then you could write it yourself. i want your personal contributions, not those of your LLM. i want contributions that the submitter actually understands. i want you to earn my trust by showing me that you understand what you are doing. i want you to grow your understanding of my project. none of this happens when you use LLMs.
if you are unable to make a contribution without the help of an LLM then you are not ready to contribute. try looking for smaller issues that you can work on instead until you learned enough to make larger contributions.
Re: The Zig project's rationale for their anti-AI contribution policy
#305Earlier quoted context omitted.
> Engineers who refuse to, or can't, or won't utilize the benefits that LLMs bring will be left behind. It's just the way it is. I'm already seeing it happening. Any examples how you see some engineers being left behind?
I'm starting to notice how those who don't use AI end up having to hand tasks over to people who can get them done quicker. It is anecdotal for sure, but it's a pattern that seems to be emerging around me that expectations of velocity increases, and those who don't use AI can't keep up.
Why is velocity the overriding goal?
Re: The Zig project's rationale for their anti-AI contribution policy
#306This is the great disconnect in thinking around LLMs right now. You have people saying they are so amazing, why wouldn't you use them? But if they are so amazing, why are you mad when someone won't accept the code they produce? Just ask the LLM to duplicate that whole project! Oh, it's not actually that amazing of a tool? Hmmm
The fact is, LLMs are incapable of invention and synthesizing new ideas. They can't contribute to the zig compiler because they have not been trained on the zig compiler, because it doesn't exist yet.
Yes, they can churn out simple apps, and quickly. That's a pretty useful thing, especially for people that don't know how to write code. But that's not as revolutionary as you think it is.
Others have mentioned the hype around 3D printing several years back. Kinda the same story. People thought manufacturing was dead, stores were dead. You'd just print everything you need yourself! Turns out it's not quite like that. It could still get to that point someday but these are hard problems that take time.
Similar with LLMs. It took us, what, 70 years of computer and AI research to get to this point? And people assume we're going to skyrocket way past this point in another year or two?
Re: The Zig project's rationale for their anti-AI contribution policy
#307Earlier quoted context omitted.
Right. It can enhance that skillset. Are you suggesting it can’t? This wouldn’t be a plausible position.
Rather that avoiding delegating it to LLM for these tasks helps you practice that skill. That said, I think it depends how you use it. You can learn from explanations, and you'd better avoid "rewrite this for me and do nothing else" kind of approach.
Right, but the LLM can help you practice the skill too. Without the LLM, you're in a self-guided, autodidactical mode. Obviously, that can have its own advantages, but most people—but especially novices—aren't in a position to assess their skill level or their progress. The average person isn't going to magically get better at thinking or writing without formal training, or at least some direction.
Re: The Zig project's rationale for their anti-AI contribution policy
#308Earlier quoted context omitted.
I'm firmly in the LLM fanbase. Not because I can't type code (was doing it for over 17 years, everywhere from low level hardware drivers in C to web frontend to robot development at home as a hobby - coding is fun!), but because in my profession it allows me to focus more on the abstraction layer where "it matters". I'm not saying that I'm no longer dealing with code at all though. The way I work is interactively wit…
This mindset is fine (it's mine essentially too). But it absolutely has to be combined with verification/testing at the same speed as code production.
I've found that for non-trivial features, I typically benefit from 3-4 rounds of: are you sure this isn't tech debt, are you sure this is thoroughly tested for (manually insert the applicable cases, because they aren't great at this, even if explicitly asked), are you sure this isn't re-inventing wheels, adding unnecessary complexity by not using existing infrastructure it should or that other existing code would not benefit from moving to this, are you sure you can't find any bugs, in hind sight, are you sure this is the best design?
Then, after it says, yes I'm sure this is production ready and we're good to move on, you have Codex and Gemini both review it one last time, and ask it to address their feedback if it's valuable or not.
After all this, it's the only time I'll look at the code and review it and make sure it's coherent.
Until then, I assume it's garbage.
I'd estimate this still improves velocity by 10x, and more importantly, allows me to operate at a pace I couldn't without burning out.
Re: The Zig project's rationale for their anti-AI contribution policy
#309[flagged]
Re: The Zig project's rationale for their anti-AI contribution policy
#310Earlier quoted context omitted.
You could extend that argument to any tool used by the developer, like a linter, sanitizer, the IDE itself, or even auto-completion. Why target LLMs specifically? The more I think about it, the more nonsensical it is. - What if I do everything by hand, but have an LLM review my work at the very end? - What if I have an LLM guide me through the codebase just by specifying the files I should read and in what order, but…
I think you’re missing the underlying point. The Zig team is focused on the contributor and their relationship to the project, not on the correctness of the work. People, not product. Yes, an LLM can help you better understand your code and pick up on things you may have missed before you submit your change. But I think they look at it as you’ve then robbed the Zig team of that interaction with the contributor. They…
My claim that LLMs can benefit the end product and create quality contributions does not imply that the person behind the contribution is less capable/creative/smart than someone who doesn't use LLMs.
But it seems that the Zig policy implies that. Otherwise what would be wrong with interacting with contributors using LLMs?