Zig Creator Calls Spade a Spade, Anthropic Blows Smoke • Hacker News Board

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#781

Post by theamk » Tue, Jul 14, 2026, 2:50 AM UTC

mikey_p wrote: post #715

budsniffer952 wrote: post #491

Earlier quoted context omitted.

> Call a spade a spade, the rewrite was poorly justified In what world do you think they have to justify a rewrite to anyone outside their company? Bizarre mentality.

They didn't have to but Anthropic chose to open their mouth and announce their "reasons" for the rewrite. Don't blame anyone but Anthropic for this, they didn't have to try to justify it, but they decided to anyway.

Sure that had to justify it, people were writing all sorts of posts about how Bun was no longer trusted since it was rewritten with Rust.

Bun's post was explanation of that process that was (IMHO) pretty reassuring in that the new version of Bun is not 100% garbage.

(Now in the ideal case that post would be released before, or at the same time as, rust-based source code on github... Then there would be much less drama)

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#782

Post by Ygg2 » Tue, Jul 14, 2026, 2:51 AM UTC

RetroTechie wrote: post #649

Ygg2 wrote: post #301

Earlier quoted context omitted.

It's funny, but I think the article is showing it's age. It's no longer true. In hindsight having automated auto complete rewriting your code base wasn't something on 2000's radar. Now switching from language to language is much easier. Just for Rust, there was Ladybird and Bun complete rewrite, that ran into zero things that Joel rallied about.

> It's funny, but I think the article is showing it's age. It's no longer true. Joel argues 2 effects: # Developer & time-cost of a rewrite is a big unknown. That's still true, but LLMs may cut that down by a factor of 10x or more. You cut time & developer-hours by throwing tokens ($) at it. An optimist might say this cost has vanished. # Shipping a rewritten product is -by itself- an unknown risk. That still holds.…

> Developer & time-cost of a rewrite is a big unknown... An optimist might say this cost has vanished.

I wouldn't say it vanished. I'd say it moved from unknown to known. It's highly likely that for code the size of Bun the price is around 200k dollars of tokens + a month of programmers time to monitor it.

> Shipping a rewritten product is -by itself- an unknown risk. That still holds. You can do all the testing you want, but your test suite != your clients environment(s? multiply by number of users or target platforms).

Fair point.

That said, it seems the number of relevant platforms is shrinking. Both on the hardware side - x86_64 AMD, x86_64 Intel, and aarch64. On the OS side, you have Linux, Mac and the dying Windows.

Still, it seems with enough tests and original source code, you can limit this risk to a few edge cases.

> All in all Joel's article held up pretty well

Aside from the fact that it mostly applies to commercial endeavors[1], it still missed the mark on old code decaying over time.

Turns out being exposed to the Internet has a chance to turn even old code sour.

[1] If you don't care about your users, or you care more about pleasing/attracting new developers, then points made in his article don't make rewriting it that bad.

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#783

Post by ozozozd » Tue, Jul 14, 2026, 3:07 AM UTC

jeremyjh wrote: post #141

This paragraph is written by AI. I did not notice it earlier in the piece: > The piece about the migration process is very cool, with details that are reusable. No complaints, I think that’s the real contribution here. I particularly like the honesty in explaining that this was a port to unsafe Rust, allowing a literal file-by-file migration to minimize risk, paving the way for redesign in future steps. That’s a sens…

Pretty sure this section’s title was “Say something nice”

…he had to resort to AI for this part.

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#784

Post by ozozozd » Tue, Jul 14, 2026, 3:11 AM UTC

handoflixue wrote: post #188

"We wrap LLMs in Agent harnesses because AI isn’t enough." This feels equivalent to saying you're not a real coder if you need a compiler to hold your hand. What, a human coder isn't enough? Of course we're going to improve tools by building more tools on top of them. That's how we went from punch cards to assembly to high-level languages!

Umm, yeah.

Obviously the neckbeard who wrote C in vim and compiled when he is done is a better coder than the one who kept compiling and fixed issues when told by the compiler.

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#785

Post by asdf88990 » Tue, Jul 14, 2026, 3:13 AM UTC

asdf88990 wrote: post #353

mbesto wrote: post #344

Earlier quoted context omitted.

You can't unilaterally say all AI blogs are low quality. That's bullshit. > would spend more time writing than I would have to spend reading To your point however, the reason people don't like AI generated blogs is because there is a explicit recognition that the author of the blog lacked effort . There is a visceral response for the reader about the social contract "if you didn't spend as much time as I did why shou…

> You can't unilaterally say all AI blogs are low quality. That's bullshit. Quality is a bit nuanced but that quality of AI generated content is subpar to expert output is fairly established. The implications of this ever becoming false amounts to GAI.

AGI*

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#786

Post by jdiff » Tue, Jul 14, 2026, 3:15 AM UTC

selfmodruntime wrote: post #439

p-e-w wrote: post #181

Earlier quoted context omitted.

> I think the Zig people are really just concerned that maybe Zig itself is a DOA language because it doesn't offer enough over C for any serious use and their flagship project has now abandoned it. You hit the nail on the head there. Zig is 10 years old now and it’s pretty clear that the industry isn’t biting, compared to the behemoth that is Rust. Between Rust, C, and C++ there is very little room for another langu…

The industry isn't biting @ Zig because it's unstable, notoriously difficult to integrate new changes into an existing codebase and because the compiler is a bitch to develop with (hard error on unused variables with no way to turn it off).

Not sure that last one rings true. There are entire languages with no allowed unused variables (some without prepending a _ to the names) that people love to develop with.

In the industry, how often is it that a tool/language is picked up for the ease of developing that tool, vs ease of using that tool?

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#787

Post by deaux » Tue, Jul 14, 2026, 3:36 AM UTC

foobarchu wrote: post #759

deaux wrote: post #421

Earlier quoted context omitted.

Yes and no. Let's first settle on the definition of vibecoding so that we're not miscommunicating over definitions. I'm using the one that seems the median definition nowadays: >95% of the code written by LLMs, As you said it's about time invested in thinking about it, yes. But remember that even pre-AI >90% of software got never used, it was dead on arrival. Look up "success rate of software projects in business". Y…

I hate to be the guy arguing semantics, but is that the median definition? Everyone I know defines vibe coding as ignoring the actual output code completely and evaluating the result by how it behaves under test. Non-coders vibe code by default, because they don't understand how to read the code in the first place. Developers vibe code when they just trust the LLM to have been right about the behavior they don't expl…

It is. There are many people on here who think of having any LLM generated, never-human-reviewed code in the codebase, as vibecoding. There are also people like you, who believe it's about completely ignoring it, and even human-reviewing 10% of the code means it's not vibecoding. The median definition, at least on here, is somewhere in the middle, around "a large portion of the code is never looked at by a human".

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#788

Post by lolinder » Tue, Jul 14, 2026, 4:03 AM UTC

simjnd wrote: post #747

lolinder wrote: post #514

Earlier quoted context omitted.

The example shows three extra lines of code, two of which are `defer`s. I'm not an expert in Zig and can't tell you whether the example they give is contrived, but the claim they're making is way more than "a wrapper type". > And that is considering humans write the code manually. Why does it matter if agents write the code? This makes no sense. Because the particular form of non-ergonomic code that is demonstrated h…

A wrapper class if you want, a wrapper type with methods / dedicated functions. Still, seems pretty ergonomic to me. Yeah we went from one line to three, but the three lines guarantee safety whereas the one doesn't so? Also I'm not sure the token count is very relevant for an Anthropic employee who just spent 165k worth of token rewriting the whole thing in Rust. Sprinkling a few defers here and there and swapping ty…

You're failing to distinguish between token count spent and context window used.

You're correct that the former is not a concern for Anthropic, but it's also not the problem I'm pointing out.

The actual is not token count, it's context window. Your context window is finite, and every token you add to it reduces the model's accuracy during inference.

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#789

Post by handoflixue » Tue, Jul 14, 2026, 4:06 AM UTC

oblio wrote: post #321

BetterThanSober wrote: post #280

Earlier quoted context omitted.

I agree that "coding" isn't solved but LLMs needing a harness is not necessarily a huge hit on AI As for valuation, it's all a grift, always has been for anything hip in tech. SpaceX should've been in the $500b range and they have an actual rocket and working satellite constellations

LLMs needing harnesses is a hit on AI because it means LLMs can't be extended a lot (or indefinitely as AI boosters hope). We're back to (enhanced) expert systems from the 80s and nobody is excited about those. And regarding SpaceX, SpaceX even without xAI didn't make a ton of money and it's business initiatives are super long horizon things. Moon bases won't be profitable for at least 10 years and Mars bases probabl…

Coders needing compilers is a hit on coding because it means coding can't be extended a lot?

I'm just not following the logic at all.

We build vastly more ambitious software today than we did in the 80s

Re: Zig Creator Calls Spade a Spade, Anthropic Blows Smoke

#790

Post by handoflixue » Tue, Jul 14, 2026, 4:10 AM UTC

ozozozd wrote: post #784

handoflixue wrote: post #188

"We wrap LLMs in Agent harnesses because AI isn’t enough." This feels equivalent to saying you're not a real coder if you need a compiler to hold your hand. What, a human coder isn't enough? Of course we're going to improve tools by building more tools on top of them. That's how we went from punch cards to assembly to high-level languages!

Umm, yeah. Obviously the neckbeard who wrote C in vim and compiled when he is done is a better coder than the one who kept compiling and fixed issues when told by the compiler.

The neckbeards that wrote C did so precisely because they saw how C was a better way to get things done, and they were probably the first people to start using compilers, because, again, they're the ones that built them.

The neckbeards that wrote C tend to view LLMs as the obvious next step, and a lot of them actively use them for hobby projects even if they're not quite "maintain the Linux Kernel" tier yet.