Comment by switz
8 days ago
It largely works and it's a massive business success. This is the classic engineer asking the 'why this technology?' to what amounts to a business question.
They chose it early on, it works, and it makes obscene amounts of revenue. End of story. That doesn't mean it was the "greatest" choice, or has a perfect technical architecture.
Rewrites are never easy, even the bun rewrite. But a non-UI developer tool with a rigid API surface contract (and associated tests) will always be easier to trust after a rewrite than a partially tested UI tool with ambiguous functionality.
>It largely works and it's a massive business success. This is the classic engineer asking the 'why this technology?' to what amounts to a business question.
Your counter argument would be valid for a 2000 or a 2020 business decision about some tech stack.
But the whole point of their product is that it supposedly nullifies such "business" concerns around the use of technology, by making it cheap and fast to build whatever you like automatically.
That they wont, or worse, couldn't, speaks against that.
Yeah, this is what I’m trying to get at.
There’s two arguments in competition:
1. LLMs make it cheap (in the time sense) and easy to build
2. Rewrites and/or writing something in a native app or program is harder and more time consuming
I think I am willing to take it as an axiom that a native version of CC would be superior from a user perspective. Performance, etc.
I just don’t see how one can say that building things reliably good is easy now when the company providing these tools can’t even do it well.
>2. Rewrites and/or writing something in a native app or program is harder and more time consuming
Why would it be harder and/or more time consuming rather than the opposite? It's like having full specs and a full test-suite to match against the result you want.
> I just don’t see how one can say that building things reliably good is easy now when the company providing these tools can’t even do it well.
What do you mean? Claude cli is wildly successful. Why do they need to re-write?
> I just don’t see how one can say that building things reliably good is easy now when the company providing these tools can’t even do it well.
I don't know how you can't see it, to me it's blindingly obvious: risk aversion.
Let's say the risk for a problem is 1%; hell, let's put it at 0.1% even. For a company at this scale even that amount of risk is too much.
I trust Opus/Fable to drive prod database migrations and backfills. I don't trust it with our financial ledger. I trust it with part of the infra. I don't trust it with backups. Etc.
You and others are arguing against a premise that nobody defended, namely "Claude can rewrite everything, for free and with zero mistakes". A bit of a straw man, don't you think?
And that's not even touching the fact that writing a GUI app is difficult for LLMs due to difficulties in it getting feedback and a "feel" whether it delivered what was asked (though I know people are working on it).
> I think I am willing to take it as an axiom that a native version of CC would be superior from a user perspective. Performance, etc.
How does that follow, and from where? I never once noticed any visual jank/lag in the TUI; not in iTerm2, not in Kitty, not in Alacritty, not in WezTerm and not in Ghostty. And even if we exclude those two, me and many other devs are quite fine with a TUI and don't miss a GUI program for everyday coding.
Not saying that our preference is superior -- but it'd be strange to blatantly claim: "for dev purposes, GUI > TUI/CLI".
3 replies →
> But the whole point of their product is that it supposedly nullifies such "business" concerns around the use of technology, by making it cheap and fast to build whatever you like automatically.
This is a spectrum, it's not just 0% vs 100%. Even Fable frakked up a few things really badly in my professional work (though to its credit after a very detailed 2h chat it self-corrected and fixed all the blunders).
I would also challenge "fast" -- Fable (and I assume Mythos) are wicked fast and efficient and even they can't compensate for f.ex. slow recompilations or test suite reruns or security scans, linters etc.
Reminder that the Bun's Zig-to-Rust rewrite took 11 days with dozens of agents working 24/7 and the author put the cost they'd pay (if they had to pay) at about $168k.
> $168k
Billions of dollars of annual revenue go through Claude Code, and the people who work on it must be a lot of millions in headcount.
The time matters a fair bit, it's probably time someone can't spend breaking things in the name of new features, but if rewriting the stack had even a tiny impact on retention or driving higher usage, it would pay back that $168k.
13 replies →
can't imagine rewriting a runtime to be easier than a coding harness
2 replies →
>Reminder that the Bun's Zig-to-Rust rewrite took 11 days with dozens of agents working 24/7 and the author put the cost they'd pay (if they had to pay) at about $168k.
For an entity like Anthropic that's not even the cost of a single developer for a year. It's closer to what they pay a chef on premises.
That the showstopper for a better Claude agent is that they'd need to pay $168k or event $1M or even $10M in costs, can't be used as an excuse.
7 replies →
It has to have been purely a marketing move. There's no other way that acquiring a software product for millions and then completely rewriting it makes any sense.
4 replies →
> Reminder that the Bun's Zig-to-Rust rewrite took 11 days with dozens of agents working 24/7 and the author put the cost they'd pay (if they had to pay) at about $168k.
Does anybody really believe that it only took 11 days, one engineer and $168k in tokens?
3 replies →
[flagged]
> by making it cheap and fast to build whatever you like automatically.
Cheaper, but not free (if you don't buy into the marketing promises too much). The bigger the project, the bigger the cost, even with a discount.
At the same time, the early versions weren't very good and you can be sure that any rewrite will also need to be similarly iterated upon until it is also good enough and polished.
If you do that and don't spend enough effort on making it be something polished --> your competitors have a better product and you lose.
If you pause feature development to give enough effort to the initiative, you don't get to add new features quickly enough --> your competitors have a better product and you lose.
Maybe their priorities lay elsewhere, like how I've noticed that the desktop app version of Claude Code has gotten both faster (no 2-4 second lag when switching conversations), more stable and usable over time, to where I enjoy using the models because of it, not in spite of it (though not that they haven't had bumps along the way, like that one cache invalidation issue, or how people didn't like the auto accept timeout thing). I don't doubt that you can get pretty far with gradual patches and improvements, instead of only big rewrites.
Honestly it's really cool for me to see Kimi having their own CLI too, same with OpenCode, Pi, Hermes (well more of an agent than just a coding harness but you get the idea) - there's so many competing solutions out there, each good or bad in unique ways.
Just wish we'd see similarly many GUI solutions, for now OpenCode GUI seems like the one I've settled on (cross platform and supports most models), though it's not exactly ideal either (feels a bit barebones, especially in regards to sub-tasks and progress/plan tracking, even ZCode seems a bit better in that regard, it was actually surprisingly good after they pushed out some updates).
Can't have been that cheap if they thought buying Bun for an undisclosed amount of money was cheaper.
3 replies →
How much extra money do you think they would make if Claude Code wasn’t JavaScript?
Right now? Zero.
In 2 years? A well-engineered TUI could be the difference between the Blackberry and the iPhone for all we know.
4 replies →
>making it cheap and fast to build whatever you like automatically
This can be true, while "nullifies such "business" concerns" can be false. Both are not dependent on each other.
Automation doesn't "nullify business concerns", it just changes them.
By the same argument, why does it matter from the technology stack side? It doesn't just nullify the business concerns - it largely nullifies the tech stack concerns. Your preference doesn't matter if you aren't touching the code and the product works for your user base.
> But the whole point of their product is that it supposedly nullifies such "business" concerns around the use of technology, by making it cheap and fast to build whatever you like automatically.
Eventually? I am sure they would agree. Currently it's you (and lots of people like you) who are doing the supposing, not Anthropic.
They succeeded in spite of their tech choices. Their model outshone it, which is an extremely rare thing to happen and not something they could've counted on. In any other timeline they could've/would've been hurt by their choices.
It's like "why did you go all in on buying scamcoin 3.0 as your investment strategy?" -- "I 5xed my money! End of story! It was fine!"
> They succeeded in spite of their tech choices.
Or those choices just don't matter, it's fundamentally just "tabs vs spaces".
As much as an enthusiast dev like myself hates it -- this is innately true, way too often.
I am 46 y/o and still excited to code and solve problems with code and I still have trouble to admit to myself sometimes that people make dozens of millions with PHP and the tech hardly matters when you can throw bodies at the problem (and when that throwing of bodies at the problem actually solves it, of course).
2 replies →
Apply this reasoning to any other industry. Yes the average person is not the judge of the quality of a doctor or engineer. That doesn’t invalidate it. You want a doctor who cares about medicine , not whatever will accomplish a business goal.
Eh, the rendering of Claude Code is genuinely such a mess. I have quit claude code over it because when used as a terminal in PHPStorm it sometimes gets so bad that it becomes hard to use.
This isn't a minor nitpick, it's a pretty major UX issue.
Not saying it's like a massive business downside because I'm just one of a few users, maybe this affects their bottom line a little bit, but probably not by much.
Regardless, switching to pi has been a nice breath of fresh air. It just renders well and smoothly and handles terminal resizes well, which is especially important when used in a terminal window in PHPStorm.
4 replies →
If they don't matter why isn't GTA6 being built in React?
Tabs vs spaces makes no tradeoffs. Tech choices do
The choices were clearly (far) less important than having the best model and a good product that was way ahead of the competition.
However, that's not the same as the technology choices not mattering at all. As others have mentioned the product is buggy, and it appears Anthropic are struggling to continue to release new features within the existing architecture.
That's also not to say that Anthropic made bad choices - there's always going to be a tension between building quickly to capture the market now vs moving slower and building something more maintainable in the long-term.
A TUI outputting nothing but text shouldn't consume 70 GB RAM and yet there they were just half a year ago: https://x.com/jarredsumner/status/2026497606575398987
They couldn't even fix flickering in their TUI and their new renderer is complete garbage.
They succeeded despite their tech.
>> They succeeded in spite of their tech choices.
It is rarely the case that technology choice is the make-or-break when it comes to whether a product is successful and achieves widespread adoption. Some choices are less ideal than others, but at the end of the day if you manage to make something that people want, the rest won't matter much.
What do you mean in spite of their tech choices? When have the tech choices ever been an issue in the lifespan of Claude Code? From where I sit, it seems like their tech choices enabled them to create an industry-defining product.
for about half a year claude code had this obnoxious flicker problem. i almost quit and went to codex over it.
I mean people are using Claude Code because of their underlying LLM - they'll put up with Claude Code. There's no other real option to get Opus at a reasonably affordable price without CC.
Most people would choose to swim a lap through a pool of pee to get a billion dollars at the end. The pool of pee itself wasn't the once in a lifetime opportunity (for most).
Sorry, I'm bad at analogies.
1 reply →
> When have the tech choices ever been an issue in the lifespan of Claude Code?
This is just blatantly ignoring all of the glaring issues Claude Code has had over its lifespan.
4 replies →
I have been working all day every day in Claude. I loathe their bug-ridden UI. Every release is a new crop of bugs, sometimes the old ones get fixed, usually not.
Any kind of scrolling back, copying text, using their menu system - basically anything that isn’t typing characters has had/still has unaddressed bugs.
OpenAI shipped a competitive model and I’m over in Codex now. I have yet to hit a bug.
If you’re holding the SOTA crown, people will put up with your buggy mess. As soon as that crown slips your pile of trash becomes a huge liability.
> basically anything that isn’t typing characters has had/still has unaddressed bugs.
Oh, that's buggy too. I just tried Claude Code on win10 powershell, and the first typed character goes in the wrong spot and can't be backspaced.
It is by far the the least reliable program on my machine, and every time I have to interact with it I feel like walking in eggshells.
> I loathe their bug-ridden UI.
So weird that the same exact people telling you that programming careers are now obsolete are the same group who haven't been able to fix screen flickering bugs for like a year...
Oh, and the memory use! I run a lot of concurrent sessions. 3 gigs for a terminal window is ludicrous.
The vim mode in that text box was a mess for sure
The criticism didn't appear to me to be that the solution didn't work, just that many of the working solutions we are selecting are dangerously overcomplicated due to shortsighted decisionmaking. The benefits of throwing redundant stacks of abstraction atop each other in terms of time to market are questionable, and obviously absent in every other metric.
So, you have a vibe-coded TUI which happens to work, and then, as a workaround you vibe-translate its engine to make it more performant. Where does that leave you ? Basically, fully dependent on AI to fix whatever breaks. Workaround on a workaround is the way I see it, and it aligns with the AI design mentality in general. For a variety of usecases, this might still be a win in terms of overall cost. But, for software that is intended to be built to last, I dont see this approach working out.
That does seem to be the way many use it. I'd be very surprised if they didn't have to insert a rule to prevent opus from constantly asking why they didn't just use ncurses. I just asked sonnet for design options for a tui to onteract with llms to perform sw dev tasks. After describing the tui it immediately suggested ratatui and crossterm as the tech stack. I feel like they must have ignored even the advice of their own llm to come up with this solution.
Edit, the sonnet question shouldn't be taken as proof, it knows I'm a rust dev.
2 replies →
Bun was not ported to Rust for performance reasons and its not clear to me how anyone can think it was. The reason they've given is memory safety.
4 replies →
I'm going to guess Anthropic are OK with "fully dependent on AI to fix whatever breaks".
> for sw that is intended to be built to last, I dont see this working out.
the era in which the tech industry built software to last was over long before LLMs, especially VC-backed startups.
2 replies →
Correct
And the question of “if AI is so amazing, shouldn’t it enable easy development of a native TUI even if JS is easier at first?”
Don’t get me wrong I find great value in coding agents daily. Just finding the hype cycle tiring.
This reply makes no sense in this context, though. Sure, it exploded in popularity based on whatever random tech choices were made. But now, when apparently they're deciding there's a problem there, why unleash $150k of tokens to rewrite a JS runtime wrapper from Zig to a million lines of rust, rather than simply rewrite Claude Code itself to rust?
They probably should rewrite it in Rust, but also, I think the Bun guy wanted to rewrite it in Rust because he thinks Rust is a better choice for Bun, independent of Bun being used by Claude Code.
This speaks for the benefits of JavaScript runtimes like Bun and Node.js. JavaScript is a dynamically typed language which makes it a good choice for explorative programming. It is a Lisp in sheeps' clothing.
Programs which need more stability and performance than exploration are better done in statically typed languages like Rust. Therefore Bun is a platform for JavaScript programming, but itself is written in Zig or Rust.
This is the “eating yogurt with a hammer” argument. Yes, of course you can do that. Yes, the yogurt gets eaten. It’s just… you see someone eating yogurt with a hammer and it’s hard not to wonder wtf is going on.
> It largely works and it's a massive business success.
I'd argue these tech companies got popular because they have good models, nothing else.
Even OpenAI took two years to fix basic chat scrolling.
Claude code still can’t handle scrolling history without corruption. It is embarrassingly broken.
> “It largely works”
A ringing endorsement!
> It largely works and it's a massive business success.
The engineer is suggesting that it could be done cheaper and maybe with better outcome. Ironically, this is a classic business case.
...while proving their technology has finally reduced these questions down to what's best, instead of "how much effort will it take to be good enough".
If you have unlimited access to the magical development tool, then why would you not?
But they haven't.
This is a useless post-hoc rationalization. "It worked out, so it doesn't matter". You're trying to galaxy brain yourself into ignoring the obvious conclusion.
The point is that if you were starting a new TUI LLM harness today, you would basically use CC's architectural decisions as a guide for what not to do.
> It largely works and it's a massive business success.
You can make anything work when you have enough money to buy and radically change the entire runtime you’re relying on.
One must suspect that if they did not have insane amounts of money to burn, they could have tried other approaches to fixing the problems. Maybe engineering, perhaps.
I disagree, Solid Fuel.
Nobody cares what a bot account thinks.
For a company that solved coding and doesn't need any software engineers… why spend money to acquire a runtime rather than ask claude to rewrite it in assembly directly and be done with it?
Could it be that they aren't being entirely honest?
Massive business success? I don't know the financials since they're not published, but google says the acquisition cost low hundreds of millions. So they could throw away the code and rewrite it.
This is far less so in this case because this is thier hot path. Everything runs through it and tens of billions in revenue depends on it. It needs to be as fast and solid as possible
This is a confusing comment because it’s the exact argument you would present against rewriting Bun to Zig, but you are arguing for one and against the other.
As an industry we are responsible for making our part good. So yes a business can succeed in spite of bad tech choices, but that doesn’t make it good tech.
It doesn’t work, it performs horribly and is full of bugs. Serious people use open harnesses.
Any choice would have made obscene money in this market. It doesn’t make it a good choice.
No, it's because they wanted a unified pipeline in claude code, claude app, and their website. All of them use more or less the same claude features (claude code has artifacts, claude website has "Ask User a Question" tool, etc.).
Much less fragmented compared to "write the app 3 times in 3 different languages".
I think it makes sense that when you've outlawed competition for many/most users of your product's matching service that you would cheap out on it if you were maximally extractive and took no pride in your work, sure.
But the "coding is mostly solved" narrative kinda doesn't match right? If good, correct, high-performance software is like, free now? Wouldn't you want it to be slick as hell, really reliable, all that? Even a little breakage costs a lot of money at that scale and pricing, it would be better than a wash if you put the magic code thing on the case.
"Claude. Do all employee work. Make no mistake. Notify in slack when revenue is double."
So Claude isn't great for everything?!?
[dead]