| ▲ | pdimitar a day ago |
| > 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. |
|
| ▲ | hyperpape a day ago | parent | next [-] |
| > $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. |
| |
| ▲ | sscaryterry 20 hours ago | parent | next [-] | | If only paying the $168k was some sort of a guarantee. Vibing doesn't give you that. You might get more maintainable code for $168k by hiring humans, but if its something bespoke it isn't going to get you far (or far quickly). Vibing is straight out gambling right now, the thing is, I don't know who the house is any more. | | |
| ▲ | nomel 18 hours ago | parent | next [-] | | It's going to take an order of magnitude longer though, delaying any of that revenue significantly. I'm sorry, but we're talking 11 days here. What does "maintainable" even mean with impossible time-scales like this now!? | | |
| ▲ | sscaryterry 18 hours ago | parent | next [-] | | The new normal is there is no normal. No common sense, FOMO, YOLO, everything combined is what we're living right now :) | |
| ▲ | nkrisc 17 hours ago | parent | prev [-] | | Perpetual complete rewrites. When there’s more bugs the LLM can fix, rewrite the whole codebase. Repeat ad infinitum. | | |
| ▲ | pdimitar 17 hours ago | parent [-] | | True on the premise, remains to be seen if that's what's going to happen in practice. In my work I have Fable/Opus add bespoke linters and tie them to verify/precommit tasks (including in CI) so nothing of the reworks and 15+ initiatives we have in flight ever regresses. Some discipline will remove that worry of yours. It's not nice to immediately assume that the rewrite's orchestrator (Jarred) did not use discipline. He even outlined a few false starts. |
|
| |
| ▲ | throwaway7783 17 hours ago | parent | prev [-] | | .. by hiring the right humans - which is not always a given | | |
| ▲ | pdimitar 17 hours ago | parent [-] | | Even worse: it's much safer to assume you'll hire the wrong humans, most of the time. |
|
| |
| ▲ | pdimitar a day ago | parent | prev | next [-] | | Yep, same thought. And it seems Anthropic agrees. | |
| ▲ | NDizzle a day ago | parent | prev [-] | | The company I work for is about 15mm into what is effectively a rewrite. Just a lone data point… | | |
|
|
| ▲ | mobelkh 19 hours ago | parent | prev | next [-] |
| can't imagine rewriting a runtime to be easier than a coding harness |
| |
| ▲ | usef- 18 hours ago | parent | next [-] | | You might be surprised. Runtimes can be easier to test than UI for AI, and the bun rewrite was almost line-for-line translation, whereas CC likely uses many more libraries that cannot be ported directly. The major open harnesses are in the ~800k lines of code size ( https://simonwillison.net/2026/Jul/15/grok-build/ ) and CC is the oldest and quite-likely largest judging by features. | |
| ▲ | pdimitar 19 hours ago | parent | prev [-] | | It's really not about a PL runtime vs. an agent harness, it's about how spaghetti and complex the code is. I do get your point though. |
|
|
| ▲ | coldtea a day ago | parent | prev | next [-] |
| >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. |
| |
| ▲ | jbvlkt 20 hours ago | parent | next [-] | | Lets see what happens in the future. From my experience cost of maintaining this amount of shitty code explodes pretty quickly. We will see in a few years if SW development in all phases using agents is that much automated and easy as people now predict. | |
| ▲ | hluska 21 hours ago | parent | prev | next [-] | | Do you know their entire roadmap? If not, maybe different people prioritize things differently when they see their full strategic position. | | |
| ▲ | coldtea 21 hours ago | parent [-] | | How is that relevant to my response? The argument I responded to argued that cost might be the prohibiting factor. I'm saying that for them, the costs mentioned are negligible. | | |
| ▲ | pdimitar 17 hours ago | parent [-] | | I didn't claim that the cost is the prohibiting factor at all. Obviously they gave Jarred free Fable access and to do as his pleases. The cost was an FYI tidbit and nothing more. What I argued was that you seemed to have been arguing an extreme point i.e. LLMs can one-shot stuff in any PL and that it does not matter in what PL they'd rewrite Bun. If I misunderstood -- my apologies. | | |
| ▲ | coldtea 8 hours ago | parent [-] | | Well, I never said anything about one-shotting it. What I said is, those AI companies push LLMs as the replacement of programmers, that can do everything code-wise, say their programmers "don't write code anymore" etc. So how come they can't have the LLM write something better than "react for cli" for their flagship agent product? | | |
| ▲ | pdimitar 8 hours ago | parent [-] | | My only half-decent guess: they deem it too big and risky and believe they'll lose revenue while working on it and ironing out remaining kinks. Claude Code is likely not well-specified and it's a product of rapid iteration and now nobody really knows how the whole thing works. LLMs don't do well when requirements are muddy. |
|
|
|
| |
| ▲ | pdimitar a day ago | parent | prev [-] | | I don't work for them and I don't know their priorities. I can only speculate they're not okay with it but no idea why exactly. |
|
|
| ▲ | TurdF3rguson 18 hours ago | parent | prev | next [-] |
| 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. |
| |
| ▲ | pdimitar 18 hours ago | parent [-] | | Maybe it's one of the cases when techies call the shots? I can understand people being more sold on Rust compared to Zig -- there are legitimate differences on the memory safety front and I can see how people will prefer one or the other. Plus I believe Jarred (Bun's main dev) went out of his way to explain why he chose Rust over Zig in his blog post. Of course the marketing angle might indeed be the explanation; not arguing against that, I simply followed with interest and Jarred seemed very reasonable to me. | | |
| ▲ | TurdF3rguson 18 hours ago | parent [-] | | The rewrite makes sense, it's all their dog food at that point. It's the acquisition that doesn't make sense. Why didn't Anthropic just rewrite it themselves? | | |
| ▲ | pdimitar 18 hours ago | parent | next [-] | | Good question. I'd guess they didn't want community split? | |
| ▲ | tonyhart7 17 hours ago | parent | prev [-] | | "Why didn't Anthropic just rewrite it themselves?" they rewrite themselves, Bun team is under Antrophic umbrella |
|
|
|
|
| ▲ | shafyy a day ago | parent | prev | next [-] |
| > 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? |
| |
| ▲ | simonw 21 hours ago | parent | next [-] | | It played out in public on the GitHub repository, so yes. | |
| ▲ | pdimitar a day ago | parent | prev | next [-] | | I know what Fable did for just 5x6h sessions, singular agent, for my professional work. Jarred used many agents and they worked 24/7. It tracks for me. So yes, I do believe it. What makes you skeptical? | |
| ▲ | greenavocado 6 hours ago | parent | prev [-] | | 100% believe it. I use multi agent orchestration within oh-my-pi and it can absolutely do targeted things like this. |
|
|
| ▲ | BedVibe_Studios 16 hours ago | parent | prev [-] |
| [flagged] |
