> This Rust rewrite would've taken a team of engineers with full-context on the codebase a year of work. With 1 engineer using Fable & closely monitoring Claude Code, we went from start to 100% of the test suite passing on all platforms in 11 days.
This is impressive from a technological standpoint, but it does gloss over the fact that it would have cost $165k in tokens were Bun not part of Anthropic.
The comparison here isn’t completely fair - it would take a small team a year to port it if they spent $0 extra on it.
I’d be interested to see a comparison between spending $165k in 11 days on Claude vs splitting that between 50 people over 11 days for a line-by-line rewrite of the Zig code. I suspect Claude might be faster and therefore cheaper, but maybe not by a lot.
They napkin math is fairly easy to do. One human works around 250 days per year, and if we assume Bay Area salaries we could assume ~300k/y conservatively for a fully loaded cost.
$1200 per day.
Your estimation is 50*11 days so $660,000. That’s 4x what Claude cost.
That’s assuming that you actually get those 50 people to work without blockers, stepping on each other, or other coordination issues. The coordination complexity alone is astounding.
I don’t like it necessarily, but Claude wins here, easily. It’s not close.
Unless you hire smart people from EU and what have you (especially ex-USSR)
Which takes us to a point of future US dev salaries if this thing with agents gets better more and more
Sure, but can we not work out how to make humans more efficient for less money? There are obvious optimizations there that none of us would like to be part of.
Humans can't become 100x efficient cost wise. That's how cheap LLMs are.
Less money? Cost of living is much lower in EU
> That’s assuming that you actually get those 50 people to work without blockers, stepping on each other, or other coordination issues. The coordination complexity alone is astounding.
This is a question of exceptional management, which needs to be present both in the Claude and human cases, and is scarce. Not everyone given the Claude tokens would be able to deliver the same result.
Why assume the upper level salary here? Using senior level developers making astronomical salaries for what is a mechanical line-by-line port would be a poor financial decision.
What does the math look like with 25 devs making ~100k and doing it in 22 days? I’m sure you could find a reasonable combination which costs less. And if you’re already paying the devs the salary, it’s basically free (minus the opportunity cost of them not working on other things).
> Why assume the upper level salary here?
Even a junior is going to cost you $200k by the time you're done paying payroll taxes, healthcare, etc.
Nonsense. Junior salaries are on the order of $50k in the UK. There's no healthcare to pay, but employer taxes and overheads might be around 30%, so you're talking way under $100k.
I think it'd take you at least eleven days to meaningfully coordinate 50 people!
I feel like a core difference is that the AI implementor can get cheaper/faster (and indeed _uniformly_ better), whereas it would be very difficult for the same humans to do so.
Even if this is not the right answer today, it can at the very least serve as a herald of a possible future, no?
Your example of using 50 people for this reminded me of the classic “Nine women can’t make a baby in one month.”
HINT: those 50 people must be coordinated...
> I suspect Claude might be faster and therefore cheaper, but maybe not by a lot.
While Jarred used Mythos-class model, some open weights, if they were as capable (certainly, GLM 5.2 looks the part), would have been way, way cheaper than professionals.
Approx costs:
I did some more sizeable work with GLM 5.2 on Max reasoning (planning and implementing 8 features end to end) and it performed pretty well, but worse than Opus 4.8, with largely the same adversarial agent review loop.
Opus 4.8 still found some real issues afterwards and spent about an hour fixing things, before the code was good enough to ship. Overall promising, wrote about it here: https://blog.kronis.dev/blog/z-ai-s-glm-5-2-is-a-great-model...
The GLM Coding Plan seems to have lower token limits than the corresponding Anthropic Max subscriptions, but if you had to pay API rates for some LLM to do work somewhat reliably, it's a no brainer (unless you're swimming in money that you can give away and value your time more).
But not all models are equally capable, so I don't know your basis of comparison is even valid, let alone the numbers.
$165k won't get you far on salaried engineers. There's every chance that 1 engineer, assuming Anthropic employs them, is on $500k or more. Assuming average of $336k in that pool of 50 engineers, then for 11 days for 50 engineers you've spent $710k[0].
Salary info: https://www.levels.fyi/companies/anthropic/salaries/software...
[0]The maths I used (posting because I'm tired and prone to mistakes):
You don't need top engineers to port a program from one language to the other. Outsource it to India.
Of course, then you can also ask, could it have been done with a cheaper model. Probably yes. But then you wouldn't get free marketing.
I agree you probably don't need top-dollar bay-area engineers for this, but hardcore outsourcing to a LCOL probably isnt going to work either due to novelty and generally being setup to do the more rote thing (generalizing a ton here obvi). This feels like something in the middle.
Outsourcing to India would actually be the disaster the naysayers were saying this would be.
Have you seen the "rewrite by outsourcing to India" thing work?
What a weird thing to say. The phrase “outsourcing to India” being used as shorthand for “you don’t need top engineers.” The nationality stereotypes are mean and degrading.
And at a macro level, often found to be accurate due to how the businesses in India operate. Poll the west's engineers: you'll find that engineering from India is not currently viewed very favorably, in general.
There are excellent engineers in India, but the system they operate in unfortunately doesn't allow them to shine.
Many of the large enterprises we work for did move software engineering work from HCOL locations in Europe or the US to India, often with disastrous results.
On Teams, channels related to AI are flooded with daily support requests from supposed engineers from India who clearly are not competent enough to set up GitHub Copilot or properly report issues they encounter during the setup.
And don't get me started on the shared libraries some teams located in India work on. If the library I need to use is full of obvious bugs where I wonder how any competent engineer could have shipped this to production, and then I see that the work has been moved to India, how am I supposed to feel about this?
Do we really need to sugarcoat this?
India has amazing software engineers and less competent ones.
USA has amazing software engineers and less competent ones.
Europe has amazing software engineers and less competent ones.
etc
You get what you pay for, pay top end in India and they will be same as top end in Bay Area (and many in Bay Area/USA are migrants...)
That's fair, I shouldn't have commented that. I don't like the national stereotypes at all - I see "outsource to India" as being more about less expensive engineers than not needing "top engineers".
That said, I don't think "rewrite from one language to another" with inexpensive engineers is a pattern that works. Happy to be proven wrong.