Hacker News Reader

Comment by nozzlegear | Hacker News Reader

> what say you now?

I think that when you have a $165,000 hammer, all of your problems begin to look a lot like nails.

I've done rewrites like this, maybe it wasn't Zig to Rust, but I have been able to rewrite sizable projects, from C# to Rust before. I incorporated a similar strategy, have Claude Opus review the codebase, write a spec, then have Claude implement it, while reviewing the spec, and using the codebase as fallback and gospel over the spec. That said, it's not the entire story here as I said, there was a lot of thought put into it, it it had not been done with Claude, I have a feeling he might have started an "experimental" version of Bun in Rust instead, as many developers have done in the past before LLMs.

Curious why you'd move from C# to Rust. C# has you covered mostly for memory safety so I would guess performance or lots of shared memory across threads?

Not the author but I also moved from C# to Rust. In the first place I did not consider Rust for C# works like REST API but after I proficient with Rust I no longer want to work with C# for the following reasons:

1. Microsoft don't want to open source .NET Core debugger. 2. I tired of keeping upgrade .NET on my projects. 3. Result type in Rust make me more productive than exception in .NET. 4. async/await in Rust is lightweight and a better than .NET. 5. Thread-safety in Rust is a compiler error instead of figure out by checking the docs if type is thread-safe. 6. Community libraries in Rust has a great quality and docs.

Only thing I am not a fan of with Rust is how insanely massive a debug output build folder can get (tens of GBs) and if you have enough Rust projects it can eat away a ton of storage.

This was purely a hobby project I wanted to test the limits of Claude and see how quickly it could do such a change. It was surprisingly very stable I still found bugs but was able to resolve them within a small time window. For additional context I didnt use Fable as only Opus was available to me.

I would guess the cost to do this with humans would be _at least_ $1.5M in compensation alone (I'm thinking three 500k/year Bay Area engineers) so this is already an order of magnitude cheaper.

Is it worth $165K? I'm less sure of that but it's honestly a moot point - this will get to 5 then 4 digits of cost pretty fast.

I think putting it in terms of API pricing is oversimplifying disingenuously. Anthropic still hasn't pulled the rug out from under us, so I'm sure it cost a great deal of money once everything comes together, likely surpassing 1.5M. Summarily, they got the result faster, which a group of engineers couldn't do, but at a greater expense.

GLM 5.2 (open-weights) is at or near Opus 4.7 level performance already. I think it's unlikely Anthropic will be able to durably charge us much more than the CapEx depreciation cost of GPUs + the OpEx of running them for non-frontier models (which Fable will be in 6 months to a year).

Bay Area salaries are well-known to be extremely inflated.

Have European engineers do it for $100k or Asian engineers do it for $50k and the math is already looking a lot sketchier.

More gets done in the Bay Area than those places.

Reply on news.ycombinator.com