I'll be very interested in how this AI port turns out. I am involved in a number of active projects that are being held back by the language / framework is holding back the project, but where a rewrite would be too big of a project to undertake by using only human power.
I've had more success vibe coding Rust than I have in more dynamic languages. I suspect the strictness of the Rust compiler forces the AI agent to produce better code. Not sure. It could be just that I am less familiar with Rust so it feels like it's doing a better job.
Rust is a good choice to let LLMs run without a ton of supervision. In my experience you need to monitor the progress heavily and take ownership of the design of the thing you're building or porting. Test harness is a must. Each iteration should run the test and ensure it doesn't break things in other places.
I am in the middle of porting TypeScript to Rust and learned a ton doing this. You can check out the work in progress here https://github.com/mohsen1/tsz/
I've been targeting Go instead of Rust for a few things. But same deal, I'm not really a Go programmer and it seems to work well enough. I do have a few decades of engineering all sorts of code bases; so I'm not coming at this completely naively.
My way of compensating for my own inability to do detailed code reviews is making sure the tests, integration tests, end to end tests, cover everything I care about. Without that, you can't be sure it is not skipping detail work. I've also made it do some bench marking and stress testing and then analyze the code base for potential bottlenecks. After it found and fixed a few issues, it got better. Finally, prompting it to do critical reviews, look for refactoring opportunities, etc. can give you a nice list of stuff to fix next. Having it run memory leak checkers and static code analysis tools also is a good strategy. Once you start running low on issues you find this way, the code is probably not horrible. Or at least you hit some sort of local optimum.
The lack of code reviews sounds pretty horrible. But it is now quickly becoming the biggest bottleneck in AI assisted coding. Eliminating that bottleneck is scary but it enables a few step changes in volume of code that becomes possible. Using strict compilers and strict memory management helps eliminate a few categories of bugs and issues.
I was previously doing this with languages I do understand. Once you start routinely dealing with larger and larger commits, reviews become a problem.
I expect working with larger code bases like this will get a lot easier and better over time. I noticed that the main headaches I face with this type of engineering are the tendency of models to keep deliberately cutting corners, only doing happy path testing, or deferring essential work for later. I suspect a lot of the models are simply biased to conserving token usage. Pretty annoying but also easy to compensate for with follow up prompts and testing. And probably something that becomes less of an issue as the models get tuned to behave better without additional prompting.
I have the same experience. Maybe I’ve used the same amount of time getting the rewrite out, but the amount of quality checking have increased for me. Before, I would probably not bother to create end to end tests and benchmarks, but now the mental cost for being extra vigilant is so cheap.
My rewrite is running stable in production for two weeks with 50x speedup, which have made the doomed old solution viable again.
Wonder what this will mean for future legacy projects and how how we should structure the programs to be inside “rewrite with llm”-size? Maybe a renessanse for microservices?
I've actually been vibe coding a port of Django to Rust as a fun learning experience. I didn't expect it to be possible, but I've already got the core ORM working (including makemigrations, migrate, and inspectdb) with basic admin support running.
Single file deployment, and the process seems to only use 3-4 MB of memory.
I've been able to use inspectdb on existing Django databases, and then browse and change that data using the rust admin.
I am probably not the right person to build a production ready version of this - since I am not a Rust developer - but gee I am impressed by how good it is becoming.
We were taught the same (Australian) - though it always felt slightly off as March often has major heatwaves, and December can be quite spring-like, often cool and wet.
Adelaide’s climate anecdotally feels to be more humid in recent years (historically bone dry Mediterranean climate) and the seasons feel like they’ve shifted a few weeks forward.
The Kaurna (Australian Aboriginal people of Adelaide, pronounced Gar-nuh) apparently mapped seasons a little differently, with a longer summer that resonates with my experience:
Have they fixed all the keyboard bugs introducted in iOS 26.0 yet? I’m not sure how much longer I can put up with issues like this - I might need to switch back to Android if they don't fix these soon.
Seriously, how hard is it to correctly measure the keyboard height and not render important UI elements, such as submit buttons, underneath it so you can’t click “Send”? It's getting close to unusable.
So many bugs in this version of iOS, ive never seen anything like it. The UI for so many websites is mildly broken or misaligned now, keyboard randomly has a noticeable lag, audio does not return to normal volume if a background app makes a noise for a moment, and many more. Really awful, I’ve never wanted to downgrade iOS back to the old version until now.
I am quite surprised that most languages do not have an ORM and migrations as powerful as Django. I get that it's Python's dynamic Meta programming that makes it such as clean API - but I am still surprised that there isn't much that comes close.
Have used pmtiles to self-host a “find your nearest store” map, which only needed to cover Australia. Created two sources: (1) a low-detail worldwide map to fill out the view (about 50 MB), and (2) a medium-to-high detail source for Australia only, up to zoom level 15 (about 900 MB). In this case, there’s no need for up-to-date maps, so we were able to upload these two files to S3 and forget about them. Works great!
I've had more success vibe coding Rust than I have in more dynamic languages. I suspect the strictness of the Rust compiler forces the AI agent to produce better code. Not sure. It could be just that I am less familiar with Rust so it feels like it's doing a better job.
reply