No reason, unless the project is simple. The more you can offload onto your compiler/typer - the shorter is the feedback loop, the better agents work.
Lack of strictly enforced static typing make agents fail much sooner with Python. In my opinion, Rust and Scala are the best targets for agentic flows - and, coincidentally, they have the most advanced typers among mainstream languages.
But any statically typed language behaves better than any dynamically/duck typed language. When I say "better" I mean delivery time and the amount of shipped defects.
Another thing which helps (but not generally applicable) - ask your agent to verify critical protocols with formal proof in TLA+/lean/coq. Agents are bad at formal proofs - but generally are much better than most of the humans.
>Lack of strictly enforced static typing make agents fail much sooner with Python.
Just tell your agent "Use type hints. Add a pre-commit hook to run ruff, black, mypy, and pytest." It will save you 99% of headaches.
I've tested many flows involving linters. Results are far from ideal - agents tend to work around linters, mass-add ignore annotations, etc, especially in situations when fixing one warning/error triggers another (and that happens regularly).
What if you want to offload a lot of the work to libraries rather than generating (and presumably reviewing?) it yourself? Python has a very strong ecosystem of useful libraries because it's been around so long and is popular in a number of application domains.
Well, Python is not the only language with a mature ecosystem.
Also, in many cases it's cheaper to rewrite a small lib instead of fighting crappy code - but that applies regardless of the target language.
I feel like types doesn't really make a difference in this context. Types are good for enforcing standards between in a multi human situation, but AI doesn't really make the same mistakes that warrants it.
Models are trained on human data and they make exactly the same mistakes - and a lot of mistakes humans don't usually make.
Also they are extremely bad at high-level design.
Rust is a fantastic language to emit from AI.
Studies report that the language design tends to result in lower defect code (vs peers such as Go and Java) due to how the syntax aids error handling, logic flow, and API design.
You don't need to know Rust to begin using it. You'll learn it quickly enough.
The code is easy to read, and Serde makes parsing, especially JSON, extremely pleasant. Writing HTTP services is a breeze.
AI makes Rust development go 10x faster. The borrow checker isn't even an issue. It's invisible now. You almost never hit it anyway when you write web services, but now it's no issue at all when writing highly concurrent code too. Claude etc. emit the correct code and lifetimes, and it's entirely ergonomic and idiomatic.
The biggest problem with Rust is the compile time.
What study?
And I don't see how Go design patterns would be any worse. The main issue people have with it is the repetition/verbosity, which LLMs handle just fine.
> AI makes Rust development go 10x faster. The borrow checker isn't even an issue. It's invisible now.
What happens when things break and the AI agent can't fix it?
That would be bad, which is why Rust is preferred to python. In Rust when things break the AI gets a clear error message that makes it clear how to fix. In Python when things break, the AI will randomly spin its wheels for days trying different things without being able root cause the issue.
A failure to compile is by far the easiest thing for the AI to fix.
You'll learn Rust faster with AI and should be able to solve it yourself.
You're unlikely to wind up in such a situation though. The design work Claude does in Rust is really sensible and idiomatic, and I really don't think you'll be unable to refactor or redesign things. Claude is extremely good with Rust generation, refactoring, and manipulation.
I'll go as far as to say that AI has removed most of the complaints people had with learning or using Rust. It's not even a speed bump now.
Come on now, how do you learn anything if you just tell claude to do something and feed it error messages?