alt Hacker NewsDefinitely agree with this article.
At Netflix, I lead the Go language guild. We've been seen increasing reports of users finding their AI agents writing better Go code than other languages, and increasing reports of projects favouring Go over other languages.
Two additional notes I'll add:
- Go has _great_ resources on writing good Go code, including treasure troves at https://go.dev/doc/effective_go and https://google.github.io/styleguide/go/. edit: Sorry, I forgot to add: we give these resources to AI agents and they use them to produce even better Go code.
- For a language team, Go is a dream. The `go fix` tooling, AST/SSA packages, ease of reading and writing `go.mod` (go mod edit, etc), and various other "platform"-y features make modifying Go code at scale way easier than other languages.
Replies
I work at a large devsec company which uses primarily Go and TypeScript
I've found that the LLM generated Go has few mistakes, and generally isn't too obscure. But the volume of code is so high, colleagues do a bad job of reviewing it.
I've seen a lot of very silly decisions made, like returning the wrong HTTP code, or miscategorizing a metric used for an SLO, that I just don't think is helped by the sheer volume of code one has to wade through.
Ironically, we are considering migrating some initiatives to Rust, exactly because experiments indicate it works well with LLM development.
Your post reminds me of what I love about Python, we have PEP-8 which is a style guide, and it kind of shifts how you write code a bit (for the better) which is something I sorely miss in other languages, I don't get the feeling people care about style guides for other languages very much.
> For a language team, Go is a dream.
I agree very strongly. There's no debate about things that have 1000000 permutations in other languages. e.g. The correct format can always be checked by `go fmt` with no real config options. the end.
Go wins for simplicity. however what I have seen is companies end up going with Java coz it's simple enough - not simple as Go, but simple enough + fast enough.
though the letdown with Java is the wider ecosystem that makes unwarranted contraptions out of simple things.
When you give those resources to your coding agent, do you give them URLs? Or work with local versions?
I've found a lot of success pointing claude at locally downloaded docs over llms.txt URLs but not sure how to scale the pattern for a bigger project.
A sort of an amateur I found Go to be really good when used with language models. Simplicity and tooling helps I suppose and I expected it to. However I was pleasantly surprised with how they are also pretty good with Flutter and Dart. Again good tooling, good documentation and perhaps not much historical baggage like a python or a PHP would have. And no stack overflow to speak of pretty much.
I have a question: why do you think Go is better compared to other languages?
After all, learning a new language takes a lot of time. While basic syntax is common and quick to pick up, mastering a language's specific mental model requires a significant time investment, which is why I've used Go before but never seriously.
My interest was piqued recently when I heard about TypeScript tooling being ported to Go, and I know it is incredibly fast. However, where do the results claiming that AI agents generate superior Go code actually come from? Is it a fair, apples-to-apples comparison?
Since Go is a very small language with only 25 keywords, the way you write code is extremely standardized. Because of this, I would assume it naturally produces a lot of excellent best practices and conventions, but I'm not sure if there are actual, direct code examples proving this
Uber reported that their Go code has quantitatively more concurrency bugs than code in other languages, and while to me it seems obvious from looking at Go's concurrency model, this is backed by actual data. Is there any quantitative data to back the claim that Go is better in an LLM based workflow than another popular language?