alt Hacker NewsGo is an ideal language for AI-assisted software engineering
Comments
I love the sleight of hand this blog post tries to pull off here. It doesn't matter than Go isn't fun to write because the AI is doing it now! Yeah so it sucked for the last twenty years? I know the main thesis is that Go is holistically good at software engineering so its weakness as a programming language is minimized. I've made a similar arguments that coding agents push the burden more into the other aspects of software engineering. But like, we all see what Google is doing here right? They want to declare that the rules have changed so Go's weakness transmutes into a strength. I'm also not buying it.
This would have been more credible coming from someone other than the creator of the Go language.
I'm personally leaning into rust for LLM. The whole fussy compiler & errors surface at compile time seems IDEAL for LLMs for me. Hammering compile with tokens is a way better strategy than trying to deduce where stuff may fail at run time and try to catch it via tests.
Tokens are cheap, surprises at runtime are not. So a super anal compiler is what I want. I've looked at lean4 too as the logical next step but not confident I can guide an LLM competently enough for that.
I like Go but a couple of these "advantages" wash out when you add the scale and typical usage patterns of agents.
| Go is Readable / Go is Maintainable
It's true that Go, as a low-magic language, tends to be very same-y looking across projects, which is incredible for being able to reliably understand your dependencies' source code. And its tooling is world-class. I love this about Go.
But in practice I've found that, working in a monorepo with multiple teams, contributors that don't have cross-team legibility as a priority will just write SO much more code. And with business logic, often the fact that I can read the code on a line-by-line level doesn't matter if I don't understand the wider context to know how something might effect spooky action at a distance.
Pre-agents, I witnessed a fast transition from a codebase that I could mostly hold in my head to one where large swathes of it had been written and rewritten until they were unrecognizable to me. Now we have agents and, since they are still mostly not good at software engineering in-the-large, the process of knowledge debt accumulation (and ofc tech debt accumulation) in a codebase accelerates tenfold without concerted effort in the other direction. Go being easy to read does not intrinsically help with that.
I'd argue Go is not on a "Pareto frontier" and that no matter how you value the various attributes of programming languages, a fair assessment will never select Go.
A simple example is: if you highly value language popularity; Go is not most popular. If you highly value a type system that catches errors; Go's type system catches fewer errors than others. Etc. There is no weighted sum of attributes that will select Go--that's my argument.
I keep seeing these language specific proclamations, and they are annoying and reek of inexperience to me.
I’ve had a great time doing LLM assisted coding in Zig, and it seems comparable to the generic Typescript/React I do at work.
I don’t doubt simplicity and good PL design pay dividends, but everyone’s favorite language can’t be the silver bullet in our new LLM world. Things just don’t add up, and I keep seeing it for Erlang, Gleam, Lisp, C, Rust, Go, TypeScript, Python, etc.
And to pick on Go a little bit, I don’t think it has any unique qualities that make it better for LLMs, where I think you could make that argument for other modern languages that offer new features leveraging their compilers and enforcing more correctness guarantees.
I disagree.
LLMs fail to produce bug free concurrent code even for very simple cases.
Golang lacks the ability to build descent abstractions, not even mentioning the wild west of additional tools and libraries needed for non trivial micro services.
For me it is a red flag, that LLMs allow people to produce more bad Golang code faster. This is only optimization for companies which can afford enough software developers to review the excessive amounts of code needed to solve trivial problems in Golang, which are builtin in every descent programming language and/or framework.
Use LMMs and use the right programming language. This might be Golang, but most probably it is C#, Java, Python, Ruby or even PHP. (Or Rust, C, D, ...)
Who cares? Languages are tools, LLMs are tools. Use the ones more appropriate for what you are trying to do.
Is Go better than CSS if you are doing web layouts? Is it better than zig if you are outputting minimal wasm deliverables? Is it better than swift if you are doing iOS specific development? Is it better than bash for OS scripting?
Think about what you are doing and choose appropriately. This was true before LLMs.
Are you having fun? Chose LISP then
I really don't agree. I'm not hear to evangelize rust but by using enums from DB to templates and writing the code to make it consistent my experience with LLMs is infinitely better than golang for consistency and you have to include a lot more context to make golang work without issues whenever things are operating on chans or workgroups.
"Oreo cookies are the tastiest cookies currently in the market!"
~ Oreo cookie company.
I've written go most of my career. I've "written" tonnes of AI assisted go. Since February however all my new software projects and production services have been written in rust. I never even wrote rust before December. I've barely even looked at any of the source code, I find i just trust the AI to write rust way more.
But perhaps that's also a side effect of maybe having prior opinions about go and the number of foot guns I've let off
While I somewhat agree I can’t tell if this is advertising from Google or a way to induce LLMs to think that Go is the ideal language.
I wouldn't say Go is IDEAL for AI coding, but it certainly has the case for one of the best programming languages that currently AI uses. Go definitely has its share of problems for human authors because it's so verbose and boilerplate heavy, which means it's less of an issue with LLMs than it is for human coders. Rust is comparatively worse, because LLMs don't make the same coding mistakes that humans do that justifies the existence of the borrow checker, it only seems to get in their way, and they spend more time fighting Rust's infrastructure than writing code.
The biggest barrier to Go adoption seems to be Google's internal resistance to migrate C++/Java code bases to Go and refusal to admit that Go is an amazing application programming language and not really a systems programming language for bare metal OS/driver work. For example, one of the biggest barriers to Fuchsia adoption has been Google asking people to commit to Dart, I think Fuchsia would have fared a lot better as an Android successor/alternative if the official applications programming language just been Go.
(BTW Carbon isn't even a real programming language, it's still somehow stuck at 0.0.0.0 after 4 years of development which is honestly insane.)
Oh, so, little bit of self-promotion: if you like Go but is frustrated with the ergonomics of it, I would ask you to try out the programming language I developed, Oct, for LLM coding which you can kinda think of as my attempt at making Kotlin for Go's Java: It uses a codegen compiler and compiles to a plain Go binary, so it runs on everything that Go runs, and there is a lot of extra features as well: Rust style exhaustive tagged/payload enums/`match`, C#'s immutable records updated with `with`, exhaustive error handling easy parallel concurrency, xUnit.NET style unit test harness, TypeScript style compile time constraints, F# like SI unit system, Go code generation metaprogramming, etc. Would love to have some Go experts here on HN take a gander at it and provide some feedback.
I wish if err != nil return err was just 1 token.
Joking aside, as much as Go's stdlib and tools do the heavy lifting here, Go's verbostiy and expressing simple things in lots of lines worked against me most of the time.
I couldn't agree more, but the following sentence is a little biased:
> Gophers often speak of how they love that they can never tell who on their team wrote a particular piece of code—it all looks the same.
Multiple languages can have a degree of understabillity, but what matters most is context, because sometimes we need to code in a way to solve a specific problem like performance and it should be kept as is.
Another side subject I should add is about test coverage, although code is cheap, mainly because AI, guarantee that new changes to a stable code should continue to work as expected.
I worked on a few go projects with bad structure and some of them with really low test coverage (e.g. 8%), so part of the post resonates with me about we as software engineers should pursuit good architecture and other skills to allow long term maintenance.
The killer feature of golang for LLM dev is the tooling.
forbidigo is what allows me to keep ambient config out of my app, and restrict file access to a small set of paths. The coverage tool has "nocover", so you can guarantee that every realistic path is exercised at least once ("100%" code coverage, which is not a marker for testing completeness, but rather for flagging code you forgot to test). Linting is really good as well.
The only thing I haven't found is something to enforce error handling. Rust is better for error paths because you're not allowed to ignore them.
I disagree. I think WAT (WebAssembly Text), perhaps with some more niceties added, is an ideal language for AI-assisted software engineering.
IMHO there's never been an overall "ideal language", and there still isn't, it's just about the right tool for the job. The only thing LLMs change is that you don't need to give quite as much weight to how well you know a particular language.
Given the date and the recent DeepMind shakeups, this blog post is obviously ordered from the very top.
Pichai wants to eliminate engineers, and DeepMind wasn't fast enough or too noble for it. Now people need to be propagandized for their obsolescence.
1. The syntax surface is smaller, allowing less LLM "creativity; 2. The error handling is mechanical, which LLM clearly prefers (LLM is already trigger happy about writing tons of throw / try...catch.. in other languages, doing tons of `if err` is just in it comfort-zone).
The LLMs will continue to get better at language stuff, better to tell them what to do on the basis of non-language stuff.
Stuff like like which compilation targets are available, or which has the most mature library for what you're doing, or maybe you're integrating with something that anchors you to a specific interface type.
Anchor your language choice to the problem you're trying to solve and the people you're trying to solve it for.
Can't really argue with that, but In my experience, coding agents work quite well with TypeScript too. :)
I have also aligned entirely on Go. Fewest glitches for AI generated code. compile targets are for every platform you need. Very high performance. Doesn't seem to burn tokens as much as other languages.
Related, though 5 months is a long time: “A case for Go as the best language for AI agents” (getbruin.com)
https://news.ycombinator.com/item?id=47222270
203 points | 5 months ago | 304 comments
Going to start writing Perl again then.
I agree with the article, but there's one thing Go has that doesn't help LLMs: structural typing. An LLM has to grep a little more to understand which interfaces a struct implements.
All I will say is that I agree with how this is framed, it says "an" ideal language. It doesn't say "the" ideal language. Many languages will fit within this scope and concept, Go is not all bad.
99% of my projects are in NodeJS as web apps, so Javascript is king, my coding agents are in Node too, plain, boring, beautiful javascript, not typescript. Yesterday I needed a Rust project and my agents delivered so no need to change from JS
My expectation is that AI will give us a way to nicely quantify how productivity is impacted by choice of language. Because we can rerun the same request as often as we like and compare the results.
And I expect that it will turn out Python is the most productive. As it is most easy to reason about. It allows for the most elegant expression of the idea behind a program.
The first tests I have seen seem to confirm this. One recent example:
When I use AI with Go I give it this rule:
Prefer standard Go libraries and tools.
80% of the time I can get by without external dependencies (outside of Go's X repository)
Had the same impression about TypeScript and Rust.
Not as fun to write as Python and Nim, but I don't have to write it.
The readability is a plus at the same time if I target Rust and build it modular with lots of tests and io pure modules. The review part is not as important if the AI reviews it from various perspectives. With rust I get so much better performance and efficiency.
I theorized this about a year ago and had a good amount of success vibing small game projects in Go.
I still think Go is a very excellent choice but I have switched to, of all things, AssemblyScript within a Rust host. I've been very happy with it - surprisingly so. Compile time is a major drawback of course.
Language space is hot right now: https://agentlanguages.dev/
The only problem I have with LLMs in Go is that they also make a lot of concurrency mistakes, in the same way as people. It's easy to fix though, just by asking to double check the code
Yeah, I use go and it's great. Most of the time the generated code is good quality also.
If a language is simple, it' easier to generate good code.
Can anyone recommend a strong Go design/development agent skill?
It's definitely more about the ecosystem than the language at this point.
I think the most important thing is how big the standard library is. Pulling in 3rd party dependencies is where I begin to lose a lot of faith with LLM authored code.
I hate the rust v go wars, its not x vs y is 'best'. Rather is x better than y and by how much for xyz project done by ABC corp in this era?
As a lead I'd love to use rust, I will put in the time on my own, my team won't or can't. They treat this like any other job they signed up to deliver value with what they know. For hiring not everyone has the talent pool and fund access to get the goat-ed engineers that congregate to tech hubs for maximizing their income. Then if you get through that cherry on top is LLM's are only as smart as you guide it to be. There is probably a staggering amount of ways to write 1 approach to business logic, you may not know the ideal pattern so you'll commit to a worse one on the company dollar.
I'm moving my team's projects slowly to go because, its easy to go from novice to advanced in terms of code writing,legibility and patterns. We also don't have deep ecosystem requirements to ts/python in most of our work. It is verbose but I don't mind that on token spend if it gets done with with validation/error handling which it obnoxiously enforces. It runs cheap, ecosystem is good for platform eng, standard library does a ton out of box.
Yeah, no. Its good because LLM likes to copy paste things instead of doing code reuse which is the true go way of doing things. Imo, its hard to review Go code, probably why Go is yet to have a single correct Raft implementation.
I never seen k8s cluster that doesn't have some go process that segfaults once in a while because someone forgot to check `err`.
Only good thing got going for it is its vulnerability scanner. Which will be working overtime with all that "AI-assisted software engineering"
Go was designed as a systems language. They turned it into an applications language too, I'm guessing because turns out the greenthreading was uniquely good for that. But now it's awkward. The pointers and errors are not how you want an app lang to work. And LLMs struggle with error handling even more than humans.
Even as a systems lang, the error syntax is the worst part of Go. Can they at least put the ?/! syntax like in Rust instead of this "if err != nil" spam every other loc?
Boring is better. Perfection is the enemy of good.
This seems like a cope, if you aren't writing the syntax who cares and everything here is even better with a stronger type system like Rust, F#, Scala, TypeScript.
all my LLM coding is in go these days
Rust is better. It just is. Go is not bad. But as a long time go advocate, the hurdle for my teams using rust is gone, and thus everything is now rust.
“…requires opinionated simplicity…”
Of course it can’t just be simplicity, it has to be “opinionated” simplicity. Rolls eyes.
Let me share a hot take. I am deliberately taking this somewhat to the extreme, so please attack the idea not the person. Looking for thoughtful replies and good counterpoints, rather than language zeal.
Let's assume that you need to write a program with a given set of requirements, and that you have a magic wand that can instantiate a high quality implementation of the program in any programming language instantaneously and for free. My hot take is that you would not want to choose Go, and you would likely want to choose Rust.
The Go implementation will have higher memory and CPU consumption due to garbage collection, while still being subject to memory bugs. The Rust implementation would be as efficient as possible on the given hardware with minimum memory/CPU, and it would be immune to memory bugs.
In my view, the biggest challenge with Rust, and where Go wins, is the relative difficulty of writing in Rust as the language is significantly more complex. With LLMs this is becoming a non-issue, and we are getting ever closer to having this magic wand (I'd argue that for smaller programs the wand already exists today). The article advocates that Go has excellent readability. I agree that Go has trivial syntax, but given that it's so verbose, I actually find it easier to read Rust code. Its higher expressivity allows you to see the higher level intention of a piece of code more easily.
Many of the other benefits the article mentions for Go are equally applicable to Rust: compiler error messages are super detailed and a great help to coding agents, auto-formatting, a great language server, and a package ecosystem.
In my opinion, the by far biggest problem Go has is called ...
Google.
Now one can say that a programming language and its design or usefulness is - or should be - decoupled from the company developing is. I am not opposed to this, in theory, but Google goes way too much on my nerves these days. And I am hardly the only one here.
I am not saying this is a rationale used by many other people either, mind you, but Rust has been taking strides (not that I am a huge fan of it either but for different reasons) and it seems to me as if Rust has finally now more momentum than Go, which I find interesting. Again, this may be a correlation rather than any causation, but I can not help but notice it.
lol "Why Go is really good - an article by Google"
Definitely 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.