171–180 of 201 posts
Not because it is concise but because you won't need to spend tokens debugging segfaults and a whole spectrum of bugs that the compiler catches. LLMs usually write tests in the same source files so most features are implemented and working in one shot.
Claude could work on it okay apparently but some local llm's struggled with it and got stuck in reasoning loops trying to close the parenthesis.
Is there a relationship between how good a programming language is for coding agents and how popular it is among humans? If so, wouldn't Python be the best language for agents, since it's is the most popular (and hence has the most context available for models)?
As much as I love Python, JavaScript (including TypeScript) is probably more popular.
Ive been amazed at how well LLMs are at writing Gleam[1] and Lustre[2]. Compared to a mainstream language, there is basically zero gleam code in the training data. I have no evidence to back this up, but I suspect that languages that are good for humans[3] will be good for LLMs. Compiled, strongly typed, statically typed, immutable, pure functions, pattern matched, memory safe, etc. [1] https://gleam.run [2] https://…
I’ve been developing a language for a few years, and even with incomplete semantics and a simple one page example LLMs don’t have much trouble writing it. I think the language/syntax has an impact, but the tooling around it will be most important for LLMs, in the same way it is for humans.
The biggest challenges are maintaining non-functional requirements, specifically CPU and memory effenciency.
Ive been amazed at how well LLMs are at writing Gleam[1] and Lustre[2]. Compared to a mainstream language, there is basically zero gleam code in the training data. I have no evidence to back this up, but I suspect that languages that are good for humans[3] will be good for LLMs. Compiled, strongly typed, statically typed, immutable, pure functions, pattern matched, memory safe, etc. [1] https://gleam.run [2] https://…
Ive been amazed at how well LLMs are at writing Gleam[1] and Lustre[2]. Compared to a mainstream language, there is basically zero gleam code in the training data. I have no evidence to back this up, but I suspect that languages that are good for humans[3] will be good for LLMs. Compiled, strongly typed, statically typed, immutable, pure functions, pattern matched, memory safe, etc. [1] https://gleam.run [2] https://…
That's not a take I was expecting to find here. I've found most LLMs absolutely dreadful when it comes to Gleam, to the point that I most often disable even inline autocomplete when working in Gleam codebases. Too often I find them getting pulled into larger ruts in the training data and trying to insert language features that don't exist (ifs, loops, and syntactic constructs) from more popular languages like TypeScr…
Also a small note: the axis on one of your plots alternates between 4% and 5% increments whilst holding the ticks constant. Maybe because of rounding?
Contrary to what most comments seem to indicate, my takeaway from this is that it doesn't really matter all that much for the agents what language you pick. If humans are still to be involved in the process at some point, then its imperative that the language can be read by them, so the preference or skills of the developer(s) are of primary concern, not the agent.
Similarly contrary: I don't know why people aren't talking more about Python. Am I interpretting the final vs. graph incorrectly? I've got some education in materials engineering; it'd be trivial to drop a curve (line) for optimizing the language selection, and Python obviously comes out on top. The author doesn't even mention it. That discredits the whole article as far as I'm concerned.
We studied this question pretty systematically in the MirrorCode paper [1], comparing Python, C, Rust, Go, OCaml, and Ada across 19 very long-horizon tasks, for Claude Opus 4.7 and GPT-5.5. > In our results, there was little sign of inter-language differences in solve rates, for any model (Figure 5b). This suggests that AI models have learned generalized programming skills, rather than pattern-matching syntax. This d…
That is, for larger, more complicated software. There could be a set of static analysis tools that guarantee the correctness of the code. This would be very cheap to run and maintain.