Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Vera: a programming language designed for machines to write

github.com

Post reply on HN
Print view View original

21–30 of 105 posts

Re: Vera: a programming language designed for machines to write

#21

Post by drivingmenuts »

svachalek wrote: post #16
rtpg wrote: post #12

The lack of naming seems to indicate a fundamental misunderstanding of how LLM coding agents are successful, and just makes me doubt anything about this project being useful and workable.

Yeah it seems based on 2023 research which is ancient, back when we didn't have coding agents at all, and on some 1980s sci fi concepts of "how machines think" (beedeeboop) rather than the all too human coding agents we have. If I had to design one of these, I'd go for: 1. Token minimization (which may be circular, I'm sure tokens are selected for these models at least in part based on syntax of popular languages) 2.…

> all too human coding agents

There is no actual thought occurring. Arguably, we can say the same about a lot of humans at any given moment, but with machines there never is. It's all statistics.

Re: Vera: a programming language designed for machines to write

#22

Post by ycombinatornews »

2001zhaozhao wrote: post #8

> There are no variable names. @Int.0 is the most recent Int binding; @Int.1 is the one before. You already lost me here. There's a reason variable names are a thing in programming, and that's to semantically convey meaning. This matters no matter whether a human is writing the code or a LLM.

Same here, reminds of JIRA’s field_17190 in MCP responses instead of description (and in similar excel-like systems)

Good luck managing hallucinations on that context

Re: Vera: a programming language designed for machines to write

#23

Post by zem »

sornaensis wrote: post #11
danpalmer wrote: post #5

> The empirical literature shows that models are particularly vulnerable to naming-related errors like choosing misleading names, reusing names incorrectly, and losing track of which name refers to which value. I think Vera might be missing something here. In my experience, LLMs code better the less of a mental model you need, vs the more is in text on the page. Go – very little hidden, everything in text on the page…

I'm curious what issues you had with haskell? I have had the opposite experience and find them dreadful at Java et al. Surely, denser languages should be better for LLMs?

my (uninformed) speculation is that you want resilience and error correction, which implies some level of redundancy rather than pure density.

Re: Vera: a programming language designed for machines to write

#24

Post by hgoel »

hyperhello wrote: post #2

> Division by zero is not a runtime error — it is a type error. The compiler checks every call site to prove the divisor is non-zero. Elaborate a little here.

Presumably an analyzer that makes it an error to not have an immediately traceable zero check.

C# can do something similar with null references. It can require you to indicate which arguments and variables are capable of being null, and then compiler error/warning if you pass it to something that expects a non-null reference without a null check.

Re: Vera: a programming language designed for machines to write

#25

Post by hyperhello »

hgoel wrote: post #24
hyperhello wrote: post #2

> Division by zero is not a runtime error — it is a type error. The compiler checks every call site to prove the divisor is non-zero. Elaborate a little here.

Presumably an analyzer that makes it an error to not have an immediately traceable zero check. C# can do something similar with null references. It can require you to indicate which arguments and variables are capable of being null, and then compiler error/warning if you pass it to something that expects a non-null reference without a null check.

But that’s because null is a static type. Zero isn’t a static type. How can I know if a calculation produces zero if I can’t predict the result of it at compile time?

Re: Vera: a programming language designed for machines to write

#26

Post by lesam »

Octoth0rpe wrote: post #19
svachalek wrote: post #16

Earlier quoted context omitted.

Yeah it seems based on 2023 research which is ancient, back when we didn't have coding agents at all, and on some 1980s sci fi concepts of "how machines think" (beedeeboop) rather than the all too human coding agents we have. If I had to design one of these, I'd go for: 1. Token minimization (which may be circular, I'm sure tokens are selected for these models at least in part based on syntax of popular languages) 2.…

> That is, a feature can largely be written in one file, rather than bits and pieces all over the codebase. This seems to be at odds with the goal of token minimization. Lots of small files that are narrowly scoped means less has to be loaded into context when making a change, right? Throwing out another idea: I wonder if we could see some kind of equivalent of c header files for more modern languages so that an llm…

I think AST aware code reading is criminally underused by agents - you don't need a header file if you can see a listing of all the functions in a library.

Similarly, I don't read the whole file a function is in while editing it in an IDE, why should a coding agent get the whole file polluting its context by default?

Re: Vera: a programming language designed for machines to write

#27

Post by hgoel »

hyperhello wrote: post #25
hgoel wrote: post #24

Earlier quoted context omitted.

Presumably an analyzer that makes it an error to not have an immediately traceable zero check. C# can do something similar with null references. It can require you to indicate which arguments and variables are capable of being null, and then compiler error/warning if you pass it to something that expects a non-null reference without a null check.

But that’s because null is a static type. Zero isn’t a static type. How can I know if a calculation produces zero if I can’t predict the result of it at compile time?

I think it's about if there's a possibility of it being zero. Of course there's no way to tell at compile time that a value will definitely be zero.

So, in pseudocode

int div(int a, int b): return a / b;

Would probably be a compile time error, but

int div(int a, int b): return b == 0 ? ERR : (a /b);

Would not, or at least that's what I'd expect.

Re: Vera: a programming language designed for machines to write

#30

Post by still_grokking »

Octoth0rpe wrote: post #19
svachalek wrote: post #16

Earlier quoted context omitted.

Yeah it seems based on 2023 research which is ancient, back when we didn't have coding agents at all, and on some 1980s sci fi concepts of "how machines think" (beedeeboop) rather than the all too human coding agents we have. If I had to design one of these, I'd go for: 1. Token minimization (which may be circular, I'm sure tokens are selected for these models at least in part based on syntax of popular languages) 2.…

> That is, a feature can largely be written in one file, rather than bits and pieces all over the codebase. This seems to be at odds with the goal of token minimization. Lots of small files that are narrowly scoped means less has to be loaded into context when making a change, right? Throwing out another idea: I wonder if we could see some kind of equivalent of c header files for more modern languages so that an llm…

Why would you need "header files" when a LSP server can give you just the outline of some file?
Post reply on HN