It may surprise some people here to see that Andrew is warming up to using LLMs to discover bugs (inspired by results from SQLlite) and considers it a tool on the path to getting to bug free software.
kasajian 2 minutes ago [-]
Andrew is a real weird guy. On one hand, he's innovative enough to see possibilities which made him create Zig, but at the same time it boggles the mind that an such an intelligent person can be so utterly stupid when it comes to LLMs. Makes me wonder what other stupid decisions he makes, tbh.
saghm 10 minutes ago [-]
> It may surprise some people here to see that Andrew is warming up to using LLMs to discover bugs (inspired by results from SQLlite) and considers it a tool on the path to getting to bug free software.
Someone in the thread below says their bug was closed because of mentioning that they use AI to confirm the bug they had encountered. Is he going to go back and reopen all of those now that he learned what pretty much everyone else already knew?
mjburgess 6 minutes ago [-]
There's a difference between Opus 4.5 and Astra 6
f33d5173 3 minutes ago [-]
With regards to whether when it finds a legitimate bug, it should be given weight?
jabedude 1 hours ago [-]
How is Zig doing as a project? I remember they took a hard line against AI
agentultra 44 minutes ago [-]
They seem to be doing fine. Tigerbeetle and Ghostty are two projects that continue to do well and are written in Zig. The foundation’s funding also seems to be doing well. They are continuing to make releases.
abc42 57 minutes ago [-]
It looks like they're spending 5 months what should be a 1 month job these days.
onlyrealcuzzo 55 minutes ago [-]
Filed a compiler bug related to dwarf tables that screws up debugging and line of code coverage that they completely ignored, just because I mentioned that I had every LLM check it to confirm it's a bug, since all I know is what kcov and every coverage tool generates incorrect coverage data for my repo, for 100% certain.
bendmorris 44 minutes ago [-]
Sounds like you violated the clearly stated project rules and admitted to it. Are you surprised that they're not engaging with you?
giancarlostoro 1 minutes ago [-]
Reading their comment it sounds like they wanted to confirm the bug existed with AI, not sure they ever said they had AI write the code. Why have such a dumb policy?
unclad5968 38 minutes ago [-]
It's a violation of project rules to confirm bugs with AI?
>If you use a chatbot to give you advice on a comment on the issue tracker, that comment is unwelcome.
>No LLMs for finding bugs.
>No talking about use of chatbot/LLM services.
I've said it before and I'll say it again- it's a cult that bans dissent
alexrp 7 minutes ago [-]
For the record, there isn't even uniformity of thought on LLMs within the core team, let alone the broader Zig community.
jibalt 26 minutes ago [-]
Yes ... pretty damn stupid.
saghm 8 minutes ago [-]
Pointing out something that is not good doesn't require surprise at the fact that it happened
phoghed 10 minutes ago [-]
Yeah, the maintainers of a DOA hobby project should certainly be allowed to run it however they want imo
IshKebab 38 minutes ago [-]
Wow I thought surely they wouldn't object to using AI to confirm bugs, but they really do.
Tbf I guess as a popular open source project not using AI to fix bugs, they probably already have more open bugs than they can ever fix so it doesn't really help them for people to find more.
I would imagine his bug was actually ignored just because Zig has 2700 open bugs, rather than some AI policy violation.
They don’t, at least not any more. Andrew Kelley has explicitly stated that he sees the value of using LLMs to uncover bugs. Inspired by sqllite project.
They may just be taking the slow route of rejecting by default until they can be sure that the usage of LLMs provides long term value. I don’t see anything wrong with that. If you’re writing robust software, using LLMs at this stage is a bit of a gamble. We don’t fully know the long term effects on code quality yet.
saghm 7 minutes ago [-]
Ah, so yet another language in the long line of "I'm smart enough to use this but you the user are not"
unleaded 57 seconds ago [-]
Project maintainers know what level of AI use is acceptable for themselves, and quantifying it and enforcing it for random contributors is very difficult.
acedTrex 28 minutes ago [-]
The popular LLM projects have infinitely many more bugs than the zig project does this is a ridiculous message.
UncleOxidant 32 minutes ago [-]
If they really insist on no LLM involvement at all then they're going to fall behind and lose out. Your LLM use case seems really very conservative - you didn't write any code with it, you just use it to confirm the bug. There are many OSS projects that are also taking a similar hardline against LLMs - people are going to fork them and then move on. I've had LLMs fix bugs/add features to a couple of projects like this and, well, they're missing out on the fixes/added features that I'm using locally.
acedTrex 28 minutes ago [-]
They are doing fine, all this "left behind" talk has no basis other than cope.
acedTrex 38 minutes ago [-]
> breaks the project rules
> gets ignored
Who could have forseen this.
greggoB 52 minutes ago [-]
Can you offer any specifics? The ToC looks quite extensive, which to me indicates a lot of design decisions needed to be made (probably involving many people) and unclear how that process might be accelerated by AI.
Unless you're suggesting the language design should also be vibed together?
nvme0n1p1 45 minutes ago [-]
> Unless you're suggesting the language design should also be vibed together?
Sounds like a fun little project, have a bunch of AI pushers fork Zig and see if they can do a better job. I want to see results, not snarky HN comments. After all this progress, ChatGPT should be able to one-shot a better language since AI is so good now... right?
agentultra 40 minutes ago [-]
Claude can’t one-shot a C compiler.
None of these systems can. They need enormous training. They need alignment and reinforcement. They need harnesses. And most importantly they need a human that knows how to write and develop a C compiler.
The ISO specifications are not sufficient. Neither are the System V guidelines. Not even spec tests and compcert.
spankalee 41 minutes ago [-]
One-shot, no, but there are a bunch of people pretty much solo-building their personal ideal language with AI and it's going quite well. You need to know just enough about language design to be dangerous, but you don't need to be a seasoned pro.
Been thinking about doing this myself (did some PL in grad school but it's been a long time), but I find myself wanting to reach for a Scheme (using macros to grow the language I want) and customize it or build something atop Janet.
Curious why you wanted a more ML / Rust / Scala inspired syntax. (Personal preference here is totally valid btw, just curious.)
UncleOxidant 28 minutes ago [-]
You're not going to one-shot it, but over the course of a couple of months of evenings you could come up with something usable/interesting if you manage the LLM well.
IshKebab 34 minutes ago [-]
Nobody is one-shotting big projects. Even humans can't do that.
dingdingdang 37 minutes ago [-]
Yep, it's true, but the reality of what it would take to actually fork and commence with healthy use of AI alongside with the elusive soft/hard stance needed to lead technically and socially is probably a bigger challenge than anyone is willing to take on! Soo.. slow and (rather?) well it goes for Zig.
mg74 49 minutes ago [-]
Slow and steady wins the race
saghm 5 minutes ago [-]
And apparently ignores legitimate compiler bugs on the way that someone happened to ask an LLM to double check their diagnosis
jibalt 24 minutes ago [-]
Parables aren't reality.
re-thc 44 minutes ago [-]
Anthropic levels of slowness (pacing)?
mathisfun123 46 minutes ago [-]
in tech? really?
Zak 35 minutes ago [-]
In programming languages, usually. Building software on top of a rapidly-changing language is not often a recipe for success.
2 minutes ago [-]
nvme0n1p1 43 minutes ago [-]
Yes, the Lindy effect applies in tech too.
acedTrex 37 minutes ago [-]
Im really enjoying using it, works great tbh
DASD 46 minutes ago [-]
Seems to be C++ing which is disappointing. Looking more at C3 and Odin for cases where I'd hoped Zig to land.
deagle50 36 minutes ago [-]
Odin scratches this “stick shift” itch for me better than anything else. Highly recommended.
zer0-c00l 29 minutes ago [-]
can you elaborate on what you mean by "C++ing"?
sureglymop 27 minutes ago [-]
C3 is honestly so good and a bit underrated.
silisili 14 minutes ago [-]
It's my favorite of the new round of languages by far. I just wish it had a bigger ecosystem.
luiwammus 22 minutes ago [-]
Although I understand that upgrading LLVM version is a lot of work, it's a bit frustating that loop vectorization is still disabled.
alexrp 20 minutes ago [-]
The fix could not be backported to LLVM 22 because it changed the LLVM library ABI. We also could not skip straight to LLVM 23 because that would make life harder for distro package maintainers.
https://youtu.be/zwi5b5xSsKA?is=PTjJJjSnVMdRuZag
It may surprise some people here to see that Andrew is warming up to using LLMs to discover bugs (inspired by results from SQLlite) and considers it a tool on the path to getting to bug free software.
Someone in the thread below says their bug was closed because of mentioning that they use AI to confirm the bug they had encountered. Is he going to go back and reopen all of those now that he learned what pretty much everyone else already knew?
>No LLMs for finding bugs.
>No talking about use of chatbot/LLM services.
I've said it before and I'll say it again- it's a cult that bans dissent
Tbf I guess as a popular open source project not using AI to fix bugs, they probably already have more open bugs than they can ever fix so it doesn't really help them for people to find more.
I would imagine his bug was actually ignored just because Zig has 2700 open bugs, rather than some AI policy violation.
Show me a popular open source project that doesn't have a large number of open issues and I'll show you one that has a triage bot auto-close them.
https://youtu.be/zwi5b5xSsKA?is=PTjJJjSnVMdRuZag
They may just be taking the slow route of rejecting by default until they can be sure that the usage of LLMs provides long term value. I don’t see anything wrong with that. If you’re writing robust software, using LLMs at this stage is a bit of a gamble. We don’t fully know the long term effects on code quality yet.
> gets ignored
Who could have forseen this.
Unless you're suggesting the language design should also be vibed together?
Sounds like a fun little project, have a bunch of AI pushers fork Zig and see if they can do a better job. I want to see results, not snarky HN comments. After all this progress, ChatGPT should be able to one-shot a better language since AI is so good now... right?
None of these systems can. They need enormous training. They need alignment and reinforcement. They need harnesses. And most importantly they need a human that knows how to write and develop a C compiler.
The ISO specifications are not sufficient. Neither are the System V guidelines. Not even spec tests and compcert.
I'm doing it myself: https://zena-lang.dev/
Curious why you wanted a more ML / Rust / Scala inspired syntax. (Personal preference here is totally valid btw, just curious.)
Just don't be surprised if the project BFDL talks shit about you or your company later.
(Still a good language though, credit where credit is due.)