frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

It's hunting season in orbit as Russia's killer satellites mystify skywatchers

https://arstechnica.com/space/2025/07/its-hunting-season-in-orbit-as-russias-killer-satellites-mystify-skywatchers/
1•LorenDB•46s ago•0 comments

Show HN: ByteWise Search a Privacy, Zero-Traffic, Community-Driven Search Engine

1•FerkiHN•2m ago•0 comments

KDE ISO Image Writer is finally getting a UI redesign and new features

https://www.neowin.net/news/kde-iso-image-writer-is-finally-getting-a-ui-redesign-and-new-features/
2•bundie•3m ago•0 comments

Mony – see how many work-hours every purchase costs (built with v0 and Windsurf)

https://mony.alexstreza.dev
1•astre9•7m ago•0 comments

Gemini Prompting Guide 101 – Executive Summary

https://twitter.com/TenZorroAI/status/1943620725367017761
1•paulo20223•8m ago•0 comments

Stacked Pull Requests FTW

https://www.git-tower.com/blog/tower-mac-13
1•andregit•8m ago•0 comments

Show HN: Dispytch – a Python framework for building event-driven services

https://github.com/e1-m/dispytch
1•e1-m•10m ago•0 comments

Genetic testing of critically ill adults can yield surprises

https://www.science.org/content/article/genetic-testing-critically-ill-adults-can-yield-surprises-and-reveal-disparities
1•rbanffy•12m ago•0 comments

The cloud is not a chemical plant

https://berthub.eu/articles/posts/the-cloud-is-not-a-chemical-plant/
1•TechTechTech•13m ago•0 comments

Stop forcing AI tools on your engineers – by Anton Zaides

https://newsletter.manager.dev/p/stop-forcing-ai-tools-on-your-engineers
3•rbanffy•17m ago•0 comments

FP8 is ~100 tflops faster when the kernel name has "cutlass" in it

https://twitter.com/cis_female/status/1943069934332055912
7•limoce•17m ago•1 comments

Google Research: Graph foundation models for relational data

https://research.google/blog/graph-foundation-models-for-relational-data/
2•ZeroCool2u•22m ago•0 comments

Show HN: Tweek GPT. Interact with your calendar and tasks using GPT

https://chatgpt.com/g/g-6855973a1d108191abb0a7708664b8f7-tweek
3•nikkey80•23m ago•0 comments

Accelerated demand for full-stack developers in 2025 (UK, US, and Canada)

https://www.barchart.com/story/news/33344443/belitsoft-reports-accelerated-demand-for-full-stack-developers-in-2025-uk-us-and-canada
1•Aninay•25m ago•0 comments

Simple Made Easy (2011) [video]

https://www.youtube.com/watch?v=SxdOUGdseq4
1•tosh•27m ago•0 comments

SQLite async connection pool for high-performance

https://github.com/slaily/aiosqlitepool
1•slaily•27m ago•1 comments

Platforms weren't supposed to be permanent

https://ravi64.com/permanent-platform-lock-in/
4•outrunner•33m ago•0 comments

The Meritocracy Trap

https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0326021
1•lentoutcry•35m ago•2 comments

Submatrix Cloud Phone and Cloud Storage

1•yt1314•36m ago•0 comments

At least 13 may have killed themselves over UK Post Office wrongful convictions

https://www.nbcnews.com/world/united-kingdom/least-13-killed-uks-post-office-wrongful-convictions-scandal-rcna217676
4•perihelions•36m ago•0 comments

Mystery interstellar object could be oldest known comet

https://www.bbc.com/news/articles/cx23g5jpj9go
1•neversaydie•36m ago•0 comments

A default McDonald's password left millions exposed

https://www.smartcompany.com.au/technology/big-hack-mcdonalds-data-breach-exposes-job-applicants-ai-hiring-paradoxai/
1•rbanffy•40m ago•0 comments

Trinity-1: Real-Time Gaussian-Splatting Avatar Model

https://twitter.com/simli_ai/status/1943399617380651455
2•gudmund•41m ago•0 comments

Britain and Europe need to get serious about air conditioning

https://www.ft.com/content/50f69324-8dc8-4ef1-b471-d78e260adae0
2•sandbach•41m ago•1 comments

Show HN: A Good Job Advert

https://sudowrite.com/jobs/designer
1•herodoturtle•47m ago•0 comments

Quantum Internet Is (Slowly) Becoming a Reality

https://cacm.acm.org/news/quantum-internet-is-slowly-becoming-a-reality/
2•pseudolus•49m ago•0 comments

At Amazon's Biggest Data Center, Everything Is Supersized for A.I

https://www.nytimes.com/2025/06/24/technology/amazon-ai-data-centers.html
9•pseudolus•51m ago•1 comments

3I/ATLAS: Interstellar object 'may be oldest comet ever seen'

https://phys.org/news/2025-07-3iatlas-interstellar-oldest-comet.html
2•pseudolus•53m ago•0 comments

Precision gene editing medicine makes history, and it's just getting started

https://www.nature.com/articles/s41587-025-02741-6
2•bookofjoe•54m ago•0 comments

Freed from ICE detention, Mahmoud Khalil files $20M claim against Trump admin

https://apnews.com/article/mahmoud-khalil-ice-release-trump-columbia-protests-570f7af32010c16b1a00dd7e78f4c687
3•sandbach•58m ago•0 comments
Open in hackernews

An almost catastrophic OpenZFS bug and the humans that made it

https://despairlabs.com/blog/posts/2025-07-10-an-openzfs-bug-and-the-humans-that-made-it/
29•r4um•4h ago

Comments

jpfr•2h ago
The problems with C are real.

At the same time, the tooling has gotten much better in the last years.

Clang-analyzer is fast enough to run as part of the CI. Newer gcc also give quite a few more warnings for unused results.

My recommendation to the project is to

- Remove all compiler warnings and enable warning-as-error

- Increase the coverage of unit tests to >80%

That is a lot of work. But that's what is required for high-criticality systems engineering.

a_t48•1h ago
FWIW you can do the same thing in cpp, too - but Rust’s syntax certainly makes it easier.
flohofwoe•1h ago
I'm not sure why C is blamed in this case when you can do exactly the same strong typing fix in C, and with C99 struct literals it's also not much worse to work with:

    typedef struct { size_t size; } PhysicalSize;
    typedef struct { size_t size; } AllocatedSize;

    PhysicalSize psize = { 123 }; // or { .size = 123 }
    AllocatedSize asize = { 234 };

    psize = asize; // error
...and in reverse, Rust wouldn't protect you from that exact same bug if the programmer decided to use usize like in the original C code.

IME overly strong typing is a double-edged sword though, on one hand it makes the code more robust, but on the other hand also more 'change resistant'.

I still would like to see a strong typedef variant in C so that the struct wrapping wouldn't be needed, e.g.:

https://www.open-std.org/jtc1/sc22/wg14/www/docs/n3320.htm

beeb•57m ago
Rust would warn you of an unused variable: "warning: value assigned to `psize` is never read"
bloak•45m ago
And so would GCC: warning: variable psize set but not used [-Wunused-but-set-variable]
beeb•35m ago
The fact that the bug slipped through the cracks highlights the importance of sane defaults.
flohofwoe•15m ago
The warning is in the -Wall warning set, which tbh should be the bare minimum each C/C++ project enables (along with -Wextra, and -Werror).
fredoralive•1h ago
I missed it, but I was distracted by cols variable being initialised with the original width, but then being immediately overwritten with the logical width.
Cthulhu_•1h ago
Wouldn't this have been caught by an exhaustive unit test or even a fuzz test? I don't know what kind of testing practices are applied to projects like zfs, nor what kinds or amounts of tests functions like this are subject to, but I would imagine that especially for low-level functions like this, unit tests with all of the known edge cases would be written.

(yes this is very much an armchair opinion, I mostly do front-end JS for a living)

bspammer•1h ago
Yeah that surprised me too - I would have assumed that ZFS had a bunch of "store and retrieve" tests in many different configurations that would have caught this.
4gotunameagain•3m ago
Does it even need an exhaustive unit test?

A single call where the psize is different than the asize would have caught it.

topspin•1h ago
I found it. All that tells you is that it's a simple problem. Had I not been told it was broken I likely would not have.

It's the kind of bug that makes you stop breathing for a brief moment. So I ran this function through Gemini 2.5 Pro, ChatGPT o3 and Grok 3. No context other than the source code fragment was provided. All three also clearly identified the problem.

There is no longer a reason for trivial flaws such as this surviving to release code. We're past that now, and that's an astonishing thing.

These are the questions I ponder: Should we consider the possibility that the ongoing, incomplete and decades long pursuit of "better" languages is now misguided? Or, that perhaps "better" might now mean whatever properties make code easier for LLMs to analyze and validate against specifications, as opposed to merely preventing the flaws humans are prone to make?

kalaksi•1h ago
> whatever properties make code easier for LLMs to analyze

So double down on languages that are more represented in training data? I think it's still worthwhile to actually improve programming languages. Relying only on LLMs is fragile. So ideally do both: improve language and AI.

topspin•37m ago
> So double down on languages that are more represented in training data?

The pragmatic answer to that is: this appears to be highly effective.

What I have in mind is something else, however. Consider the safety nets we try to build with, for example, elaborate type systems. These new analysis tools can operate on enormous contexts and infer and enforce "type" with a capacity far greater what a human mind can hope to approach. So perhaps there is little value to complex types. Instead, a simple type system supported by specification will be the superior approach. seL4 is an example of the concept: C, but exhaustively specified and verified.

dwroberts•1h ago
> I found it. All that tells you is that it's a simple problem

Not totally clear what you mean here - are you saying you’re the author of the article or PR, or that you independently discovered the same issue (after the fact)?

topspin•33m ago
Ok, so somehow that is causing confusion. I will clarify.

The author asked that the reader attempt to find the flaw by inspecting the provided code. The flaw was obvious enough that I was able to find it. The implication is that if it were less obvious, I might not have. I was not attempting to take any credit at all: exactly the opposite.

piker•46m ago
No way is it practical to run complex code like this through a sycophantic parrot. Try it again with some old, well known code and see how many “Certainly! Your error is …” you get.
spacecadet•7m ago
Doesnt make one much more than a sycophantic parrot when they also repeat platitudes without anything else to add.
perching_aix•5m ago
There was an article here about a month or so ago doing exactly that unpractical thing against I think NFS, and finding a small handful of confirmed vulnerabilities that way. Wish granted I suppose?
rini17•35m ago
Don't forget author did 99% of the work for you by finding that function.
topspin•32m ago
Having wrote "Had I not been told it was broken I likely would not have," should make it clear that this wasn't lost on me.
spacecadet•9m ago
Like gibberlink. Programming languages are insane to me. In a way we created them to communicate with machines, but they evolved to complement a very human workflow. It makes little sense outside of assisting humans to train LLMs on human computer languages, why not let the AIs generate their own optimized languages?
topspin•1m ago
> why not let the AIs generate their own optimized languages?

Excellent question. What would it end up looking like? Would it be full of monads and HKTs? Lambda calculus? WebAssembly?

I hope to learn the answer one day.

0points•4m ago
> There is no longer a reason for trivial flaws such as this surviving to release code.

This is unrelated to "no longer due to ChatGPT times".

We've been able to detect this issue for decades already, see -Wunused-variable.

apple1417•1h ago
Having run into similar problems several times, I've also never really been satisfied with the solutions. You have to have different types to cause compile errors, but then you have throw those types away whenever you perform any actual operations on them.

    struct TypeA { int inner; };
    struct TypeB { int inner; };

    struct TypeA a1, a2;
    // whoops
    TypeB result = {.inner = a1.inner + a2.inner};
Don't get me wrong, where I've used this sort of pattern it's definitely caught issues, and it definitely massively lowers the surface area for this type of bug. But I still feel like it's quite fragile.

The use case I felt worked best was seperating out UTC datetime vs localised datetime structs - mainly since it's something you already had to use function calls to add/subtract from, you couldn't play with raw values.

Narew•1h ago
It remind me a devlog from andrew kelley on the same topics : https://ziglang.org/devlog/2024/#2024-11-04
atiq-ca•1h ago
Thanks contribution to openzfs.
Nokinside•1h ago
Software verification tools based on abstract Interpretation are really good today.

If you want free software I recommend IKOS - a is a sound static analyzer for C/C++ developed at NASA. Checks: https://github.com/NASA-SW-VnV/ikos/blob/master/analyzer/REA... Numerical abstract domains: https://github.com/NASA-SW-VnV/ikos/blob/master/analyzer/REA...

Commercial tool like Astree https://www.absint.com/astree/index.htm if you have money.

prmoustache•54m ago
Isn't it a case for eliminating all warnings and treat them as bugs?

It seems you are dooming your project the minute you start ignoring your first warning.

bloak•36m ago
Most projects I've worked on treat warnings as bugs. It's annoying, sometimes, when you have to fiddle with the code and add lines to prevent bogus warnings from breaking the build, particularly when you're making a temporary change for debugging purposes, and I remember a couple of occasions when we had to insert a comment something like "This was needed to prevent a warning caused by a bug in GCC X.Y.Z (link to compiler bug on issue tracker)". But, on balance, it's worth it.
nottorp•54m ago
So why is the solution Rust, and not any of the other 2000 "modern" languages?
desdenova•38m ago
So give me a list of the 2000 languages OpenZFS could've been written in.
Uriopass•50m ago
In this case any simple unit test would have catched it. Surprised it wasn't mentioned in the post.
0points•6m ago
Unexpected issue (for me).

I would have expected that the compiler should complain that psize is computed but unused.

Why isn't -Wunused-variable enabled in OpenZFS?

v5v3•4m ago
Gpt4o-mini response:

>The provided code snippet is a function that converts an allocation size (asize) into the largest physical size (psize) that can be safely written to an allocation for a given virtual device (vdev). Here are some observations and potential issues in the code:

Return Value: The function currently returns asize instead of psize. This seems to be a mistake, as the purpose of the function is to compute and return the psize. The correct return statement should be:

    return psize;
Comment Clarity: The comments mention that the function does not take into account the effect of gang headers. It might be helpful to clarify what "gang headers" are and how they affect the allocation sizes, especially for someone unfamiliar with the context.

Variable Initialization: The variable psize is calculated based on asize, ashift, cols, and nparity. Ensure that these values are correctly initialized and that vdev_raidz_get_logical_width returns a valid value for cols. If cols is zero, it could lead to division by zero in the DIV_ROUND_UP macro.

Assertions: The assertion ASSERT0(asize % (1 << ashift)); checks that asize is a multiple of 2^ashift. If this assertion fails, it will cause the program to terminate. Ensure that this condition is always met before calling this function, or consider handling this case more gracefully.

Macro Usage: The DIV_ROUND_UP macro should be checked to ensure it handles edge cases correctly, such as when psize is zero. If psize is zero, the division could lead to unexpected behavior.

Code Readability: Consider adding more comments to explain the logic behind the calculations, especially for someone who may not be familiar with the RAID-Z implementation.

Error Handling: There is no error handling in the function. Depending on the context in which this function is used, it might be beneficial to add checks for invalid input values and return an error code or handle exceptions accordingly.

Here is a revised version of the function with the return value corrected:

.....(Snipped for formatting issues)

Make sure to test the function thoroughly to ensure it behaves as expected under various conditions.