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

Google fixed more Chrome bugs in June than over the past two years, thanks to AI

blog.google

Post reply on HN
Print view View original

571–580 of 667 posts

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#571

Post by intellix »

userbinator wrote: post #550

What remains to be seen is whether Google also introduced more Chrome bugs in June than over the past two years, thanks to AI. The big problem is that AI output can be very convincing and look "right", even appear to work, until you examine it in detail and realise all the edge-cases it didn't handle.

to be fair, with AI reviews i'm finding the opposite to be true. Anytime I push a one line fix it continuously tells me about all of the edge cases I didn't handle until it's pretty much bullet proof

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#572

Post by tonfa »

throwaway2037 wrote: post #560
hn_submit wrote: post #389

To me this merely signals how broken C++ development really is. Most if not all of the bugs being uncovered are memory related and therefore intimately tied to the mental memory model of C and C++, namely manual memory management. It's fine for a C or C++ program encompassing a couple hundred lines but beyond that it's a liability. C and C++ are simply not fit for purpose when large scale software projects are concer…

Assume that you are writing a green field project in C++. If you never use "naked pointers" and always use std::unique_ptr and std::shared_ptr, will it not reduce nearly all memory related bugs? I don't have a lot of experience with them, but I found it dramatically reduced memory related bugs. I'm a very average C++ programmer, and those templates helped me greatly. Do you think it would help Chrome/ium to use (more…

At a minimum you'd also need to enable runtime bound checking for span/vector accesses (I think chrome did that).

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#573

Post by karmasimida »

userbinator wrote: post #550

What remains to be seen is whether Google also introduced more Chrome bugs in June than over the past two years, thanks to AI. The big problem is that AI output can be very convincing and look "right", even appear to work, until you examine it in detail and realise all the edge-cases it didn't handle.

Let's be honest with ourselves, AI review is better than human right now, especially top tier models. Not saying that for important project like Chrome, you can skip reviewing changes. Far from it. But it is probably better and more thorough than most human devs already.

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#574

Post by raverbashing »

fluffybucktsnek wrote: post #559
rpdillon wrote: post #487

Earlier quoted context omitted.

Makes sense, but strangely, no one has responded to my question about why Servo hasn't been picked up, if Rust is such an important factor in browser engine implementation. People are calling using C and C++ "ridiculous" and "irresponsible" and "not fit for purpose". And yet, no one's using the alternative that's sitting right there?

Because Servo is unfinished, and companies have different priorities. For instance, Microsoft could've have been strict and formally checked code for Windows since the inception of constraint checkers, but they chose other priorities. Now they're are slowly trying to integrate Rust to help reduce security bugs.

You know what's funny?

Windows was built in C when "C was not guaranteed to win", hence why they have weird things like Pascal calling convention etc

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#575

Post by myko »

IshKebab wrote: post #546
MichaelZuo wrote: post #493

Earlier quoted context omitted.

The real curious thing is serious C/C++ folks seem like one of the least likely groups imaginable, to want to undergo humiliating and embarrassing blunders… Yet they seemingly don’t mind that it practically guarantees them to make blunders over and over again.

Pre-Rust "serious C++ folks" used it because it was the best option if you wanted essentially zero performance overhead no heavy runtime and GC spikes. They didn't like the lack of memory safety but it was seen as an unfortunate but necessary trade-off. These days most of the sensible people have moved from C++ to Rust and so the "serious C++ folks" are an entirely different distribution of people who are much more i…

or Swift! I know it isn't super popular outside of Apple ecosystems but I migrated a C 200k LOC personal project to Swift over the last ~4 years and it's gone really well.

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#576

Post by zik »

hn_submit wrote: post #389

To me this merely signals how broken C++ development really is. Most if not all of the bugs being uncovered are memory related and therefore intimately tied to the mental memory model of C and C++, namely manual memory management. It's fine for a C or C++ program encompassing a couple hundred lines but beyond that it's a liability. C and C++ are simply not fit for purpose when large scale software projects are concer…

> Most if not all of the bugs being uncovered are memory related

I checked the stats. 73% were memory management related issues, mostly use-after-free.

The rest were logic errors of various sorts.

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#577

Post by fennecbutt »

gtowey wrote: post #496
MichaelZuo wrote: post #493

Earlier quoted context omitted.

The real curious thing is serious C/C++ folks seem like one of the least likely groups imaginable, to want to undergo humiliating and embarrassing blunders… Yet they seemingly don’t mind that it practically guarantees them to make blunders over and over again.

We call them blunders mostly because the solutions are so well known. In contrast, the last company I worked for did everything in typescript and the amount of problems caused by code that blocked the main event loop was staggering. And at that, our best JavaScript people generally just threw up their arms saying there wasn't a good way to fix it. Between the two, I prefer a language that lets me fix problems.

"our best java script people" I've used node.js for more than a decade now, I was there for the start of "now everyone is truly full stack"...but yes the majority of developers I've worked with have had no idea about how js etc works on the inside, no knowledge of event loop or what causes the few memory leaks possible in js.

But then again I only know because I love that shit and started out in c/embedded, c# etc. And on my own weak side I fucken suuuuck at frontend related stuff (not the design stuff at all, just...fuck you css).

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#578

Post by fennecbutt »

Matheus28 wrote: post #512
Dylan16807 wrote: post #466

Earlier quoted context omitted.

Even if that was the tradeoff, your average C/C++ program isn't notably fast or lean.

I’ll take a Qt application over the Electron garbage that we see all the time nowadays.

10-100x develop & maintain cost.

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#579

Post by wizzwizz4 »

userbinator wrote: post #550

What remains to be seen is whether Google also introduced more Chrome bugs in June than over the past two years, thanks to AI. The big problem is that AI output can be very convincing and look "right", even appear to work, until you examine it in detail and realise all the edge-cases it didn't handle.

I've heard screen-reader users reporting that Chrome and Edge are now virtually unusable in their Windows screen-reader, while Firefox remains fine.

Re: Google fixed more Chrome bugs in June than over the past two years, thanks to AI

#580

Post by prymitive »

karmasimida wrote: post #573
userbinator wrote: post #550

What remains to be seen is whether Google also introduced more Chrome bugs in June than over the past two years, thanks to AI. The big problem is that AI output can be very convincing and look "right", even appear to work, until you examine it in detail and realise all the edge-cases it didn't handle.

Let's be honest with ourselves, AI review is better than human right now, especially top tier models. Not saying that for important project like Chrome, you can skip reviewing changes. Far from it. But it is probably better and more thorough than most human devs already.

To be fair it’s also worth noting that it’s much easier to find a buggy edge case with existing code than it is to write bug free code that doesn’t have any edge cases at all. It’s so much easier to read some concrete logic and find holes in it, than it is to start from nothing and end up with perfection. It’s true both for humans and agents, but agents are better are validating correctness.
Post reply on HN