Live data from Hacker News

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

blog.google

661–667 of 667 posts

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

#661

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…

> These days most of the sensible people have moved from C++ to Rust

Wrong. There are more than 16 million C++ developers worldwide.

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

#662
post #413

Earlier quoted context omitted.

LLM increase the range of things bikesheddable, so some folks will try to have a LLM design a nuclear reactor and manage the coffee budget in addition to the traditional bikeshed design complications. Whether this is an improvement or more engines of what passes for civilization catching on fire, well…

I don’t understand how LLMs make more stuff “bike sheddable”. What LLMs do is allow people to contribute low value garbage to all areas, but we have a word for that and it’s not “bike shedding”. It’s “slop”.

And that slop increases the range of things bikesheddable, like having free kerosene and matches available at an Arson Anonymous meeting.

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

#663
post #528

Earlier quoted context omitted.

Most programmers don’t have 30 years to perfect their code

It had no crash during 30 years, not after 30 years.

I did, in Linux. It was pretty common too. It got fix. But, every now and then, I still get an occasional panic.

I also recall having my shell crashing (zsh or bash, I don't remember).

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

#664
post #528

Earlier quoted context omitted.

It had no crash during 30 years, not after 30 years.

I did, in Linux. It was pretty common too. It got fix. But, every now and then, I still get an occasional panic. I also recall having my shell crashing (zsh or bash, I don't remember).

I certainly also remember the kernel crashing, but this was in the 90s. Later perhaps once or twice on faulty hardware. Shell, I don't think I have seen this ever.

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

#665
post #529

Earlier quoted context omitted.

Until a couple of years ago you needed to be able to read research papers and code to build fuzzing harnesses and triage the findings to find vulns. Now you can point Claude, codex, Kimi, or even some smaller open models that run local and get a servable fuzzing loop in a couple of hours. That's democratization - shifting power and skills away from those with the wealth to purchase vulns and run offensive security te…

Instead you need the wealth to buy infinite tokens, right?

Sure. Wealth has always given early adopters and first movers wings.

As hardware specs get better, and model providers keep making different classes of mistakes that alienate users, more people will opt for or support local models. I tend to take Schneiers' "Attacks only improve" philosophy and apply it to damn near everything like this. Inference will get more expensive, but IMO cloud based inference is at or near the maximum that users can tolerate, across multiple spectra. There may be a marginal increase in cost, but as the different metrics between what is affordable for rapidly scalable, cloud based inference and the lag of local inference with open models and expensive hardware converge, prices will come down.

I am not the right person to say what the peak is going to look at, but when the companies with (practically speaking) unlimited compute resources and money are starting to take a good hard look, there is going to be a drive towards efficiency. I hear grumbling at work, and the appreciation from my leaders when I show up with a tool that shows how I reduced my token costs, or I keep asking the questions of what the token cost (real, and internal billing) are for tools my peers write are.

I also have absolutely eye-watering personal AI bills that are starting to make buying a better tier of local inference gear look more affordable, even with inflated hardware prices. The current generation of open models are very effective, and paying for multiple $200 dollar a month subs is not feasible longer term, and as one example, in one month, if I was paying enterprise token rates, I would have burned through $8000+ token budgets on one of those accounts, doing actual, practical useful work, it makes more sense to buy some much better hardware than to pay for one-time inference costs.

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

#666
post #664

Earlier quoted context omitted.

I did, in Linux. It was pretty common too. It got fix. But, every now and then, I still get an occasional panic. I also recall having my shell crashing (zsh or bash, I don't remember).

I certainly also remember the kernel crashing, but this was in the 90s. Later perhaps once or twice on faulty hardware. Shell, I don't think I have seen this ever.

In my case, the crashes were from last year to the start of this one. Some were related to AMDGPU, others to my WiFi card driver, so they're pretty recent.

I don't quite remember the details of the shell crash, I only remember it being on a tool that've never seem crash due to a fault signal. It was somewhat amusing.

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

#667

Have LLMs shown any decent capabilities in resolving non-security bugs yet? Security bugs are important, but my day to day frustration with tech tends to be caused by UX/functionality bugs. And Google seem to struggle more than most other companies with those. Google Home became so unbelievably buggy, and I felt so betrayed by that, that I stopped using every single Google product - from Gmail to Android to Google Cl…

The Google Home is hot garbage. I do like the hardware though.
Post reply on HN