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

21–30 of 668 posts

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

#21

Post by nevi-me »

truncate wrote: post #5

Not that I don't believe its possible to fix a lot of bugs, I also wonder what the actual dynamic was. Were the people in team working much more than usual as well? Given its Google, I wouldn't be surprised if there was an "internal push" to fix more bugs over next X sprints so that they can publish this blog and some manager can show impact and AI adaption to his superior.

1. Our backlog of bugs gets processed quicker because instead of staring at the code for 10 minutes fiuring out what's happening, there's a tool that can reason about it quicker.

2. Code reviews and security reviews happen quicker and produce more findings.

I would think that (m)any team(s) using AI might also be seeing a higher rate of finding and fixing issues.

Even the Linux Kernel (I'd say Windows and Apple too) are seeing the same phenomenon.

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

#22

Post by MadsRC »

ed_mercer wrote: post #6

AI meaning Claude or Codex, because Gemini is a laughingstock for coding. Also Gemini was mentioned only once in the article.

I’ve heard from people inside Google that they’re prohibited from using anything but their own models. AlbertaTech on YT, ex-Google working on YT said in a video that right before she quit someone had threatened to quit if they couldn’t get access to Claude Code

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

#23

Post by Oras »

greenknight wrote: post #8
ed_mercer wrote: post #6

AI meaning Claude or Codex, because Gemini is a laughingstock for coding. Also Gemini was mentioned only once in the article.

The Gemini (and Claude / Codex) that we have, is much different to their internal models / harnesses.....

Trust me bro?

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

#24

Post by flohofwoe »

onesandofgrain wrote: post #13
geek_at wrote: post #4

Earlier quoted context omitted.

won't forgive them either for making it harder to filter out ads

[flagged]

That's something those products need to figure out, not the users, one potential solution is to erect paywalls and find out how much those products are actually worth to their users ;)

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

#27

Post by staszewski »

dabedee wrote: post #16

How many of those automated fixes were reverted? How many introduced a new bug? What's the false positive rate on the finding agents? The post has counts for everything that went right and nothing for what could go wrong.

[flagged]

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

#28

Post by colechristensen »

VBprogrammer wrote: post #17

I've recently been using AI a lot for performance optimisation during a particularly busy period at work. I would say it was almost completely useless at the high-level direction - it would point out suspicious parts of SQL queries for example but on back to back testing these almost never resulted in any performance change. In fact, if it wasn't for the fact that it made making the actual changes I identified much e…

Then you're not grounding it to reality properly. LLMs get bad pretty quickly when you just tell them to pull the answer out of thin air. Pin them to reality with actual performance tests to run to test theories and the results will be much better.

Performance optimization involves simulating real world loads and measurable results. Give them the opportunity to actually have a closed loop if you want more than trivial improvements.

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

#29

Post by WhyIsItAlwaysHN »

VBprogrammer wrote: post #17

I've recently been using AI a lot for performance optimisation during a particularly busy period at work. I would say it was almost completely useless at the high-level direction - it would point out suspicious parts of SQL queries for example but on back to back testing these almost never resulted in any performance change. In fact, if it wasn't for the fact that it made making the actual changes I identified much e…

The mistake there is to point it at code to figure out performance optimizations.

The place to find them would be performance profiles, query plans, telemetry. The guidance for perf still applies, measure before and after change.

The issue is that the code often does not contain the information to do a perf optimization. Eg. you can't tell your cache size, the volumes of data in your DB or the latency of your network through just the text. Should you provide this context, you can get better results.

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

#30

Post by sigmoid10 »

VBprogrammer wrote: post #17

I've recently been using AI a lot for performance optimisation during a particularly busy period at work. I would say it was almost completely useless at the high-level direction - it would point out suspicious parts of SQL queries for example but on back to back testing these almost never resulted in any performance change. In fact, if it wasn't for the fact that it made making the actual changes I identified much e…

Which model/agent/harness tool did you use? I've found what you describe was my exact experience some ~6-8 months ago, but since about a month or so the game has completely changed. Using 5.6 Sol with highest reasoning setting in Codex or Fable in Code, the models come up with a list of possible improvements from static analysis (ranked by complexity/benefit), write and run their own custom profilers and deliver significant performance improvements with barely any input needed from my side. So this is no longer a model issue, it's a user toolchain issue.
Post reply on HN