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

301–310 of 667 posts

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

#301

Post by stack_framer »

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 useless suggestions are exhausting. One of my co-workers uses Claude for all asynchronous communication, including Slack messages, Jira comments, code reviews, and emails.

Every single message from him, literally every time he communicates, it's a massive wall of text, overflowing with scope-creep suggestions like nothing I've ever seen before. It's impossible to ask him a simple question and get a simple answer.

And this seems to be a broader trend with AI in general. It's getting more and more difficult to retain some semblance of brevity with AI tools. I'm constantly asking them to "be brief," and "only answer the question I asked," and "don't provide more information than I requested," but they keep churning out more than I want in their responses.

It looks like a subtle attempt to use up more tokens.

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

#302

Post by internet2000 »

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…

Is this with the good Anthropic models? With extended thinking? And a way for it to validate the changes? My experience is the complete opposite.

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

#303

Post by RGS1811 »

dpark wrote: post #285
RGS1811 wrote: post #259

Earlier quoted context omitted.

It comes from C. Northcote Parkinson's work, where he calls it "The Law of Triviality". The idea is that people clog up decision-making by introducing a swarm of issues that have little relative impact or importance for the project at hand, leading to a massive misallocation of attention. His example is a $10 million construction project for a Nuclear Reactor where as much time is spent debating the materials to be u…

Thanks. I know what bikeshedding is. I’m asking what cyandees specifically means. The normal definition of bikeshedding doesn’t seem to make any sense in his sentence. I’m assuming he’s using it to mean “cruft” or “low value features” but maybe there’s some meaning I’m missing.

Funny enough, I didn't know, but your comment made me look it up, then I tracked down a PDF of the book, read the relevant section, and wrote my reply. So, even if I didn't help you out, you helped me lol.

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

#304

Post by chrisjj »

stack_framer wrote: post #301
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 useless suggestions are exhausting. One of my co-workers uses Claude for all asynchronous communication, including Slack messages, Jira comments, code reviews, and emails. Every single message from him, literally every time he communicates, it's a massive wall of text, overflowing with scope-creep suggestions like nothing I've ever seen before. It's impossible to ask him a simple question and get a simple answer.…

Have you ever seen him and Claude in the same room?

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

#305

Post by rootusrootus »

stack_framer wrote: post #301
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 useless suggestions are exhausting. One of my co-workers uses Claude for all asynchronous communication, including Slack messages, Jira comments, code reviews, and emails. Every single message from him, literally every time he communicates, it's a massive wall of text, overflowing with scope-creep suggestions like nothing I've ever seen before. It's impossible to ask him a simple question and get a simple answer.…

As much as I don't truly love the shop I'm at now, stories like this keep me from looking for anything new. At least until the AI psychosis [hopefully] passes. I can't even get my management to approve a $100 Claude Max subscription, which is kind of annoying but also means they have not changed their expectations on what the team produces. None of my coworkers is going to be shoveling AI slop my direction because then they'd have to explain to management why they are using an unapproved tool to look at internal company code.

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

#306

Post by stackskipton »

internet2000 wrote: post #302
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…

Is this with the good Anthropic models? With extended thinking? And a way for it to validate the changes? My experience is the complete opposite.

I hate these type of questions, they scream "YOUR HOLDING IT WRONG."

My experience is if you have been racking up the tech debt and have some low hanging fruit, Claude is really good at cleaning it up. If you have been properly stewarding the project, it's much less effective.

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

#307

Post by paulddraper »

The current title says "Google fixed more Chrome bugs in June than over the past two years, thanks to AI."

This is wrong on almost every count.

1. The numbers are by milestone not month.

2. The latest milestone (or month) did not exceed the previous two years of milestones.

3. The only thing discussed are security bugs, not bugs in general.

What is true: the article is about Chrome.

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

#308

Post by dpark »

RGS1811 wrote: post #303
dpark wrote: post #285

Earlier quoted context omitted.

Thanks. I know what bikeshedding is. I’m asking what cyandees specifically means. The normal definition of bikeshedding doesn’t seem to make any sense in his sentence. I’m assuming he’s using it to mean “cruft” or “low value features” but maybe there’s some meaning I’m missing.

Funny enough, I didn't know, but your comment made me look it up, then I tracked down a PDF of the book, read the relevant section, and wrote my reply. So, even if I didn't help you out, you helped me lol.

It’s a good term. :)

I originally heard it in the context of picking paint color for the bike shed, which is probably more on point for software engineers, most of whom would not be involved in any discussion around building a nuclear reactor.

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

#309

Post by dgemm »

stack_framer wrote: post #301
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 useless suggestions are exhausting. One of my co-workers uses Claude for all asynchronous communication, including Slack messages, Jira comments, code reviews, and emails. Every single message from him, literally every time he communicates, it's a massive wall of text, overflowing with scope-creep suggestions like nothing I've ever seen before. It's impossible to ask him a simple question and get a simple answer.…

They bill you per output token.

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

#310

Post by shuwix »

mettamage wrote: post #208
herrkanin wrote: post #34

Earlier quoted context omitted.

The thing that makes it work really well is to make sure it has all the tooling to verify its hypotheses. If you allow it to run the full lifecycle in loops you will be surprised how well it works.

Just like humans, AI needs a "reality" to check things against. If we don't provide that in an automated way, somehow, it will always make mistakes and we'd have to point it out. Since, at that point, we're just mediating with what reality gives us and what an AI should do with it. AI doesn't have enough senses yet. It's trapped in a box.

There's an old programming rule since 90's: By fixing a bug, 3 new bugs appear.

I can imagine the quality of bug fixing by unsupervised (we save money by layoffs) halucinating AI at current state of development.

Post reply on HN