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

Google Antigravity

antigravity.google

Post reply on HN
Print view View original

951–960 of 1001 posts

Re: Google Antigravity

#951

Post by bluelightning2k »

vimto wrote: post #938

I've been using it today and honestly I'm impressed. I seem to be the exception when I say I don't care it's a vscode fork. Having access to the extension ecosystem seems like a boon to me and I could quickly get a setup to my liking to rival my current Jetbrains Claude Code setup. It seems to streamline my existing Claude Code workflow with a much better UI. The tab complete seems the best I've experienced and the t…

I agree! It's great. Until you hit the limit, then there's literally no path to continue.

I would happily pay 20 or whatever for 4x limits. I'm very curious what they end up offering. My major reservation is side project vibes. I think it's hard to believe on this long term unless Google themselves adopt it.

Re: Google Antigravity

#952

Post by chrz »

eranation wrote: post #900

Petty nitpick, but this sentence doesn’t sound right > “Google Antigravity's Editor view offers tab autocompletion, natural language code commands, and a configurable, and context-aware configurable agent.” Is it a typo or was there a reason to add configurable twice?

They might have made the whole thing with AI to prove you can make things with AI

Re: Google Antigravity

#953

Post by Huppie »

vimto wrote: post #938

I've been using it today and honestly I'm impressed. I seem to be the exception when I say I don't care it's a vscode fork. Having access to the extension ecosystem seems like a boon to me and I could quickly get a setup to my liking to rival my current Jetbrains Claude Code setup. It seems to streamline my existing Claude Code workflow with a much better UI. The tab complete seems the best I've experienced and the t…

How is it compared to Cursur though?

Re: Google Antigravity

#954

Post by rglover »

mrweasel wrote: post #830
rglover wrote: post #171

We have a real, serious problem when even Google (presumably with a large share of the world's engineering might) is just forking VSCode.

Something incredibly weird is going on in the "AI space", everyone seems to believe that they need their own browser and IDE. All of them are just forks of each other, so why aren't they extensions or plugins? I can't really explain what the issue is, I'd assume it's about lock in, but I don't see a VS Code fork or yet another Chromium browser being something that a person couldn't easily replace with another similar…

> It that the pitch internally? Lock users into a browser or IDE, so they'll be forced to use a certain AI?

Shrugs that's the only reason that makes any sense short of they're just being blindly mimetic (which, let's be honest, isn't outside of the realm of possibility these days).

Re: Google Antigravity

#955

Post by vinay_ys »

throwaway13337 wrote: post #439

I gave it a fair shot. It is a vs code fork. There were some UI glitches. Some usability was better. Cursor has some real annoying usability issues - like their previous/next code change never going away and no way to disable it. Design of this one looks more polished and less muddy. I was working on a project and just continued with it. It was easy because they import setting from cursor. Feels like the browser wars…

This. I got overload error on the very first prompt just now. Didn't expect google to run into overload error.

Re: Google Antigravity

#956

Post by sauercrowd »

Comments here complaining about the fact that it's vscode seem to miss the point here.

That's a huge advantage, it's means all the obvious stuff will just work. LSPs, debuggers, version control, customisation.

As much as I like Emacs, it's an insane pain to make all these things work.

If your value prop is agents on a codebase, there's no point in trying to reinvent those. They have basically been solved.

Re: Google Antigravity

#957

Post by etruong42 »

senbrow wrote: post #902
throwaway13337 wrote: post #439

I gave it a fair shot. It is a vs code fork. There were some UI glitches. Some usability was better. Cursor has some real annoying usability issues - like their previous/next code change never going away and no way to disable it. Design of this one looks more polished and less muddy. I was working on a project and just continued with it. It was easy because they import setting from cursor. Feels like the browser wars…

As someone who used to work there, Google will never get product releases right in general because of how bureaucratic and heavyweight their launch processes are. They force the developing team to have a huge number of meetings and email threads that they must steer themselves to check off a ridiculously large list of "must haves" that are usually well outside their domain expertise. The result is that any non-critic…

Spot on. I would suggest a slightly different framing where the antagonist isn't really the "approving" teams but "leaders" who all want a seat at the table and exercise their authority lest their authority muscles atrophy. Since they're not part of the development, unless they object to something, would they really have any impact or leadership?

I always laugh-cry with whomever I'm sitting next to whenever launch announcements come out with more people in the "leadership" roles than the individual contributor roles. So many "leaders" but none with the awareness or the care of the farcical volumes such announcements speak.

Re: Google Antigravity

#958

Post by bitpush »

phantasmish wrote: post #728
bitpush wrote: post #689

Earlier quoted context omitted.

> Google likes to fuck with basic browser functionality for some reason. Apple is the worst offender here. Their product pages are always sluggish.

Yeah, though with theirs I can usually see why they did it (even if I’d rather they didn’t). Google’s MO is messing with scrolling for what often appears to be no user-facing reason at all.

> I can usually see why they did it

wut? scrollhijacking is bad, and doesnt matter who does it.

Re: Google Antigravity

#959

Post by overgard »

dabockster wrote: post #496
alansammarone wrote: post #480

Earlier quoted context omitted.

I believe our definitions of "winning the IDE wars" are very, very different. For one thing, using "user count" as a metric for this like using "number of lines of code added" in a performance review. And even if that was part of the metric, people who use and don't absolutely fall in love with it, so much so that they become the ones advocating for its use, are only worth a tiny fraction of a "user". neovim won the…

> I don't know what IntelliJ is. It started as a modernized Eclipse competitor (the Java IDE) but they've built a bunch of other IDEs based on it. Idk if it still runs on Java or not, but it had potential last I used it about a decade ago. But running GUI apps on the JVM isn't the best for 1000 reasons, so I hope they've moved off it.

I don't know what it's based on, but it works extremely well. I use Rider & WebStorm daily and I find Rider is a lot faster than Visual Studio when it comes to the Unreal Engine codebase and WebStorm seems to be a lot more reliable than VSCode nowadays (I don't know if it's at fault, but ever since copilot was integrated I find that code completion can stop working for minutes at a time. Very annoying)

Re: Google Antigravity

#960

Post by vimto »

bluelightning2k wrote: post #951
vimto wrote: post #938

I've been using it today and honestly I'm impressed. I seem to be the exception when I say I don't care it's a vscode fork. Having access to the extension ecosystem seems like a boon to me and I could quickly get a setup to my liking to rival my current Jetbrains Claude Code setup. It seems to streamline my existing Claude Code workflow with a much better UI. The tab complete seems the best I've experienced and the t…

I agree! It's great. Until you hit the limit, then there's literally no path to continue. I would happily pay 20 or whatever for 4x limits. I'm very curious what they end up offering. My major reservation is side project vibes. I think it's hard to believe on this long term unless Google themselves adopt it.

I think hitting limits is a common complaint I see across all the AI tools. I used it with Gemini Pro and didn't hit such limits.
Post reply on HN