Browse Comments — Clean (de-noised)
Close reading of the corpus at each pipeline stage: raw → clean → relevant → coded.
86
comments matched
· page 2 of 5
Antigravity(Antigravity 1.0) was quite disappointing from almost every perspective when I tried it about few months ago - user onboarding, initial setup, vague/incomplete documentation, limited token quotas, token limits tied to Google One plans, lack of proper token usage visibility, no straightforward way to use models from Google Cloud Vertex AI Model Garden, and more. I genuinely hope Google has significantly improved all of these aspects.
Huzaib Shafi
Though not still in league of claude code or even codex but the direction is right and one cannot underestimate google
I don't think so. This is only a new product that google created to trap people to think that is possible to build agentic workflows without deterministic tools. They just killed the antigravity IDE to replace it with this thing that is agentic, but surprise, they gonna charge more for that. Nothing is free
Wow, what a money farming machine... to Google
lol all that AI and they didn’t bother to remove the AI chop slop purple! All power and no craftsmanship.
the rate limits are obnoxious
And quota ends within 2 hours
The shift from writing code to directing intelligence was always inevitable — most just didn’t see it coming this fast.
Not there yet. Google is more hype and marketing than real world usability
The best engineers of the next decade will not be the fastest typists. They will be the best orchestrators, and that race just got a lot more interesting.
What stood out to me from Google I/O wasn’t just the 93 agents part. It’s the shift from coding manually to managing systems of agents and workflows. Now the bottleneck is orchestration. The challenge isn’t generating code, but designing good context, coordination, and decision flow between agents.
their app dont even work
Let's not forget this
Claude intelligence (cowork) is far better anti gravity.... Anthropic is already won...
No it didn’t
I think Anthropic and OpenAI in trouble... 😄
Google antigravity it was a garbage for real life coding and now is a fast garbage. They passed all trust me bro benchmarks but for real life coding any open source Chinese model is way better.
Since this showed up in my feed, I’ll call out its b.s. ... “Turns your laptop into a full AI software company.” — This is what’s wrong with LinkedIn posts! Why do people feel it necessary to put exaggerated nonsense in their posts? In our new world of AI, LinkedIn should do a better job of preventing posts that spread non-factual misinformation like this garbage. You should be ashamed of yourself for posting misinformation for the sake of hype. Truly a disgusting tactic, and says a lot about the type of person you are.
Sheshadri Bhattacharyya I’m rooting for Google too. The vision is right, AI orchestration is clearly the future. But execution still matters. Right now, a lot of developers care less about “93 agents in parallel” and more about reliability, output quality, and cost efficiency. That’s where Claude and ChatGPT still feel ahead for serious coding workflows and deeper reasoning tasks. That said, Google has something almost nobody else has: world-class talent, infrastructure, distribution, and control across the entire AI stack. If they can align product quality with that advantage, they could become extremely hard to beat. Competition here is good for everyone building with AI.