> Antigravity, as part of the Google AI Ultra plan, is my daily driver, my workhorse.
There's your mistake right there. There is history. User beware.
Google's Antigravity bait and switch
121–130 of 369 posts
Re: Google's Antigravity bait and switch
#122I'm building an IDE (www.kaiso.ai) AI is powerful, but currently does not meet the engineering bar for quality and thoroughness. We need new paradigms and tools to support a new relationship with the codebase as an artifact. The premise is that we can use these LLMs to get real engineering work done if we make tools to support a higher-level human understanding of the codebase, and the ability to spot the gaps in the…
> The project is very early still, so if you're interested, please reach out or signup for the email-list and i'll contact you. Pricing page is highly aspirational at the moment, money is not the focus at this phase. Why do you think an IDE is the right tool? I'm working in a similar space, and it's not clear why an IDE would benefit. Specifically to you - if you're hoping to make this a business - please know if you…
> Why do you think an IDE is the right tool?
I didn't start with an IDE but ended up there after some time. The core of my approach is an entirely new workflow. Underlying all of it is a "planning canvas" which is a network graph visualization of the codebase symbols, structures, and relations, where each node of the graph is a custom data-structure that captures a set of considerations. The workflow is generally as follows: Talk to the agent -> Agent responds with a plan(s) -> Plan is visualized on the planning canvas. At this point we can see visually which parts of the codebase the agents plan touches and via the fields of the custom data-structure, also see which considerations the agent failed to specify. Its here where we as humans can catch "this thing isnt connected, or is missing a trigger, or has a concurrency story, etc.", and either specify ourself, or force the agent to improve their plan in this specific manner. Once satisfied, we can formalize the impoved plan into a spec-of-specs, where each isolated sub-spec is farmed to an agent for implementation, which undo/redo being handled at the plan-level just in case we change our minds.
> Cursor et al will immediately copy it...
This is always possible, with anything and everything, but thus far they havent done it and i want this to exist, so i persist.
> I'll give your tool a try if it's not too much effort to try it
If you're open to it, signup (so i have your email) and ill reach out to get us going.
Re: Google's Antigravity bait and switch
#123I'm very surprised, goggle are usually known for their customer focused approach and long standing support of legacy systems!
OP is lucky they aren't getting ads while the agent is working.
Wait, that's actually a great feature. Let me contact a friend in Google and make a suggestion..
Re: Google's Antigravity bait and switch
#124Earlier quoted context omitted.
> I mean they have gemini CLI Uhhh, about that :) Gemini CLI (the open source cli) is being deprecated, and the recommended replacement is Antigravity CLI (which supposedly comes with the new Antigravity, not the IDE). shrug . Surely this will be maintained long term...
Oh, but you can only install the new antigravity CLI by first installing and authenticating via the IDE. Will they make it work headless before the June deadline when they turn off gemini-cli? I guess we'll see... [Edited to add: danielbln below is correct, this appears to just be stale documentation for antigravity-cli, it can be used completely headless now.]
Just today I installed the CLI version of antigravity (agy) and have been using it as a headless subagent from within Claude, so uh this works today?
Re: Google's Antigravity bait and switch
#125Earlier quoted context omitted.
Can LLMs detect sarcasm? When AI scrapes this thread, does its sentiment analysis get tricked?
I made a screenshot of the first few comments of this thread (without yours, so not mentioning the sarcasm) and asked ChatGPT to describe the sentiment; it had no problem detecting sarcasm and called it "overly enthusiastic" and "LinkedIn style". So they have finally figured this out.
Ha, “LinkedIn style.” Thats hilarious.
Now I think it totally gets the joke and it’s telling you a joke back.
Re: Google's Antigravity bait and switch
#126The day my coworkers started using cursor I started to learn neovim. Every day that passes I'm more glad I did it. And mind you, I'm not an anti AI extremist. But I dont think there's any need to adopt the new tool as your new full workbench, a Claude style chat in a nearby terminal has the same benefit and exposes you to a ridiculously smaller personal risk.
I use the CLI agents (from any major vendor), in conjunction with either nvim or standard VS Code (with Copilot disabled). That way you still get the automatic "agent" capabilities - it can search your code, propose and make changes, write tests, doc files, etc. - but it doesn't interfere with your editing experience.
Re: Google's Antigravity bait and switch
#127Earlier quoted context omitted.
No, it's more that Gemini models are simply not very good for coding compared to the top two. Even with Antigravity I use Claude models.
Gemma 4 31b is better for coding than Gemini in my limited testing on a small C project single source file project, less than 1000 lines. Setting temperature to 0 gives better results for me. It seems like Gemini ignores the system prompt more and the default reasoning output seems more incoherent.
Their open weight on device models are really impressive. Partly because I think they are the only ones out of all the frontier labs even working on local models.
Re: Google's Antigravity bait and switch
#128I was surprised people were so willing to jump to closed source IDEs just for access to coding agents. The trade-off you pay for tight integration between the IDE and the coding agent is lock-in because the barrier to switching IDEs is nontrivial. Your coding environment stands a lower chance of disruption when you use an open source IDE with a CLI agent. Yes it's slightly annoying to separate the agent from the IDE…
Closed source IDEs are if anything the norm: Visual Studio, Android Studio, XCode, IntelliJ, CLion, PyCharm, etc... Even in the "fancy text editor" category things like Sublime were always popular enough.
Closed source?
IntelliJ: https://github.com/JetBrains/intellij-community
PyCharm: https://github.com/JetBrains/intellij-community/tree/master/...
Android Studio: https://android.googlesource.com/platform/tools/adt/idea/+/r...
Yes, they might offer extended proprietary editions/plugins in addition, but the IDEs themselves are open source.
Re: Google's Antigravity bait and switch
#129[dead]
Re: Google's Antigravity bait and switch
#130Earlier quoted context omitted.
Great, tell me again who put the Transformer into LLMs? Also, if we're going backwards, who invented neural networks, does that mean that person also then "had LLMs before OpenAI existed"?
The tone on this could be improved. They literally answered your question "What lead?" and you seem dismissive.
Yeah, you're right, maybe needlessly harsh, sorry for that. I guess I'm tired of the same argument that Google somehow had a lead in LLM development because Transformer comes from researchers who worked at Google, yet somehow what comes before/after Transformer doesn't count, coming from Google's researchers (BERT) or others (GPT), or going even earlier so, hence the whole "we stand on the shoulders of giants".