Is something new here? Wasn't this launched months ago? https://antigravity.google/blog/introducing-google-antigravi...
2.5 was recently released https://antigravity.google/changelog
Antigravity 2.0
11–20 of 34 posts
Re: Antigravity 2.0
#12Antigravity 2.0 was released in May
https://antigravity.google/blog/introducing-google-antigravi...
Discussion: https://news.ycombinator.com/item?id=48196838
Re: Antigravity 2.0
#13Definitely not touching this until it's open source
Re: Antigravity 2.0
#14It's wild how much these agent interfaces have aligned UI-wise. There's almost zero difference between all of them.
It's kind of bizarre in that it's not like this is an optimal interface, either. I mean, it's fine, but why not try something different? I also don't really get why TUI's have become such a big deal, other than maybe nerd bait. The only time I want a TUI is when I'm SSH'd into a machine, which isn't very often? TUI's have so many downsides. Selecting text is inconsistent, copy paste is inconsistent, mouse behaviors..…
The SSH into machine market is huge. Cloud work, Dedicated servers, VPS, Colab.
Re: Antigravity 2.0
#15Old news.
Re: Antigravity 2.0
#16I don't see a 2.0 of the CLI, thus far. When they killed Gemini CLI (a better product), they said it was to share effort across the GUI and TUI, but I guess that doesn't mean what a normal person would assume it means. The current CLI version 1.1.10 is still completely broken for any security work (even though Gemini CLI had a security plugin and the Gemini models are competent at the task and don't refuse it when ca…
Gemini CLI was utter shit and always had delayed model release on top of it. I'm not kidding when 1 hour automated vibe-coding led to an agent 30% cheaper and faster on 1:1 tasks with the SAME Gemini models (re-ran on 50 past tasks), genuinely shameful that Google even released this, it was so buggy, trapped in infinite loops as well and so-on.
Antigravity is a whole different product, the only way I use it currently is to abstract the OAuth mechanism so we can leverage Google subscriptions within our own agents.
Re: Antigravity 2.0
#17Earlier quoted context omitted.
It's kind of bizarre in that it's not like this is an optimal interface, either. I mean, it's fine, but why not try something different? I also don't really get why TUI's have become such a big deal, other than maybe nerd bait. The only time I want a TUI is when I'm SSH'd into a machine, which isn't very often? TUI's have so many downsides. Selecting text is inconsistent, copy paste is inconsistent, mouse behaviors..…
The SSH into machine market is huge. Cloud work, Dedicated servers, VPS, Colab.
Even bigger could be sandboxes. It's certainly possible to sandbox your agents and still use a GUI, but SSH is the easiest way.
And not sandboxing your agents seems insane.
Re: Antigravity 2.0
#18It's wild how much these agent interfaces have aligned UI-wise. There's almost zero difference between all of them.
Nobody gets fired largely copying eachother. Releasing something new and risky often isn't worth it, sadly.
Re: Antigravity 2.0
#19It's wild how much these agent interfaces have aligned UI-wise. There's almost zero difference between all of them.
It's kind of bizarre in that it's not like this is an optimal interface, either. I mean, it's fine, but why not try something different? I also don't really get why TUI's have become such a big deal, other than maybe nerd bait. The only time I want a TUI is when I'm SSH'd into a machine, which isn't very often? TUI's have so many downsides. Selecting text is inconsistent, copy paste is inconsistent, mouse behaviors..…
maybe im in the minority but i take one look at these things and see its a desktop gui and lose interest, because i use TUI heavily on my work machine, and one advantage is that i can work remotely from any location to monitor long running jobs or get work done when im not at a computer.
Re: Antigravity 2.0
#20I’m curious how well the dynamic subagents work in practice compared with agents in other harnesses. Coordination overhead and duplicated work are usually where these systems start to fall apart for me.
Curious if you've seen firstmate, built by a former bigtech principal engineer. It's like a sane version of gastown, essentially a meta-harness of sorts.
https://github.com/kunchenguid/firstmate
Not affiliated, just started using a few weeks back and am pleasantly surprised how well it works even with rather dumb agents.