Comment by e12e

1 day ago

I'm quite happy using antigravity fwiw. I use Claude code for work. Only tried agy because I was already paying for Google one (youtube music, youtube without ads/premium and a few TB of storage).

Antigravity come with Google's models and anthropic - so Gemini 4 Argon, Gemini 3.8 Flash, Claude Opus 5.5 Claude Sonnet 5.5 and GPT-OSS 120B.

Agy is better than Claude code in some ways and vice versa.

Google models are great.

Ironically google music is so terrible I've uninstalled it and use Metrolist exclusively.

I think google models do a decent job helping me put together a blog, for example:

https://hypertekst.net

(Content is typical 90s homepage stuff, not great. But model voice isn't as grating as Claude - and while it has a "look" I think it's s bit better).

10 comments

e12e

Reply
maxglute  21 hours ago

Last December, before token maxxing I grabbed AI Pro 5TB promo ~$100 a year, coding was touch and go until 3.8, but now I don't see need for other subs. Sometime summer, they threw in youtube premium lite, maybe for retention at some point. The 5TB cloud storage useful for family sharing. It's almost no brainer except I miss proper youtube premium that locks 3-4x play back speed and queueing. I think its going to be $200/yr after promo ends, I'll probably hold onto it, but wish they can throw in proper yt premium, as in just yt, they can bundle out music (and music video ads). Periodically generating a joke video and images also useful. It's just a solid bundle. I dont even know what home/health premium about. This from someone who got screwed by Google services, but its pretty decent value.

  • akoboldfrying  20 hours ago

    > 3-4x play back speed

    This boggles my ears. I've only ever found one guy I can listen to at 2x because he talks... so... slowly.

    • maxglute  16 hours ago

      It just takes some practice. Visually impaired who use screen readers listen at 3-4x speed, 5x if very proficient. Premium has smart playbackspeed, so you can set to 2x and it will speed through silent parts up to 4x, it's useful for other reasons.

jorl17  1 day ago

In the past, whenever benchmarks used to show google as being on par with the rest, I tried them and found them extremely lacking.

It's been maybe 6 months since I last tried them in any proper fashion (other than my usual benchmark which is non-coding related), but I was so let down previously, and found it so exhausting to just figure out how to get a subscription working with them, that I really feel like I've given up.

I'm sure I'll get around to trying them. Heck, it could happen today if the mood hits, but....it does need a specific mood. The mood to get over bullshit UX and a profound disdain for the company.

  • e12e  1 day ago

    Fwiw the homepage serves as a current demo - for better or worse. Practically vibe coded (I haven't really looked at the code), but not one-shotted.

    YMMV

vohk  1 day ago

I've not been impressed with their models. Argon seems good but the usage limits on Pro feel worse than Sol/Astra/Opus on competing plans. But where Luna and Haiku have gotten to point of being 'good enough' for grunt work, I don't feel like 3.8 Flash is there.

That view somewhat biased by Flash getting stuck looping in Antigravity's CLI when I asked if it could add plan usage % to the status line. Instead of "no", it first pretended agy was Claude Code and gave me a wrong answer, then resorted to trying to analyse the binary.

Their harness situation is just awful.