Any time I upload an attachment, it just fails with something vague like "couldn't process file". Whether that's a simple .MD or .txt with less than 100 lines or a PDF. I tried making a gem today. It just wouldn't let me save it, with some vague error too.
I also tried having it read and write stuff to "my stuff" and Google drive. But it would consistently write but not be able to read from it again. Or would read one file from Google drive and ignore everything else.
Their models are seriously impressive. But as usual Google sucks at making them work well in real products.
Context window blowouts? All the time, but never document upload failures.
This is the company that made Android, and it can't make an Android app that fetches a response from a server. Astonishing.
Google is great at some things, but this isn't it.
It is also one of the worst models to have a sort of ongoing conversation with.
Not a single person is using it for coding (outside of Google itself).
Maybe some people on a very generous free plan.
Their model is a fine mid 2025 model, backed by enormous compute resources and an army of GDM engineers to help the “researchers” keep the model on task as it traverses the “tree of thoughts”.
But that isn’t “the model” that’s an old model backed by massive money.
Come on.
Worthless.
Do you have any market counter points.
Market counter points that aren't really just a repackaging of:
1. "Google has the world's best distribution" and/or
2. "Google has a firehose of money that allows them to sell their 'AI product' at an enormous discount?
The models feel terrible, somehow, like they're being fed terrible system prompts.
Plus the damn thing kept crashing and asking me to "restart it". What?!
At least Kiro does what it says on the tin.
It is windsurf isn't it, why would you expect it to be different?
I've recently tried a buuuuunch of stuff (including Antigravity and Kiro) and I really, really, could not stomach Antigravity.
When the (generous!) Claude credits dry up functionality stops however. Gemini is as useless in Antigravity as everywhere else.
Also because of the long context window (1 mil tokens on thinking and pro! Claude and OpenAI only have 128k) deep research is the best
That being said, for coding I definitely still use Codex with GPT 5.3 XHigh lol
It took me however a week to ditch Gemini 3 as a user. The hallucinations were off the charts compared to GPT-5. I've never even bothered with their CLI offering.