| ▲ | blfr 3 hours ago | |||||||
This would have been a massive issue if Antigravity/Gemini were any good. I don't appreciate but kinda understand that Anthropic can act arrogant with Fable. Google (shockingly) is really in no position for this. | ||||||||
| ▲ | moshegramovsky 2 hours ago | parent | next [-] | |||||||
100% this. I was a huge Gemini fan, and I think the model itself is still very good. But Antigravity is absolutely horrible. It routinely writes broken code and then ends up in a short term cycle of reverting and re-implementing. It's so bad that I don't use it for writing code and certainly wouldn't even bother trying to get it to refactor anything. It's been relegated it to analysis and planning. It is excellent there. I can't be the only one who find this a little inexplicable that a company with Google's resources is fumbling this so badly. | ||||||||
| ||||||||
| ▲ | serf 2 hours ago | parent | prev [-] | |||||||
Gemini is great (and fast) at vision tasks. It's a huge benefit to add on to an existing pi/omp harness install just for that feature to use in conjunction with other (stronger) models. Too bad this anti 3rd party usage stance basically makes that a huge risk for a lot of people, it was the only thing Gemini has been competitive in outside of API cost. | ||||||||