no. gemini's instruction following is currently abysmal. Gemini CLI could be a great scaffold for all we know, but we cant know because the models it uses are so horribly bad at being driven in that way.
no clue why google has dropped the ball this hard on IF.
> Gemini CLI could be a great scaffold
Gemini CLI has been terminated, replaced by Antigravity CLI. Gemini CLI was supposed to have actually stopped working on June 18.
Antigravity works fine for software development tasks though, even pretty complex ones. I used it to optimize an ML training process recently, it did a good job.
Antigravity is supposed to be usable for more general tasks as well, but I haven’t tried it for anything else.
I think 3.5 Flash is supposed to improve the long-range instruction following.
I haven't tried it at that because for the short range tasks I gave it I found it around Sonnet level, but slower (because it takes more tries!) which makes it more expensive.
The old Flash models were great because they were fast.
3.5 Flash shows Google can work around the old "Good, Fast or Cheap: Pick any two" thing by picking none of them.
They have a 3.1-pro-customtools model which they allege its better at using custom tools/MCPs/etc.
It is not better.