Language models happen to share human flaws, but like humans they can amplify their abilities and reliability by building and using reliable tools.

I didn't like not seeing the reasoning of the models

The suburban family would be repelled by the look.

With Gemini 2.5 the bill is zero for now.

eh interesting..

Their willingness to integrate depends on their perception of the model quality.

You can use VS Code and cursor at the same time. One to code and the other to compile the code. That's how I build for Android. I generate code in Cursor/Windsurf then I compile and deploy using Android Studio.

Ask it to write assembly language

It seems to perform worse in Cursor, so maybe that's where the problem is.

Yeah, I am just considering cancelling my subscription and go back to ChatGPT.

Almost is a painful word in this case. Imagine if it could actually run R1. They'd make so much money. Falling short by a few dozen GB is such a shame.