Do these benchmarks even add any value at this point? This one is basically Cursor saying that their model is as good as the frontier ones at a fraction of the price. The independent benchmarks are probably part of training data now and the models are pattern-matching against them all the time. The final test of a model (and the harness, probably) is how good it works FOR YOU - since most of the models can pretty much do most of our tasks on a daily basis - it boils down to which one has the least friction to its usage.
I have been using Warp for the past couple of days and the autosuggestions when I'm working over SSH are pretty nifty, it probably saves me a fair amount of time everyday.
Making a login required is absolutely unnecessary, though.
I can relate so hard with the part which says it does not favour slow thinkers. I've faced this countless times - person at work asks me something, I reply "I'll think about it and get back to you", which inevitably leads to their disappointment.
I am okay with disappointing people, but it can be unnerving when that disappointment means I miss out on a good opportunity.
"..today it would not be at all surprising to find that an engineering team has built a backend using REST even though the backend only talks to clients that the engineering team has full control over."
This bit is particularly important to me personally because I have been that guy in the past. As a new grad fresh out of college, someone taught me REST and I was.. impressed. I thought it was the only way to design web backends. It was my hammer and everything else I saw was a nail.
A few years on, I can look back and understand how stupid I was.