HN user

shadeslayer_

252 karma
Posts12
Comments52
View on HN
CursorBench 3.1 21 days ago

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.

I really hope that a four-day working week becomes the norm. Speaking for the tech industry, I think has been proved time and again that the output of a person is in no way directly proportional to the number of hours (or days) worked - and having that extra day to recharge our batteries will help a LOT of us focus better on the remaining days. I know for a fact that it would help me.

I don't understand. If they are capable of changing over time, surely they are capable of looking back on their past selves and acknowledging what was wrong with them?

I'm a bit sceptical about this because it talks very little about what happened that caused OP to get "cancelled", and an awful lot about how they came back from it. I do understand, first-hand, the trauma that comes from being cancelled (although I have like 1500 followers on Twitter so you could argue the stakes are less) and there's no doubt that it is a bitch. But there is something to take away from it - or at least there was in my case - which was that I, in fact, was an asshole. That does not seem to be the overarching narrative of this post, and I do not see a lot of learning they have done from being cancelled.

In conclusion, kudos to the way you bounced back but I really wish there was a bit more introspection into how you see your past behaviour in the light of being cancelled.