shadeslayer_

This article gives me war flashbacks about a particularly irritating OO design interview from 5 years 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.

My friend from work showed me this a couple of weeks ago, and now we all play it as a daily office ritual. Great game!

The sense of entitlement that people have for something they will never pay for is.. crazy.

The site loads like I'm on a dial-up connection but I'm actually on a 300Mbps fiber line. Pass.

I exclusively use Lambda with Cloudwatch Rules for all the crons I write these days. It just works out of the box.

Funny thing is that the site doesn't even work right now. Kiss of death and all that..

Lags while scrolling on a 2021 MBP as well.

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.

Strange that Microsoft used OP's project in their game, but didn't bother to let him know.