535 karma · joined January 14, 2015
once you got the hang of it you could really move quickly with desktop gui development
Now do the same for tailwind
That which has been nerfed can be un-nerfed by tracing the gradient back the other way?
> But when a large language model scores well on such tests, it is not clear at all what has been measured. Is it evidence of actual understanding? A mindless statistical trick? Rote repetition?
It is measuring how well it does _at REPLACING HUMANS_. It is hard to believe how the author clearly does not understand this. I don't care how it obtains its results.
GPT-4 is like a hyperspeed entry to mid level dev that has almost no ability to contextualize. Tools built on top of 32k will allow repo ingestion.
This is the worst it will ever be.
This language clearly indicates possibilities for local models in the future or at the very least other options for hosted models.