Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
By Stephen Greenblatt.
-
When people ask me how to learn software, I often say that: They're probably overrating books and underrating experimentation; They're probably overrating tutorials and underrating non-tutorial projects.
-
I often read about getting LLMs to work for a long time toward a goal.
-
A certain kind of document management is embarrassingly important to me these days. as more and more of my projects are fundamentally the maintenance, interrogation, and development of some corpus.
-
I am late to writing about Jev, largely because I've been too busy using Jev.
-
Here's a rough and speculative outline of a psychological profile in software: Sensitive to bugs, but simply because there exist lots of bugs.
-
Lots of our software needs queue-like behavior.
-
By Cally Oldershaw.
-
Many applications can be built and deployed with either a Vercel-based stack or an AWS-based one.
-
Easily the best 9/11 book I've ever read (though I didn't set out to read a book about 9/11; I was just in the mood for a Joseph O'Neill novel).
-
Here are some of the many software-design questions on my mind: I run a spaced-repetition flashcard site, and flashcarding is obviously a good fit for LLM assistance, but questions of how to implement that LLM assistance are sometimes awkward.
-
Here are two subjects that have been on my mind: New models are vastly better at retrieving and tracking lots of real-world information, as I've discussed here and here.
-
Some misc. notes following up on the bug-blindness discussion Dan Luu prompted earlier this week: I've long advocated developing the skill of describing software that you want, whether it's something totally new or a better(-for-you) version of something…
-
Flash 3.8 is out, as I discovered when it showed up in my Antigravity terminal.
-
It is very good.
-
Here is the incomparable Dan Luu, arguing that (i) there are way more bugs than most people think and (ii) most of us systematically fail to notice them.
-
Deciding that an experiment has failed, and throwing away the work, can feel bad.
-
It would be an indecency, a stupidity, even a betrayal to find fault with such peaceable, honest work.