It costs money, but I've been enjoying my Pangram subscription for this. Saves me slop on the internet and confirms whether or not my colleagues' words are what i'm reading or not.
Some tools should be avoided outright, because they're bad tools. You can hammer nails in with a rock, making it a tool, but I wouldn't question the biases of a craftsman who avoided using rocks in their work. I use LLMs for work, but your statement here doesn't hold water at all.
Not just reserves, but also all the oil already on ships slowly making its way to its destination. I think I even saw someone predict that around September, the oil issue would get worse due to how slowly those ships move.
I agree that the rust community tends to be pretty toxic, but I don't think that is a good reason to avoid tools just because they use rust under the hood. You don't have to participate in the git dev community, let alone the rust community, to use git as your VCS.
I think one thing about git needing rust (or python or Perl) is that each language dependency adds another good sized chunk of storage for the language and its tools/packager, I have a relatively light project using Tauri Svelte and code mirror, my build directory/cache becomes 18gb in the blink of an eye, that's a whole bloated modern operating system as a side effect of building a text editor, I should just wrap webkit-GTK around a redbean with some js libs in a directory, script the middleware in Lua and call it a day :D And don't get me wrong I like the development workflow with Tauri, it feels very performant, and easy to reason with, just the sheer disk space makes me boggle!
I strongly disagree. I'm working on a semantic model for Lojban, heavily AI assisted, using multiple models. I have basically all popular frontier models doing research and panel debates. Astra and Fable are both noticeably ahead of everything else including their previous iterations. When it comes to reviews, they can also find more issues in others (or even their own) code.
I'm sure that's part of it, but I run it side by side in my review bot, and Astra medium effort consistently catches more issues than Sol 5.6, using fewer tokens.
For coding it's a little harder to tell, but at least the prose feels a little better.
reply