Funnily, AI already knows what stereotypical AI sounds like, so when I tell Claude to write a README but "make it not sounds like AI, no buzzwords, to the point, no repetition, but also don't overdo it, keep it natural" it does a very decent job.
Actually drastically improves any kind of writing by AI, even if just for my own consumption.
I'm not saying it is or isn't written by an LLM, but, Yegge writes a lot and usually well. It somehow seems unlikely he'd outsource the front page to AI, even if he's a regular user of AI for coding and code docs.
My biggest revelation was when I realized how to use Emacs to learn about Emacs. Knowing where to look up function, variable definitions etc was an eye opener in my understanding of how things work and are piped together
There was a time when this was the obvious thing to do when making systems. Sadly that's forgotten. Manpages to read on cli tooling is the same thing of course. Yet people rather go to another window, the browser, and go to a ad-driven website and get the same output as the manpage would give.
These days people rather switch to a browser window, open an LLM of their choice in a new tab and in verbose English ask "how do I do X in this popular program Y?".
Then get a hallucinated answer and come to you to complain about a missing cli option, while it's literally there, in their terminal, just one -h away. True story (had to vent out, thanks for listening).
The only 2¢ I can add here is that LLMs are surprisingly good for solving tasks that involve Elisp. There's large corpus of Emacs Lisp in the wild - the amount of it on GitHub alone is shocking.
For comparison - whenever I try using a model to write some Neovim config stuff, LLMs hallucinate badly.
Using Emacs these days is so much fun - you just ask a model and you can immediately try things - not only without restarting - you don't even have to save anything, anywhere.
You can even make Emacs do things that involve tools and languages that have nothing to do with elisp, e.g., "write elisp that would open all nested dirs in a given folder, and then run magit-log for each project, searching for specific pattern... and if found, issue npm or uv pip install with arguments...", etc.
I'm a Spacemacs user, and Claude knows the difference between Spacemacs and stock emacs. It basically wrote tools for itself to hook into the emacs LSP package and look up C++ code (in our codebase, which is, uh, challenging for FOSS language servers) from gptel. I was completely fucking unable to do this via publicly-available MCP servers in the VSCode agent mode. In general I have been able to resolve a bunch of niggling config issues that I had just been ignoring in favor of doing Actual Work.
As you said, I can evaluate the elisp Claude wrote right there in the gptel buffer, try it out, and iterate before actually pasting it into .spacemacs. It it doesn't work, Claude knows a ton of debugging tricks I can try. trace-function, advice to dump a backtrace, etc. It knows how to do everything in org-mode. Super helpful. Way better than the AI Assistant that my employer bundles with our product (which is outperformed by the Google AI Overview).
Why do you think our should not? Sincerely asking.
And while I’m here, if you’re implying that Signal is Blut trustworthy, you should step out of the HN bubble and have a look around what everyone and their dog shares through less secure means
I did not mean to say that there are better options for encrypted communication. My point was that my use case is texts like "I'll be in the gym at 6:00 bro", not things that I really want to keep or backup. If someone sends a picture or a file that I want to keep, I can already do so manually.
I don’t think there’s a correct answer here. Whatever floats your boat. Do you want to scribble things by hand into a physical notebook? Great! Want to use Notepad on Windows for .txt? Or create a .docx using Word?
Don’t follow trends and seek the “next best way to hack your productivity”. Most of those things are snake oil and a waste of time. Just use whatever you have available and build a process yourself. That’s what most people have done that are successful in applying this. They just use the tool they are comfortable with, and don’t over engineer for the sake of it
Their point was that (i) React becoming the defacto standard played into the hands of Meta, who are interested in tracking people. (ii) Tracking is made easier by running arbitrary JavaScript in the browser. And (iii) before SPAs were big (pre-React), more people used to completely disable JS in their browser.
Not saying I buy this theory. Just trying to explain what I think they were alluding to, as I had the impression you missed it and went in a different direction.
Just that it’s all done from the comfort of the editor one knows and loves, with the same key binding and semantics that at there, whether you edit files in fired, write code, a commit message or an email.
Not to get too deep into this, but there’s this warm fuzzy feeling of not having to use /yet another different app/ that’s ever so slightly different to the optimal workflow you have otherwise
Many routes have "hail and ride sections" without designated stops. You can't get off, but can hail and get on at any point. Here's a list for London [1].
I assume it’s region specific. There used to be alternatives in my area, but they’ve all died, and even with all the fake Google reviews, it’s the only way to get an idea about restaurants.
