Let me tell you about my favorite Borges story, Katabasis.
Like so much of his work, it's framed as a Silk Road campfire tale, or maybe a fragment of a manuscript from antiquity (I forget which), but of course it's really an exploration of mathematical concepts and the nature of infinity.
I built detect because I was tired of looking up find/grep/xargs syntax on Stack Overflow every time I needed to search my filesystem in any nontrivial way. It's a Rust tool that uses a concise and readable expression language to build queries.
Here are some examples:
# every rust file modified in the last week that imports tokio _and_ serde (mean time: 179ms)
detect 'ext == rs
&& content contains "use tokio"
You built a developer tool that does something really cool. You use it every day. The learning curve is steep, but in the course of developing this tool, you have become intimately familiar with the interface, so it's intuitive to you. This is a post about turning that tool into something that can find broad utility among developers, not just N=1 utility for you.
Many of the things that make tools good and useful for humans also make tools that are good and useful for LLMs. It's that Venn diagram intersection that I want to focus on, because that's where LLMs can help you improve your command line tool's UX.
Every tool has a complexity budget. Users will only devote so much time to understanding what a tool does and how before they give up. You want to use that budget on your innovative new features, not on arbitrary or idiosyncratic syntax choices.
VALIDATION_SCOPE = "Tested with: GPT-4.5, Claude 4 Opus, Gemini 2.5 Pro, DeepSeek V2"
VIBES provides a structured framework for evaluating and improving the ergonomics of tools and expression languages designed for LLM use. As LLM-driven development becomes mainstream, the economic impact of poor tool ergonomics compounds exponentially through failed attempts and workarounds.
Core Insight: LLMs and humans need fundamentally different tools. Just as we don't expect humans to write assembly code or CPUs to parse English, we shouldn't force LLMs to use human-optimized interfaces. The most effective approach is building purpose-specific tools for each type of user.
| pub fn generate_layer(x: Box<ExprAST>) -> Expr<Box<ExprAST>> { | |
| match *x { | |
| ExprAST::Add(a, b) => Expr::Add(a, b), | |
| ExprAST::Sub(a, b) => Expr::Sub(a, b), | |
| ExprAST::Mul(a, b) => Expr::Mul(a, b), | |
| ExprAST::LiteralInt(x) => Expr::LiteralInt(x), | |
| } | |
| } | |
| pub fn eval_layer(node: Expr<i64>) -> i64 { |
| #!/usr/bin/env run-cargo-script | |
| //! requires `cargo install cargo-script` | |
| //! | |
| //! ```cargo | |
| //! [dependencies] | |
| //! guppy = "0.6.2" | |
| //! structopt = "0.3.21" | |
| //! serde_json = "1.0" | |
| //! serde = "1.0" | |
| //! toml = "0.5" |
inanna@inanna-x1-carbon:~/dev/phf_bug_demonstrator$ rustup default 1.40.0
info: using existing install for '1.40.0-x86_64-unknown-linux-gnu'
info: default toolchain set to '1.40.0-x86_64-unknown-linux-gnu'
1.40.0-x86_64-unknown-linux-gnu unchanged - rustc 1.40.0 (73528e339 2019-12-16)
inanna@inanna-x1-carbon:~/dev/phf_bug_demonstrator$ cargo build
Compiling phf_bug_demonstrator v0.1.0 (/home/inanna/dev/phf_bug_demonstrator)
Finished dev [unoptimized + debuginfo] target(s) in 0.14s
| //stack-safe anamorphism (unfolding change). Builds a tree layer by layer. | |
| pub fn ana<X>(f: impl Fn(X) -> Tree<X>, seed: X) -> FixTree { | |
| let mut instructions: Vec<Option<X>> = vec![]; // depth first, Some == add child w/ seed, None == back a level | |
| let mut path_to_root: Vec<&mut Vec<Box<FixTree>>> = vec![]; // pointer to children of focused node | |
| // ^ this breaks it, requires multiple borrows... drop this in a gist (or use refcel, rain says to do so) | |
| let root = f(seed); | |
| match root { | |
| Tree::Leaf(n) => FixTree(Tree::Leaf(n)), |
I’ve been setting up structured journal entries recently - quick morning notes, weekly and quarterly retrospectives, etc. As part of this I’ve been curating a list of questions to help self-assess how I’m doing at any given time.
Some of these questions are simple bio-maintenance checklist entries: how’s my diet? Am I getting enough sleep? Are my cholesterol and triglyceride levels normal? Have I been getting enough vitamin D? Have I been doing resistance exercise recently? Cardio?
Then come some less concrete questions: have I been keeping myself intellectually engaged? Have I been engaging in some regular form of artistic creation? When’s the last time I did something nontrivial just for the fun of it? Aside from work stuff, when’s the last time I finished a project? Speaking of work, how are things there? Attempts to answer that question could fill multiple blog posts, so for now I’m going to focus on a specific angle pointed out by
| URxvt.scrollBar: false | |
| urxvt*termName: rxvt | |
| urxvt*font: xft:uushi:pixelsize=16 | |
| urxvt*boldFont: | |
| urxvt*background: #000000 | |
| urxvt*foreground: #666699 | |
| urxvt*cursorColor: #6699CC | |
| urxvt*colorBD: #CCCCFF | |
| !Visiblue |