@dhh: Fable one-shotted a Rust rewrite of the TerminalTextEffects Python library in 11M tokens. Startup time went from 87ms t…
Summary
Fable used Claude AI to one-shot a Rust rewrite of the TerminalTextEffects Python library, reducing startup time from 87ms to 2ms and increasing rendering speed by 9.6x, with zero dependencies and a single 3MB executable.
View Cached Full Text
Cached at: 08/17/26, 10:43 AM
Fable one-shotted a Rust rewrite of the TerminalTextEffects Python library in 11M tokens. Startup time went from 87ms to 2ms and rendering speed is up by 9.6x. Now zero dependencies and a 3mb single exec 🤯 https://t.co/3cTEQAqYdO
Claude Artifact
Source: https://claude.ai/code/artifact/287825bc-7aad-4541-a7e7-fa4ba8d03612 https://claude.ai/code/artifactsContent is user-generated and unverified.
Similar Articles
60% Fable cost cut by converting code to images and having the model OCR it
pxpipe is a local proxy that reduces Claude Code token usage by converting dense text (system prompts, tool docs, history) into compact PNG images, achieving ~60% cost savings by exploiting the fixed token cost of images regardless of text density.
@_avichawla: I cut Fable 5 token usage 2.5x with just one change! - Before: 5.5 M tokens · 7 errors · $8.94 - After: 2.3 M tokens · …
The author reduced token usage for an AI agent by 2.5x by switching from Firebase to InsForge, an open-source backend platform for agentic coding, cutting tokens from 5.5M to 2.3M and eliminating manual interventions.
@ArizePhoenix: - 55.8% on Terminal-Bench 4.0 (up from 42.0% for Fable 5) - 52.6% on Terminal-Bench-Science (up from 24.7%) - 65.0% on …
ArizePhoenix shows significant performance improvements on benchmarks like Terminal-Bench 4.0 and Humanity's Last Exam, with gains from previous versions such as Fable 5.
@liambraus: CLAUDE CODE TAKES 3.4 SECONDS TO START UP. THIS ONE DOES IT IN 14 MILLISECONDS. A single developer just built their own…
A single developer built a code agent harness in Rust that starts up 245 times faster than Claude Code (14 ms vs 3.4 s) and uses up to 20x less RAM, achieving 10.4k stars on GitHub.
@tom_doerr: Reduces Claude Code and Cursor token costs by 60-95% https://github.com/yvgude/lean-ctx
lean-ctx is an open-source Rust-based context runtime that reduces token costs for AI coding agents like Claude Code, Cursor, Copilot, and others by 60–95% through file read compression and shell output optimization. It operates as a Shell Hook and MCP Server with 56 tools and multiple read modes.