Command Code
2.6K posts
@CommandCodeAI
Command Code with taste; the first coding agent that observes how you write code and adapts to your preferences over time with meta neuro-symbolic AI `taste-1`.
AI Terminology #19: Quantization ↳ A technique that reduces the precision of a model’s numbers (e.g., from 32-bit to 8-bit) to make it smaller, faster, and more efficient to run. x.com/CommandCodeAI/…
Amjad Masad’s Replit allows users to build apps together like they’re doodling on a white board. It also made the Jordanian immigrant a billionaire along the way. Read more about how this AI company is reimagining vibe coding: forbes.com/sites/richardn… 📸: Cody Pickens for Forbes
AI Terminology #18: Backpropagation ↳ A training algorithm that computes gradients of the loss function and propagates them backward through the network to update model weights. x.com/CommandCodeAI/…
Introducing chartli 📊 CLI that turns plain numbers into terminal charts. ascii, spark, bars, columns, heatmap, unicode, braille, svg. $ 𝚗𝚙𝚡 𝚌𝚑𝚊𝚛𝚝𝚕𝚒 I wanted terminal charts with zero setup. No browser, no Python env, no matplotlib. Pipe numbers in, get a chart out. Again built using Command Code with my CLI taste. $ npx chartli data.txt -t ascii -w 24 -h 8 8 chart types spanning a fun range of Unicode density: - ascii (line charts with ○◇◆● markers) - spark (▁▂▃▄▅▆▇█ sparklines, one row per series) - bars (horizontal, ░▒▓█ shading per series) - columns (vertical grouped bars) - heatmap (2D grid, ░▒▓█ intensity mapping) - unicode (grouped bars with ▁▂▃▄▅▆▇█ sub-cell resolution) - braille (⠁⠂⠃ 2×4 dot matrix, highest density) - svg (vector output, circles or polylines) Input format is dead simple: rows of space-separated numbers. Multiple columns = multiple series. 0.0 0.1 0.1 0.1 0.2 0.4 0.2 0.4 0.3 0.2 0.4 0.2 Composes with pipes: $ cat metrics.txt | chartli -t spark S1 ▁▂▃▄▅▆ S2 ▁▄▂▇▅█ S3 ▁▂▄▃▆▅ S4 ▁▄▂▇▂▇ The braille renderer is my fav. Each braille character encodes a 2×4 dot grid, so a 16-wide chart gives you 32 pixels of horizontal resolution. Free anti-aliasing from Unicode. The bars renderer uses 4 shading levels (░▒▓█) to visually separate series without color. Works on any terminal, any font. Heatmap maps values to a 5-step intensity scale across a row×column grid, so you can spot patterns in tabular data at a glance. SVG mode has 2 render paths: circles (scatter plot) and lines (polylines). Output is valid XML you can pipe straight to a file or into another tool. Zero config by default, every dimension overridable (-w width, -h height, -m SVG mode). No config files. No themes. No dashboards. $ 𝚗𝚙𝚡 𝚌𝚑𝚊𝚛𝚝𝚕𝚒 Or global install it. $ npm i -g chartli # Skill for your agents $ npx skills add ahmadawais/chartli If you work in terminals and want quick data visualization without leaving your workflow, try it. ⌘ let's go!!
Happy to announce, I joined @CommandCodeAI as their Developer Experience Engineer in January '26! Command Code is a terminal-based coding agent that continuously learns your coding taste. So it codes like you, not just what you ask for. That's the hard problem worth solving. I own developer experience end-to-end - Key features, agent infra, and eliminating friction wherever it hides. Before I even interviewed, I spent $110 worth of credits stress testing Command. Catalogued 5–6 pages worth of DX papercuts. Presented it to the team. Eight weeks in. 77 PRs. 309 contributions. Every problem I found in that stress-test? Fixed! Read how it all happened below! PS: We're hiring --> Shoot your shot in the comments.
