Skip to content

Repository files navigation

TAIS Explainers

Animated, interactive explainers for Technical AI Safety research, made mostly by Claude. It's partly an experiment in how well an agentic system handles a teaching task, and partly because I (Agustin) wanted good visualizations of these topics to exist. Browse them at https://agustinbrusco.github.io/tais-explainers/.

Heads-up: unless a piece is marked as checked by me, I haven't verified its facts myself. The reviews described below are done by other Claude models, not by people. If you find a mistake, please open an issue.

The aim is a visceral understanding: you drag a lens across the layers of a model and watch what it decodes, and you watch a chain-of-thought monitor lose its grip as reasoning moves into latent space. That understanding also has to be correct, so every claim traces back to a specific place in a source.

Explainers

See projects/README.md.

How a piece gets made

  1. Brief: what you'll be able to see, predict or explain afterwards, and which misconceptions it defuses.
  2. Research: the primary sources, actually read, in references/.
  3. Claims ledger: every statement in the piece → a source, a location, and a status (sourced, simplified, speculative).
  4. Script → the hardest visual first → build, as a web explorable (D3 / Three.js, no build step), a Manim video with local TTS narration, or both.
  5. Review: rendered frames checked against a visual checklist, an adversarial fact-check, and a simulated learner read-through, all before a human sees it.

Every figure carries a badge: schematic, real (with the model and layer), or speculative.

Layout

path what
projects/ one folder per explainer: brief, claims ledger, script, narration, web/, manim/
references/ per-topic dossiers and source lists (PDFs are fetched locally, not committed)
kit/ the shared visual language: semantic color tokens, Manim helpers, web CSS/JS, starters
scripts/ TTS, paper fetching, contact sheets, headless screenshots, scaffolding
learner/ the learner profile, concept map and journal the explainers are tailored to
.claude/ Claude Code skills (explainer, research, review) and review agents

Setup

Linux or macOS, with uv, Node ≥ 20, and TeX Live (for Manim math).

# Manim needs Cairo/Pango headers (Debian/Ubuntu):
sudo apt install libcairo2-dev libpango1.0-dev pkg-config

./scripts/setup.sh            # Python env, Kokoro TTS model (~340 MB), headless Chromium
./scripts/setup.sh --interp   # optional: CPU torch + TransformerLens, for visuals built from real activations
./scripts/doctor.sh           # checks every tool and prints a fix for anything missing

No system ffmpeg is needed (a static build ships with imageio-ffmpeg), and no GPU is needed.

Licensing

TBD.

About

Visual explainers on technical AI safety, made mostly by Claude as an experiment. Not personally fact-checked unless marked.

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages