I got interested in AI safety and quickly ran into a problem.
To understand things like interpretability, evals, or monitoring, you need a solid grip on:
linear algebra calculus pandas / matplotlib

half the time i just didn’t want to open my laptop + set up notebooks so I built an app called tangent mostly because i was frustrated learning AI safety, the reason is everything is taught like:

here’s syntax or here’s theory with no connection to actual safety work

in the app you can learn: pandas matplotlib linear algebra calculus

But every concept is tied to real safety stuff:
gradient explosions as red flags
embedding norms for OOD
detection eval log filtering + audit joins distribution shift tracking

some features : short lessons (2–8 min), 180 exercises, spaced repetition, works offline

android only rn: https://github.com/SomaxSoma/tangent-/releases/latest if you guys try it, please tell me what’s missing / wrong ,especially if you’re doing eval or monitoring.