Numpath

👋 Sign in for the ability to sort posts by relevant, latest, or top.

Oscar Rieken

Jun 1

Making LLM outputs auditable: the provider abstraction pattern

#numpath #python #llm #claude

5 min read

Oscar Rieken

Jun 1

60 hand-crafted math problems: what I learned writing seed data for an adaptive tutor

#numpath #dyscalculia #python #education

5 min read

Oscar Rieken

Jun 1

From Bayesian to deep knowledge tracing — upgrading NumPath's student model with a PyTorch LSTM

#numpath #adaptivelearning #pytorch #python

5 min read

Oscar Rieken

Jun 1

Building a mistake taxonomy for dyscalculia — 8 error patterns, rule-based, no ML required

#numpath #dyscalculia #adaptivelearning #python

5 min read

Oscar Rieken

Jun 1

Clean Architecture in a FastAPI + Vue 3 monorepo

#numpath #cleanarchitecture #python #fastapi

5 min read

Oscar Rieken

Jun 1

Building a FastAPI + Vue 3 research platform: the 4 bugs that almost broke Phase 1

#numpath #fastapi #docker #python

5 min read

Oscar Rieken

May 27

Bayesian Knowledge Tracing in 37 lines of Python — how NumPath models what a student knows

#numpath #adaptivelearning #bayesian #python

4 min read

Oscar Rieken

May 21

Attempt history in the teacher dashboard — the scalar subquery pattern

#numpath #adaptivelearning #python #vue

4 min read

Oscar Rieken

May 21

Prompt engineering for teacher insights with Claude — structured JSON and graceful fallbacks

#numpath #adaptivelearning #python #llm

4 min read

Oscar Rieken

May 21

Closing the feedback loop: how mistake classification drives adaptive problem selection in NumPath

#numpath #adaptivelearning #python #bayesian

3 min read

Oscar Rieken

May 21

Why I'm building an AI math tutor for dyscalculia — and grounding it in 30 years of ITS research

#numpath #adaptivelearning #dyscalculia #python

5 min read

Oscar Rieken

May 21

Why teachers need explainable AI, not just accurate AI — building the KC dashboard

#numpath #adaptivelearning #vue #python

3 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.

DEV Community

# numpath

Making LLM outputs auditable: the provider abstraction pattern

60 hand-crafted math problems: what I learned writing seed data for an adaptive tutor

From Bayesian to deep knowledge tracing — upgrading NumPath's student model with a PyTorch LSTM

Building a mistake taxonomy for dyscalculia — 8 error patterns, rule-based, no ML required

Clean Architecture in a FastAPI + Vue 3 monorepo

Building a FastAPI + Vue 3 research platform: the 4 bugs that almost broke Phase 1

Bayesian Knowledge Tracing in 37 lines of Python — how NumPath models what a student knows

Attempt history in the teacher dashboard — the scalar subquery pattern

Prompt engineering for teacher insights with Claude — structured JSON and graceful fallbacks

Closing the feedback loop: how mistake classification drives adaptive problem selection in NumPath

Why I'm building an AI math tutor for dyscalculia — and grounding it in 30 years of ITS research

Why teachers need explainable AI, not just accurate AI — building the KC dashboard