Loading...

Tag trends are in beta. Feedback? Thoughts? Email me at [email protected]

Alice the Caml

My fast zero-allocation webserver using OxCaml

TensorFlow.js is 500KB. I just needed a trendline. So I built micro-ml.

8 ML algorithms + statistics suite in ~56KB gzipped, updated my package.

Technology behind Koharu: Building a pure-Rust ML pipeline for manga translation (Tauri + Candle)

Fast Autoscheduling for Sparse ML Frameworks

A Python tool for review-driven regression testing of ML/LLM outputs

confidential-ml-transport - attestation-bound encrypted tensor transport for confidential ML inference

Why I chose Python for IaC and how I built re-usable AWS infra for ML using it

The maturity gap in ML pipeline infrastructure

I upgraded my Python automation for daily AI/ML news collection

Which Python backend framework should I prioritize learning in 2026? ( For AI/ML and others)

Timefence - Detect temporal data leakage in ML training datasets

Httpz – Zero-Allocation HTTP/1.1 Parser for OxCaml

Fun with Algebraic Effects - from Toy Examples to Hardcaml Simulations

minikv: A little KV store implementation in OCaml to practice DB systems things

What would make OCaml serverless ready?

Built a 24MB offline ML app with Burn + Tauri - runs on my iPhone at 80ms inference

New Book: "Mastering Modern Time Series Forecasting" – A Hands-On Guide to Statistical, ML, and

Show HN: CLI for working with Apple Core ML models

Show HN: Munimet.ro – ML-based status page for the local subways in SF

A 2026 look at three bio-ML opinions I had in 2024

Edge AI vs ML Compilers

Built a 24MB offline ML app with Burn (burn.dev) + Tauri - running on my iPhone at 80ms inference.

Qwen2.5 runs on my own ML framework (Magnetron)

I wrote a book! "Ultimate ONNX for Deep Learning Optimization" (Edge ML)

Dispor - Deploy ML Models from Jupyter Notebooks

Offline symbolic regression guided by ML diagnostics – early prototype demo

ML: Burn or Candle?

ML-DSA in golang

More →