Observed arrival · 2026-09-19
Thomas van Dongen’s Small, Fast ML Workshop
A personal site collecting open-source machine-learning projects, technical writing, and work on production systems for embeddings, retrieval, and language models.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- ML engineers building search, retrieval, and embedding systems
- Worth noticing
- The project list includes Semble, Model2Vec, SemHash, Pyversity, and Potion, with visible repository activity counts.
Field notes
The homepage groups five named projects under an open-source portfolio, including tools for agent code search, static embeddings, semantic filtering, and retrieval diversification. It also lists technical writing on model distillation and efficient self-attention. Several entries show repository-style activity counts, while the biography connects the projects to AI systems for scientific publishing and to the Minish ML lab.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
◉HumanPersonal, local, civic, or handmade
One card from the complete issue