Reading up on scikit-learn
4 deep · digging since mar 06
- Classic ML to cope with Dumb LLM Judges
Combining many low‑confidence LLM relevance judgments via a decision tree boosts precision for e‑commerce search relevance, achieving up to ~96.5% precision on ~40% of test pairs.
- 2.7. Novelty and Outlier Detection — scikit-learn 1.9.1 documentation
The scikit-learn documentation explains how novelty and outlier detection differ, describing algorithms like Isolation Forest, Local Outlier Factor, and One‑Class SVM for identifying abnormal observations.
- Rethinking open source mentorship in the AI era - The GitHub Blog
In the AI era, open source maintainers should use the 3 Cs framework to mentor strategically without burnout as contribution volume grows.
- Show HN: Timber – Ollama for classical ML models, 336x faster than Python
Timber compiles classical ML models into self-contained C99 artifacts, enabling 2 µs inference that is approximately 336× faster than Python.