WangNet is a lightweight 1.8 MB neural network that classifies whether numbers are Numberwang, with inference in pure Python requiring no dependencies. It supports 11 languages, achieves 88.9% accuracy on held-out test cases, and can be run locally or via a hosted Hugging Face demo.
A Hacker News discussion questions why embeddings are predominantly used for retrieval and RAG systems despite being capable of clustering, recommendations, anomaly detection, and classification. The author argues that embeddings' semantic capabilities remain largely untapped and wonders whether retrieval dominates because it's easier to productize than other use cases.
This article explores knowledge distillation applied to a bigram language model, the simplest possible sequence model. The author demonstrates that distillation does not improve the bigram's learned distribution and that standard training achieves equivalent results with sufficient data, but the analysis reveals what soft targets change and what they preserve.
A comparison of AI models for mushroom identification reveals that Gemini 3.8 Flash excels at recognition accuracy, while GPT-6 Astra demonstrates greater wisdom by requesting additional information and providing appropriate safety disclaimers. When models are allowed free-form responses rather than forced to give definitive answers, they typically include warnings about misidentifications, though dangerous errors without warnings remain rare.