{"author":{"name":"Jonathan Warrell","slug":"jonathan-warrell","article_count":1,"latest_published_at":"2026-04-18T18:53:38.894+00:00","profile_url":"https://platform.waiboom.ai/authors/jonathan-warrell","api_url":"https://platform.waiboom.ai/api/authors/jonathan-warrell"},"articles":[{"slug":"interpretability-and-implicit-model-semantics-in-biomedicine-and-deep-learning","title":"Interpretability Alone Isn't Enough: A New Framework for Model Semantics","url":"https://platform.waiboom.ai/article/2026/04/18/interpretability-and-implicit-model-semantics-in-biomedicine-and-deep-learning","content_type":"research_summary","summary":"Jonathan Warrell introduces a formal framework for analyzing interpretability in deep learning by drawing on model semantics from philosophy of science. The work argues that interpretability is only one component of a model's broader semantics, not its entirety. The framework is illustrated through biomedical examples, suggesting that understanding how models work requires looking beyond traditional interpretability approaches to capture implicit meaning and assumptions embedded in model behavior.","published_at":"2026-04-18T18:53:38.894+00:00","updated_at":"2026-04-22T00:59:04.768177+00:00","source":{"url":"https://www.nature.com/articles/s42256-026-01177-0","name":"Nature Machine Intelligence"},"featured_image":{"url":"https://bs-uploads.toptal.io/blackfish-uploads/components/blog_post_page/8079129/cover_image/regular_1708x683/Cortex_Semantic_Metadata_Image_Labeling-Blog-fd1d9feab22ad96eeb3d6d5df7d3816c.png","alt":null},"categories":[{"name":"Research","slug":"research"},{"name":"AI Safety & Alignment","slug":"ai-safety-alignment"}]}]}