https://thecodersblog.com/tag/semantics/Recent content in Semantics on The Coders BlogHugoen-usTue, 12 May 2026 07:50:50 +0000https://thecodersblog.com/embeddings-for-preferences-not-semantics-2026/Tue, 12 May 2026 07:50:50 +0000https://thecodersblog.com/embeddings-for-preferences-not-semantics-2026/<h1 id="ai-embeddings-prioritizing-preferences-over-semantics">AI Embeddings: Prioritizing Preferences Over Semantics</h1> <p>The &ldquo;$4.2 Million Embedding Error&rdquo; incident, where a Retrieval Augmented Generation (RAG) pipeline misinterpreted tax credit eligibility due to a nuanced semantic overlap, is not an isolated anomaly. It’s a stark illustration of a foundational problem: our current obsession with semantic embeddings might be fundamentally misaligned with the tasks AI is increasingly being asked to perform. For years, the dominant paradigm in embedding technology has been to capture lexical and conceptual similarity. Models like BERT, Sentence-BERT, BGE-M3, and OpenAI&rsquo;s <code>text-embedding-3-large</code> excel at this, mapping sentences and documents into vector spaces where proximity signifies semantic relatedness. However, this research proposes a critical shift: for many real-world applications, particularly those involving human interaction, preference capture, and nuanced decision-making, the true north should be <strong>preferential similarity</strong>, not semantic similarity.</p>