The Representation Layer — long-form notes by Alper Nebi Kanlı, a Staff Software Engineer in London working on search and information retrieval, on embeddings, retrieval, language models, and the systems underneath modern AI.
Abliteration deletes a model's refusal with a difference of means and some linear algebra. A walk through what that operation actually touches: one direction or many, refusal or safety, and the gap between a structure being present and the model using it.
A tour of the micro debate on representational convergence, from lines and categories to circles, helices and spectra, and the gap between a structure being present, readable, and actually used.
A tour of the macro debate on representational convergence, from the Platonic Representation Hypothesis to scaled critiques and the Aristotelian view.
a new encoder-only model
continuing the journey of embeddings, exploring the llm era
an overview of the journey of embeddings
what am i trying to do in the series words and their mappings?
a brief introduction to the series words and their mappings
Elasticsearch is a fast, scalable search and analytics engine built on Apache Lucene, known for real-time search and powerful querying. Its architecture consists of clusters, nodes, and shards, with nodes handling indexing and queries while shards distribute data for better performance and fault tolerance.