How to Anonymize Personal Data in an LLM Pipeline.
Author(s): Souvik Sarkar Originally published on Towards AI. 5 key techniques explained. Every team building on large language models faces the same quiet risk. Training data, fine-tuning datasets, retrieval-augmented generation inputs, and user prompts all carry personally identifiable information (PII), meaning names, …
5 Reasons Why RAG Fails in Production.
Author(s): Souvik Sarkar Originally published on Towards AI. And how OKF fixes that. Most teams building AI-powered products in 2026 are running some version of RAG, short for Retrieval-Augmented Generation. The pattern is familiar: take a user question, search a vector database …
AI’s Empathy is an Unhealthy Addiction
Author(s): Souvik Sarkar Originally published on Towards AI. New research reveals the risk of a one-sided relationship. It’s always available. It remembers every small detail of your life. It offers unfailing support and is free of the messy demands of human relationships. …
AI’s Empathy is an Unhealthy Addiction
Author(s): Souvik Sarkar Originally published on Towards AI. New research reveals the risk of a one-sided relationship. It’s always available. It remembers every small detail of your life. It offers unfailing support and is free of the messy demands of human relationships. …
Recent Posts
![[Day 37/100] Build Your Own Agent Memory Layer with Postgres and pgvector](https://miro.medium.com/v2/resize:fit:700/1*-Doos2nmUT3FPZ-Qxbk3Hw.png "[Day 37/100] Build Your Own Agent Memory Layer with Postgres and pgvector")
