Blog
60 posts.
Category
2026-06-05
Boltzmann Machines & Energy-Based Models: The Nobel-Prize-Winning Physics Behind Neural Networks
AI & ML
2026-06-05
A Mathematical Framework for Transformer Circuits: How LLMs Actually Work
Interpretability & Safety
2026-06-05
Mechanistic Interpretability & Sparse Autoencoders: Giving AI an X-Ray
Interpretability & Safety
2026-04-18
SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering (ACL 2026)
Interpretability & Safety
2026-04-14
King Salhesh, Malini & the Unfulfilled Loves – The Magical Bloom of Salhesh Fulbari and the Cool Touch of Jur Shital
Culture & Mithila
2026-03-08
Internet Penetration and RSP's Success in Nepal's 2082 Election — A Quick Correlation Look
Culture & Mithila
2026-02-14
Can You Predict a Network's Performance from Its Geometry Alone?
Interpretability & Safety
2025-12-28
Attention Is All You Need: A Visual Journey Through Semantic Space
Interpretability & Safety
2025-12-26
SAFE-MCP: A Comprehensive Security Framework for Model Context Protocol
Interpretability & Safety
2025-12-03
Mastering Hexagonal Architecture: A Complete Guide with Python Implementation
Engineering
2025-09-13
The Legend of Jimutavahana: A Detailed Story of Sacrifice and Compassion
Culture & Mithila
2025-08-06
GPT-OSS: OpenAI's Open-Weight Mixture-of-Experts Language Model - A Technical Deep Dive
AI & ML
2025-07-23
The Churia Forests and Rainfall in Nepal’s Terai: Impacts of Deforestation on Precipitation and Ecosystem Balance
Culture & Mithila