Subhadip Mitra articles - 4 total
I Trained Probes to Catch AI Models Sandbagging
TL;DR: I extracted "sandbagging directions" from three open-weight models and trained linear probes...
Why I Built a Spark-Native LLM Evaluation Framework
This post is a deep dive into building spark-llm-eval, an open-source framework for running LLM...
The MCP Maturity Model: Evaluating Your Multi-Agent Context Strategy
It's been nearly a year since Anthropic introduced the Model Context Protocol (MCP) in November 2024,...
We Need a Consent Layer for AI (And I'm Trying to Build One)
TL;DR The Problem: AI has no consent layer. Creators can't control how their data is...