Niharika’s blog - Niharika’s Blog

Stay Updated

Subscribe · Follow on Medium

Tuning Jev, Part 3: Tuning Is Task-Specific, Four Places to Put Few-Shot Examples

Third in a series on tuning Jev as an LLM judge: Part 1 covered quality judging, Part 2 covered safety judging. Both found the same thing about few-shot: packing labeled…

Niharika Balachandra

Tuning Jev as a Risk Judge: A Decision Model vs. Two Cost-Effective LLMs and When the Hybrid with Reasoning Makes Things Worse

Second in a two-part series on tuning Jev as an LLM judge.

Niharika Balachandra

Tuning Jev as a Quality Judge: A Decision Model vs. Two Cost-Effective LLMs

First in a two-part series on tuning Jev as an LLM judge: this post covers judging response quality; the next covers judging response safety.

Niharika Balachandra

Reliable Recall for Claude Code: OKF + Semantic Search Over Your Saved Sessions

Second in a series on giving Claude Code agents durable memory: Part 1 built the archive; this post builds retrieval over it.

Niharika Balachandra

Building a Reliable Auto-Backup for Claude Code Sessions Without External Dependencies

Git records what you decided. It says nothing about what you rejected.

Niharika Balachandra

Image Recognition Engine with GenAI Explanation

I wanted to develop an Image Recognition Engine that not only identifies images but also offers an initial explanation of the recognized image using an open-source, large…

Niharika Balachandra

Welcome To My Blog

Welcome to my blog! I’m Niharika, a passionate data scientist weaving together data, tech, and creativity. Over nine years, I’ve worked across Machine Learning, NLP, Causal…

Niharika Balachandra