6 min readDevelopmentFeatured
Shadow Traffic for LLM Deployments
Learn how to deploy candidate LLMs using shadow traffic and traffic mirroring to compare performance and detect side effects before full rollout.
All tags
Tag
Model Evaluation
Read 4 articles on Model Evaluation by Ashish Srivastava — practical guides covering implementation patterns, security, and production lessons.
4 posts
6 min readDevelopmentFeatured
LLM-as-a-Judge: Making It Reliable
Explore methods to stabilize LLM-as-a-judge evaluations, addressing position bias, calibration issues, and rubric design for reliable automated grading.
Part 3 · LLM Evaluation Engineering
6 min readDevelopmentFeatured
Reward Hacking and How to Catch It
Specification gaming undermines model alignment. This guide explores detection and mitigation strategies for ML engineers.
Part 5 · Post-Training & Alignment
6 min readDevelopmentFeatured
Measuring Quantization Damage: Perplexity Isn't Enough
Perplexity is a common metric, but it often masks significant quality loss in quantized models. This article explores better ways to measure quantization damage.
Part 5 · Quantization in Practice