RSS Amplifier

Blog

Research - Mrinank Sharma

mrinanksharma.net ↗RSS feed ↗8 posts

Latest posts

Forecasting Rare Language Model Behaviors

Constitutional Classifiers

Best-of-N Jailbreaking

Rapid Response: Mitigating LLM Jailbreaks with a Few Examples

Towards Understanding Sycophancy in Language Models

Do Bayesian Neural Networks Need To Be Fully Stochastic?

Many-shot Jailbreaking

Inferring the effectiveness of government interventions against COVID-19