Does AGENTS.md Actually Work? The First Empirical Study
The first empirical study evaluating AGENTS.md effectiveness has been published. We analyze its impact on coding agent success rates and inference costs.
Tags
research
4 posts
Verbalized Sampling: Restoring LLM Diversity via Prompts
Verbalized Sampling tackles mode collapse after alignment by prompting models to verbalize probability distributions, achieving 1.6-2.1x diversity gains without retraining
Analyzing Blog Revisit Intent with SSR Methodology
Experimental results and statistical analysis of 225 evaluations using LLM-based Semantic Similarity Rating. Validated high reliability with ICC 0.83 and visualizations.
What Happens When You Assign Gender and Personas to AI Agents?
Does giving an AI agent a gender or persona change performance? Drawing on 120+ psychology and NLP studies, we unpack expert personas, emotion, and role assignment — with design strategies by task type.