Scale AI Blog

Sam Denton

Senior Machine Learning Research Engineer

Beyond "Out-of-the-Box": Why Enterprises Need Specialized RL Agents

Smoothing Out LLM Variance for Reliable Enterprise Evals

Toolchaining: The Problem No One is Talking About

Training the Next Generation of Enterprise Agents: Scale's Research in Reinforcement Learning

Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for Fine-Tuning LLMs