Bio
Leading Platform Research at Applied Compute — focused primarily on continual learning, context, synthetic users/tasks, and more around our RL stack. Previously at Scale AI and Amazon.
Session (1)
Additional Speaker Details
Using publicly available information we constructed an analysis to help you get a feel for this speaker before deciding to attend their session.
Sam Denton works at the seam between frontier ML research and enterprise deployment. He has authored multiple 2026 papers on agent evaluation harnesses and retrieval evaluation (including VeRO at ICML 2026) and ships production context-and-memory systems for enterprise agents at Applied Compute. His session should offer grounded insight into what it takes to make RL-trained agents reliable at enterprise scale.
Speaking style
Deeply technicalBattle-tested
GitHub
@sam-scaleRecent writing (5)
- Memory in the wild: how we use Context Engine on our own code · blog · May 2026
- Remember, Refine, Retrieve: A Context Engine for Enterprise Agents · blog · May 2026
- Coverage, Not Averages: Semantic Stratification for Trustworthy Retrieval Evaluation · paper · Apr 2026
- VeRO: An Evaluation Harness for Agents to Optimize Agents · paper · Feb 2026
- LHAW: Controllable Underspecification for Long-Horizon Tasks · paper · Feb 2026
Podcasts & interviews (4)
- We decided if these viral AI agent demos were real or fake · Human in the Loop (Scale AI) · Aug 2025
- we try to predict the next 6 months in ai · Human in the Loop (Scale AI) · Jul 2025
- We argued about the AI headlines everyone is talking about · Human in the Loop (Scale AI) · Jul 2025
- Enterprise Evaluations | Human in the Loop Episode 6 · Human in the Loop (Scale AI) · May 2025