Research
- Predicting Ad Effectiveness: A Self-Optimizing Pipeline Over Six Cycles2026.04.23
- Autonomous Optimization on Clinical Triage: Raising DeepSeek V3.1 from 84% to 97% on the Ramaswamy Factorial Benchmark2026.04.21
- Self-Optimizing Pipeline: How Iterative Experimentation Brought Open-Weight Models to Frontier Performance on HealthBench2026.04.06
- Extending Ramaswamy et al. (2026): When Accuracy and Safety Diverge in LLM Clinical Triage2026.03.20