LLM-only pilots cost under $1 and rival ~230-person human pilots
RobbWiller · x · 2026-07-23
The post summarizes two practical uses of the forecasting method.
- After recalibration, an LLM-only pilot costing under $1 for most models had prediction error comparable to a 230-person human pilot costing about $736.
- Combining LLM forecasts + 100 people matched the accuracy of a humans-only pilot with 385 participants.
- Across 11 megastudies, interventions chosen with expert + LLM judgments produced effects that were 6% larger on average than expert-only selection.
Related event: Nature Study: LLMs Can Predict Social Science Experiment Results(14 posts)→
More from Research
- Science paper turns memristor drift into a 2.12 ms neural dynamical system — jiqizhixin · 2026-07-23
- Can LLMs Predict Experiment Results? Nature Paper Reveals Strong Alignment with Human Data — RobbWiller · 2026-07-23
- W&B says world action models can show their “dream” before choosing actions — wandb · 2026-07-23
- W&B says NVIDIA’s 14B DreamZero model fails hard tasks despite clean scalar metrics — wandb · 2026-07-23
- Winning NVIDIA Challenge Solution: Memorize Patterns, Search and Verify at Inference — NVIDIAAI · 2026-07-23
- UW-Madison Receives Multiple DOE Genesis Awards for AI in Energy — KyleCranmer · 2026-07-23