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: GPT-4 Can Predict Social Science Experiment Results(18 posts)→
More from Research
- Meta FAIR's Self-Direction turns agent failures into reusable LoRA skills, +13.8pp on Terminal-Bench — karen_ullrich · 2026-10-27
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Why don't more LLMs ship 10M-token context? A researcher asks about attention tradeoffs — agarwl_ · 2026-10-27
- PSNR below 15 dB in papers likely means the metric was misused, researcher warns — kwangmoo_yi · 2026-10-27
- Ortet's first health eval: 34 open-weight models, 50 tasks, generic rankings fall short — thegautamkamath · 2026-10-27
- Scaling-fit discrepancy: output-head FLOPs are ~65% of compute at the smallest rung, ~3% at 535B — dlwh · 2026-10-27