Wisdom of the silicon crowd: LLM ensemble prediction capabilities rival human crowd accuracy.

Human forecasting accuracy improves through the "wisdom of the crowd" effect, in which aggregated predictions tend to outperform individual ones. Past research suggests that individual large language models (LLMs) tend to underperform compared to human crowd aggregates. We simulate a wisdom of the crowd effect with LLMs.

Assume a can opener.

We propose a friendly amendment to integrative experiment design (IED), adversarial-collaboration IED, that incentivizes research teams from competing theoretical perspectives to identify zones of the design space where they possess an explanatory edge. This amendment is especially critical in debates that have high policy stakes and carry a strong normative-political charge that might otherwise prevent free exchange of ideas.

Prosocial motives underlie scientific censorship by scientists: A perspective and research agenda.

Science is among humanity's greatest achievements, yet scientific censorship is rarely studied empirically. We explore the social, psychological, and institutional causes and consequences of scientific censorship (defined as actions aimed at obstructing particular scientific ideas from reaching an audience for reasons other than low scientific quality). Popular narratives suggest that scientific censorship is driven by authoritarian officials with dark motives, such as dogmatism and intolerance.

Validating a forced-choice method for eliciting quality-of-reasoning judgments.

In this paper we investigate the criterion validity of forced-choice comparisons of the quality of written arguments with normative solutions. Across two studies, novices and experts assessing quality of reasoning through a forced-choice design were both able to choose arguments supporting more accurate solutions-62.2% (SE = 1%) of the time for novices and 74.