Superforecasting
Making highly accurate predictions about future events.
Superforecasting is the practice of making very accurate predictions about future events. It involves combining knowledge, analytical thinking, and a willingness to update beliefs as new information becomes available.
For example, a superforecaster might analyze economic data, geopolitical trends, and expert opinions to predict the likelihood of a specific stock price change. They would then track the outcome and adjust their methods for future predictions.
Superforecasting refers to the process of identifying and cultivating individuals who demonstrate superior accuracy in forecasting future events compared to average individuals or even expert judgment. This practice, popularized by Philip Tetlock's research, involves rigorous training in probabilistic thinking, cognitive bias mitigation, and continuous learning from feedback.
Key elements include breaking down complex problems into smaller, quantifiable components, assigning probabilities to potential outcomes, and updating these probabilities dynamically as new information emerges. The focus is on the process and the aggregation of diverse perspectives rather than on a single oracle.
The term 'superforecasting' is appearing in frontier AI news as labs like Anthropic explore how AI systems might be used to enhance or even replicate human forecasting abilities. This connects to the broader interest in AI's potential for strategic decision-making and understanding complex future scenarios.
- AI:AM Highlights: Exploring the J-Space, AI Superforecasters, SambaNova's Chips, & LTX Video GenAnthropic · The Cognitive Revolution ·
- Anthropic Claude
- Anthropic's research mentions AI superforecasters, suggesting an interest in leveraging AI for improved prediction capabilities.
- Forecasting
- General predictions about the future, often less rigorous or data-d
- Prediction markets
- Platforms where participants trade contracts whose payoff de
- Expert systems
- AI systems designed to mimic the decision-making ability of a hu
The term and its systematic study were popularized by psychologist Philip Tetlock through his research on expert political judgment and subsequent work on superforecasters. Source ↗
Ask an AI assistant like Claude or ChatGPT to predict the outcome of a well-defined, near-term event, such as the closing price of a specific stock tomorrow. Then, ask it to explain its reasoning and the confidence level it has in its prediction. Finally, check the actual outcome and compare it to the AI's prediction.
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- PromptRole-play a student struggling with math for AI tutor simulationSimulate a student's math struggles and uncertainty for AI tutor evaluation. · 5 min
- TemplateReusable workflow templates for healthcare teamsTeams can create and share templates for common workflows like documentation or prior authorizations. · 15 min
- TemplateTemplate for building an AI tool tailored to your workA structured approach to defining and building a custom AI tool for specific business needs. · 15 min
- TemplateEvals CSV prompt list for agent skillsA CSV file template for listing prompts used in evaluating agent skills. · 20 min
- HeuristicDouble coding agent task completion with docs linksProviding coding agents with a documentation link significantly increases their task completion rate. · 2 min
Questions people ask
- What makes a forecaster a 'superforecaster'?
- Superforecasters are individuals who consistently make more accurate predictions than others by employing specific methods like probabilistic thinking, updating beliefs, and avoiding common cognitive biases.
- Can AI be a superforecaster?
- Researchers are exploring if AI systems can achieve superforecasting capabilities, potentially by learning from vast datasets and refining their predictive models with feedback.
First seen on Subvolts Jul 9, 2026. Updated Sep 16, 2026. Written by an AI model from the items above and reviewed against them weekly; report an error.