June 26, 2025
Research and Writings
June 25, 2025
Deep Research Bench Leaderboard Goes Live
June 11, 2025
Bench to the Future: A Pastcasting Benchmark for Forecasting Agents (paper)
May 16, 2025
Deep Research Bench: Evaluating AI Web "Search" and"Research" Agents (paper)
May 12, 2025
OpenAI's Revenue in 2027: A Comprehensive Forecast
May 1, 2025
Superhuman Coders in AI 2027 - Not So Fast
April 18, 2025
Calculating Price Increases from Tariffs on American-Made Goods
April 3, 2025
The Bull Case for OpenAI
April 3, 2025
AI 2027: Forecasting the Arrival of Superintelligence
March 10, 2025
Apple's Plan to Power Siri with ChatGPT was a Predictable Failure
February 28, 2025
When should agents persist vs. adapt? Lessons from Deep Research
February 19, 2025
OpenAI Deep Research: Six Strange Failures
November 11, 2024
The Death and Life of Prediction Markets at Google
September 24, 2024
A Realistic Benchmark for Open-Web Research Agents (paper)
September 18, 2024
OpenAI's financials: a Case Study of claims vs. reality
September 13, 2024
Real-world evals of the OpenAI's o1, the first"thinking" model
August 27, 2024
Profitability of OpenAI's API
September 12, 2024
Contra Papers Claiming Superhuman AI Forecasting
June 12, 2024
The First Full OpenAI Revenue Breakdown
June 9, 2024
How to Integrate AI Into Forecasting (video)
April 2, 2024
The Rationale-Shaped Hole at the Heart of Forecasting
January 8, 2024
The Human v Bots Forecasting Tournament
Interested in our research?
Stay up to date with our latest findings and methodologies in AI reasoning and forecasting.