AI models now match superforecasters on ForecastBench; rematch set for October
burny_tech · x · 2026-09-23
The Forecast Research Institute reports that AI models now match human superforecasters on its ForecastBench benchmark, though not by a statistically significant margin. A rematch is planned for October, with superforecasters returning to compete against the top AI forecasters. The thread promises details on what the result means, why the rematch is happening, and how to compete.
More from Research
- Genome LM Minerva finds reverse transcriptase systems encode diverse structured ncRNAs — BrianHie · 2026-09-23
- q-Neurons: stochastic Jackson-derivative activations consistently beat standard ones — FrnkNlsn · 2026-09-23
- OpenAI said to launch journal with multi-agent AI reviews, threatening ML conferences — kfountou · 2026-09-23
- Yale PhD student open-sources his paper figure scripts, packaged as a Skill for Claude Code and Cursor — burny_tech · 2026-09-23
- Dev uses Opus 5.5 with Lean to formally verify Claude Agent SDK, yielding 16 bug-fix PRs — bcherny · 2026-09-23
- Mathematicians, not just LLMs, made AI's math breakthroughs possible, scholars argue — tak3sh8 · 2026-09-23