News for hackers. Stuff that matters.
Re:Claude's Cycles: Claude Opus 4.6 solves a problem posed b... by gravypod on Tuesday March 03, 2026 @09:22PM (#47242188)
This is very interesting. I wonder if someone could create a future-sight benchmark for these models? Like, if given a set of newspaper articles for the past N months can it predict if certain world events would happen? We could backtest against results that have happened since the training cutoff.
Re:Claude's Cycles: Claude Opus 4.6 solves a problem posed b... by houtanb on Wednesday March 04, 2026 @02:18AM (#47244236)
FYI, ForecastBench [1] tests LLMs' out-of-sample forecasting accuracy.

The ForecastBench Tournament Leaderboard [2] allows external participants to submit models, most of whom provide some sort of web search / news scaffolding to improve model forecasting accuracy.

[1] https://www.forecastbench.org/

[2] https://www.forecastbench.org/tournament/

Re:Claude's Cycles: Claude Opus 4.6 solves a problem posed b... by kqr on Wednesday March 04, 2026 @03:33AM (#47244698)
These days computers compete along with humans in forecasting tournaments on Metaculus. They don't quite beat the top humans yet, but they're up there. https://www.metaculus.com/futureeval/