If you don't know what the METR time horizon benchmarks are then here: https://metr.org/time-horizons/ The task completion time horizon is the task duration (measured by human expert completion time) at which an AI agent is predicted to succeed with a given level of reliability. For example, the 50%-time horizon is...
A pocket tool for Bayesian calibration. Have you ever desired external tools for the deliberate shaping of your mind? If so, I’m pleased to introduce Calibrate an open source Android app for probabilistic forecasting calibration. Do you wish that when you said something had a 75% chance, it really did...
Yesterday I discovered I had been a victim of the Typical Mind Fallacy thanks to accidentally finding out that someone very close to me doesn’t have an internal monologue, doesn’t think in words and has a visual photographic memory. Despite knowing that such people existed I thought I would know...
Epistemic status: I have made many predictions for quantitative AI development this decade, these predictions were based on what I think is solid reasoning, and extrapolations from prior data. If people do not intuitively understand the timescales of exponential functions, then multiple converging exponential functions will be even more misunderstood....