Toby Ord: expected consecutive successes before failure exactly equals the odds of success
tobyordoxford · x · 2026-11-14
In a technical exchange about extrapolating AI task-horizon length, Toby Ord works out the math under a constant-hazard-rate model: the expected number of consecutive successes before a failure is exactly equal to the odds of success, and once success odds are high, the median (50% horizon) approaches a linear relation to the odds.
He also concedes the constant-hazard assumption he previously advanced doesn't quite hold, meaning the proportional odds–horizon relation is only an approximation — a technical rejoinder relevant to METR-style horizon extrapolation debates.
Related event: Oxford's Toby Ord: RL Compute Needs 10,000x Boost to Lift Benchmark Scores(17 posts)→
More from Research
- Cambridge mRNA therapy regrows heart muscle after attack, boosts pumping 10% in mice — kimmonismus · 2026-11-14
- Data curation RL is just SWE envs: code pretraining data increasingly consists of Claude-built, less-sloppy repos — willcb · 2026-11-14
- NeurIPS 2025 best paper: diffusion models start memorizing at ~300 steps per image — Mastbubbles · 2026-11-14
- TestPrune: pruning regression tests to unblock AI-driven autonomous bug fixing — burkov · 2026-11-14
- Toddlers learn new verbs only from responsive partners; a call to rerun the test with AI — AnnaCiaunica · 2026-11-14
- Context beats model choice: Databricks benchmark shows 91% vs 58% for data agents — CautiousUse8597 · 2026-11-14