Toby Ord: task horizon likely follows a power law in RL compute, not linear
tobyordoxford · x · 2026-11-14
In a discussion with Ramez, Ben Todd and others, Oxford researcher Toby Ord argues that even if ECI is logarithmic in RL compute and horizon is exponential in ECI, the two effects don't automatically cancel back to linear — it depends on the constants. In general, task horizon can be a power law of RL compute.
Related event: Oxford's Toby Ord: RL Compute Needs 10,000x Boost to Lift Benchmark Scores(17 posts)→
More from Research
- 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
- MIT professor to showcase autonomous AI agent swarms for metamaterials discovery — ProfBuehlerMIT · 2026-11-14
- Walden talk: base models improving fast, mid-training data commoditizing — ZeYanjie · 2026-11-14