factual
Agentic coding horizon length doubling every six months
METR's horizon-length benchmark measures the length of coding tasks AIs can complete (sorted by how long they take human professionals), and for the last couple of years the task length AIs can reliably do has been doubling roughly every six months along a smooth line; the key signal to watch is whether this trend continues, accelerates and bends upward toward full autonomy, or decelerates and plateaus.
factualpending
Speaker
Daniel KokotajloEvidence Quote
“they base basically have a bunch of coding tasks sorted by how long it takes human professionals to complete the coding tasks and then they notice that oh that's interesting like generally speaking a given ai system can do most of the coding tasks below a certain point but not above a certain point”
Created: 6/14/2026, 1:48:29 AM
Your notes
Loading notes...