✳flâneur — a map of the web's best reading

Distinguish between inference scaling and "larger tasks use more compute" — AI Alignment Forum

alignmentforum.org · 1,329 words · saved by 1 readers

As many have observed, since reasoning models first came out, the amount of compute LLMs use to complete tasks has increased greatly. This trend is often called inference scaling and there is an open question of how much of recent AI progress is driven by inference scaling versus by other capability improvements. Whether inference compute is driving most recent AI progress matters because you can only scale up inference so far before costs are too high for AI to be useful (while training compute can be amortized over usage). However, it's important to distinguish between two reasons inference cost is going up: To understand this, it's helpful to think about the Pareto frontier of budget versus time-horizon. I'll denominate this in 50% reliability time-horizon. [1] Here is some fake data to illustrate what I expect this roughly looks like for recent progress: [2] For the notion of time horizon I'm using (see earlier footnote), the (unassisted) human frontier is (definitionally) a straig

x Distinguish between inference scaling and "larger tasks use more compute" — AI Alignment Forum AI Timelines Inference Scaling AI Frontpage 43 Distinguish between inference scaling and "larger tasks use more compute" by ryan_greenblatt 11th Feb 2026 3 min read 5 43 As many have observed, since reasoning models first came out , the amount of compute LLMs use to complete tasks has increased greatly. This trend is often called inference scaling and there is an open question of how much of recent AI progress is driven by inference scaling versus by other capability improvements . Whether inferenc

Explore this link on the map →

related reading