explosion

Author: tecunningham

posts/2025-09-13-recursive-self-improvement-explosion-optimization.qmd

@@ -49,7 +49,7 @@ execute:
     - **Measuring capability.**
     - **Bottlenecks.** Some arguments that AI R&D is bottlenecked by compute, e.g. see @whitfill2025bottlenecks.
     - **Scale-dependent algorithmic progress.** @gundlach2025algorithmicprogressai argue that algorithmic progress has contributed much less.
-    - **Data contribution.** Berren Millidge argues ["Most Algorithmic Progress is Data Progress"](https://www.beren.io/2025-08-02-Most-Algorithmic-Progress-is-Data-Progress/)
+    - **Data contribution.** Berren Millidge argues ["Most Algorithmic Progress is Data Progress"](https://www.beren.io/2025-08-02-Most-Algorithmic-Progress-is-Data-Progress/). Data has been growing slower than compute.