Here is an experience you have probably had by now. You set up an agent in the spring. Same model all quarter, weights frozen solid, not a single gradient step. And yet by summer the thing is noticeably better at your workflows. Fewer dumb mistakes, better tool choices, less babysitting. Nothing learned anything, in the technical sense of the word. So what improved? The answer is that improvement has three places to live, and only one of them is the model. Parts 1 and 2 of this series were about the bottom layer, the weights, where frontier labs run their industrial flywheel. This essay is about the other two layers, because that is where most of the user-visible improvement of 2026 actually happens, and because the mechanics up there are strange, underrated, and occasionally uncomfortable. Three layers, three very different update economics. The bottom layer gets all the press. The top layer gets all the updates. The employee with the immaculate notes Read more
The Sequence Knowledge - Issue 941: Learning RSI: The Model Is Frozen. The System Is Not.
Summary
Your agent got better this quarter and nobody trained anything. Where did the improvement go? Into the notes. This is the loop that runs between model releases, and it might be where the durable value
The Sequence Knowledge - Issue 941: Learning RSI: The Model Is Frozen. The System Is Not.
Report an error
The correction channel is not available yet. You can copy the article reference below for later.
Correction instructions