The Sequence Knowledge - Issue #964: Learning RSI: How Models Generate Their Own Learning Curricula
Was this email forwarded to you? Sign up here
The Sequence Knowledge - Issue #964: Learning RSI: How Models Generate Their Own Learning Curricula
Absolute Zero and the search for useful difficulty
TLDR: A fixed dataset quietly decides what a model gets to practice, so the next step in recursive self-improvement is letting models generate their own curriculum. Absolute Zero grounds proposed coding tasks in code execution, R-Zero pairs a Challenger with a Solver that grades itself by majority vote, and R-Few adds a small supply of trusted human examples to keep the loop from drifting. The catch is that difficulty is an imperfect proxy for progress: a verifier only establishes what its tests cover, and agreement among sampled answers can repeat the same mistake.
We cover why the dataset has been making decisions for us, what execution can and cannot verify through deduction, abduction, and induction, why pseudo-label quality declines as questions get harder, and what POET teaches about stepping stones. We close with the evidence a self-generated curriculum would need to show: progress across multiple rounds, under a fixed budget, on evaluation tasks the model cannot influence.
A student who can solve every exercise in a workbook needs a different workbook. A student who cannot solve any exercise probably does too. Between those extremes lies the useful part of education: problems that connect what the student knows to what the student could learn next. Building that sequence is a substantial intellectual task.
AI research is beginning to automate it. Absolute Zero and R-Zero let models generate the problems used in their own improvement. The opportunity reaches beyond inexpensive synthetic data. An adaptive curriculum can respond to a learner’s changing capabilities, making the selection of future experience part of the learning process. The challenge is ensuring that increasingly difficult homework continues to teach something useful.
The dataset has been making decisions for us...
Subscribe to TheSequence to unlock the rest.
Become a paying subscriber of TheSequence to get access to this post and other subscriber-only content.
A subscription gets you:
© 2026 Jesus Rodriguez
75 Miracle Mile, Suite 7688, Coral Gables, FL 33134