Making sense of how learning happens. https://www.carlhendrick.com/. Click to read The Learning Dispatch, by Carl Hendrick, a Substack publication with tens of thousands of subscribers.
Matt Rickard | Substack
Thoughts on engineering, startups, and AI. Click to read Matt Rickard, a Substack publication with thousands of subscribers.
How Learning Happens | Seminal Works in Educational Psychology and Wha
How Learning Happens introduces 28 giants of educational research and their findings on how we learn and what we need to learn effectively, efficiently, and
Fleetwood on Twitter / X
Studying continual learning at the moment, best papers thus far:https://t.co/Y9oXBAiyj2https://t.co/ByWlaF3ncnhttps://t.co/hG0XIzq6cHhttps://t.co/5VSEnBIkX2— Fleetwood (@fleetwood___) April 11, 2026
How the Substack feed is learning to understand your reading journey
Modeling sequences of user behavior makes discovery feel alive
Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
What would it mean to have a scientific understanding of AI? Models are not static objects: they are snapshots of time-evolving processes shaped by data, objectives, architectures, and optimization dynamics. Yet much of AI research treats models as fixed artifacts, analyzing behaviors after training rather than asking why they emerge. This position paper argues that a science of AI must move beyond post-hoc fixes and study the training dynamics that produce model behavior. Such a science should support progressively stronger forms of understanding: predicting outcomes from early training signals, intervening when trajectories go wrong, and ultimately designing training procedures that more reliably produce desired properties. Scaling laws have made prediction routine for loss; the challenge is extending this success to capabilities, biases, robustness, and safety-relevant behaviors. We articulate requirements for such theories grounded in the history and philosophy of science, examine progress in mechanistic interpretability, fairness, memorization, and simplicity bias, and identify concrete open problems.
Michael Nielsen – How science actually progresses
Introducing Nested Learning: A new ML paradigm for continual learning
Ali Behrouz, Student Researcher, and Vahab Mirrokni, VP and Google Fellow, Google Research
Keating — The Hyperteacher
Socratic AI that forces you to reconstruct understanding from memory. No hand-holding. No spoon-feeding. Free and open source.
Curriculum learning
Humans and animals learn much better when the examples are not randomly presented but organized in a meaningful order which illustrates gradually more concepts, and gradually more complex ones. Here, we formalize such training strategies in the context of machine learning, and call them "curriculum learning". In the context of recent research studying the difficulty of training in the presence of non-convex training criteria (for deep deterministic and stochastic neural networks), we explore curriculum learning in various set-ups. The experiments show that significant improvements in generalization can be achieved. We hypothesize that curriculum learning has both an effect on the speed of convergence of the training process to a minimum and, in the case of non-convex criteria, on the quality of the local minima obtained: curriculum learning can be seen as a particular form of continuation method (a general strategy for global optimization of non-convex functions).
Letta
Making machines that learn. Create stateful agents that remember everything, learn continuously, and improve themselves over time.
Center for Educational Progress | CEP | Substack
A think tank centered on orienting education toward a culture of excellence. Click to read Center for Educational Progress, a Substack publication with thousands of subscribers.
Learning Outside the Brain: Integrating Cognitive Science and Systems Biology
Learning is commonplace in organisms such as ourselves and even in organisms as far distant as the bee and the octopus. Such learning is implemented by brains, or neuronal networks, and has been extensively studied within ethology, psychology, cognitive science, and neuroscience. Whether learning also takes place in nonneuronal settings has remained a matter of sustained controversy, too often dominated by ideological views. In this survey, I will explain how learning can be rigorously interpreted as a form of information processing and then explore the evidence for whether learning also takes place in organismal contexts outside the brain, such as physiology, development, and individual cells. I will try to explain why it is important to build bridges in this way between cognitive science and systems biology, why concepts and methods from various branches of engineering may be helpful in this task, and what the eventual impact may be on how we think about the organism.
The Friction I Don't Want to Lose
I love learning. And while the friction of solving new problems is increasingly traded for speed, the experience gained by overcoming that friction is as important as ever.
LearnVector — A new AI company from Andrew Ng
A new AI company from Andrew Ng, with a $100M investment from Coursera — building one-to-one learning that stays with you until you've mastered new skills.
LearnVector — A new AI company from Andrew Ng
A new AI company from Andrew Ng, with a $100M investment from Coursera — building one-to-one learning that stays with you until you've mastered new skills.
Ever thought we acquire generalizable knowledge by discarding details and compressing our experiences? In a new BBS paper, @sabinasloman.bsky.social and I argue otherwise, proposing a novel way of studying human learning inspired by double descent in ML. Disagree? Propose a commentary by May 15 :)
