I joined Anthropic (alignment team) this week — exciting place to be at an exciting time!
Профиль
Andrew Lampinen
Профиль VivelyInterested in cognition and artificial intelligence. Researcher at Anthropic; previously DeepMind, cognitive science at Stanford. Posts are mine. lampinen.github.io
Short post on what I call the "no-magic approach to understanding intelligent systems" — the philosophy I think of as motivating our work on understanding intelligence without resorting to magical thinking about AI or humans! infinitefaculty.substack.com/p/the-no-mag...
The no-magic approach to understanding intelligent systemsToday I want to write a bit about the philosophy I think underlies much of the work that my collaborators and I (as well as many other researchers that I respect) have done on understanding artificial...infinitefaculty.substack.comReally cool work — learning over sequential experiences that contain the embodied cue of viewpoint as well as visual inputs, can give rise to human-like 3D shape perception!
tyler bonnenexcited to share some recent work! neural networks trained on multi-view sensory data are the first to match human-level 3D shape perception we predict human accuracy, error patterns, and reaction time—all zero-shot, no training on experimental data arxiv.org/abs/2602.17650 1/🧠
What is the relationship between memorization and generalization in AI? Is there a fundamental tradeoff? In infinitefaculty.substack.com/p/memorizati... I’ve reviewed some of the evolving perspectives on memorization & generalization in machine learning, from classic perspectives through LLMs.
Memorization vs. generalization in deep learning: implicit biases, benign overfitting, and moreOr: how I learned to stop worrying and love the memorizationinfinitefaculty.substack.comInteresting results by @eghbal-hosseini.bsky.social on how language models representation geometry evolves during different types of in-context learning!
Eghbal HosseiniHow do diverse context structures reshape representations in LLMs? In our new work, we explore this via representational straightening. We found LLMs are like a Swiss Army knife: they select different computational mechanisms reflected in different representational structures. 1/
New paper! In arxiv.org/abs/2601.20834 we study how language models representations of things like factuality evolve over a conversation. We find that in edge case conversations, e.g. about model consciousness or delusional content, model representations can change dramatically! 1/