Revealing a Global Workspace in Language Models
No Space Like J-Space
There is a new very cool Anthropic paper: Verbalizable Representations Form a Global Workspace in Language Models. You can read the blog post verison here.
How Large Language Models Actually Work
An Observation on Generalization
LLMs and World Models, Part 1
How do Large Language Models Make Sense of Their “Worlds”?
Mapping the Mind of a Large Language Model
We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. This is the first ever detailed look inside a modern, production-grade large language model.
Recursive Language Models: the paradigm of 2026
How we plan to manage extremely long contexts
.png?v=c8c07d4bf43b)
A global workspace in language models
Interpretability research on Claude's internal thoughts.
TranslateGemma: A new suite of open translation models
TranslateGemma is a new family of open translation models built on Gemma 3.
Language models struggle with compartmentalization
In the training data used by large language models (LLMs), the same latent concept is often presented in multiple distinct ways: the same facts appear in English and Swahili; many functions can be expressed in both Python and Haskell; we can express propositions in both formal and natural language. We show that LLMs can exhibit compartmentalization, where they fail to identify and share statistical strength between distinct presentations of unified concepts. In the worst case, LLMs simply learn parallel internal representations of each presentation of the concept, saturating model capacity with redundancies and decreasing sample efficiency with the number of such presentations. We also demonstrate that synthetic parallel data can fail to improve this despite being easily learned itself. Under this framework, we find that, for small models, early multilingual learning is nearly entirely compartmentalized. Finally, all interventions that we study exhibit a phase transition in which their effectiveness depends on the number of distinct presentations, suggesting that the language modeling objective may only inconsistently unify representations.
Task-Completion Time Horizons of Frontier AI Models
Our most up-to-date measurements of the time horizons for public frontier language models.
The Case Against LLMs as Rerankers
Authors: Apoorva Joshi, Zhenmei Shi, Akshay Goindani, Hong LiuResearch Leads: Zhenmei Shi, Akshay Goindani, Hong Liu Large language models are increasingly being used for a broad range of tasks, in…
Large language models are cultural technologies. What might that mean?
Four different perspectives
Models overview
Claude is a family of state-of-the-art large language models developed by Anthropic. This guide introduces the available models and compares their performance.