https://www.anthropic.com/news/tracing-thoughts-language-model
This provides additional evidence for a kind of conceptual universality—a shared abstract space where meanings exist and where thinking can happen before being translated into specific languages.
More practically, it suggests Claude can learn something in one language and apply that knowledge when speaking another. Studying how the model shares what it knows across contexts is important to understanding its most advanced reasoning capabilities, which generalize across many domains.
planning ability and adaptive flexibility
involving a mix of approximate and precise strategies,
tension between grammatical coherence and safety mechanisms.
Referenced in:
All notes