Anthropic's Claude develops emergent internal 'J-space' for thinking

By PulseAugur Editorial · [1 sources] · 2026-07-09 10:55

Anthropic's Claude model has developed an internal "J-space" where it can process concepts without externalizing them. This emergent capability allows Claude to think about ideas internally, a feature not explicitly programmed by its creators. Researchers are exploring this phenomenon to understand advanced AI cognition. AI

IMPACT Reveals new insights into emergent AI cognition and internal processing capabilities.

RANK_REASON The item describes research findings about an emergent capability within an existing AI model, not a new release or product. [lever_c_demoted from research: ic=1 ai=1.0]

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Anthropic's Claude develops emergent internal 'J-space' for thinking

COVERAGE [1]

Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] · 2026-07-09 10:55

"We find that Claude has developed a small collection of internal neural patterns [...] allowing the model to think about a concept without writing it down. Not

"We find that Claude has developed a small collection of internal neural patterns [...] allowing the model to think about a concept without writing it down. Notably, the J-space wasn’t designed or programmed by us, but instead emerged on its own" #KI #AI #concious www.anthropic.c…

LINKS anthropic.com/…/global-workspace

COVERAGE [1]

"We find that Claude has developed a small collection of internal neural patterns [...] allowing the model to think about a concept without writing it down. Not

RELATED ENTITIES

RELATED TOPICS