header-langage
简体中文
繁體中文
English
Tiếng Việt
한국어
日本語
ภาษาไทย
Türkçe
Scan to Download the APP
Partnered With:

Anthropic: The Claude model posits an existence akin to "conscious human-like cognition."

BlockBeats News, July 7th, Anthropic released its latest research report, which found that the Claude model spontaneously exhibits an internal "global workspace" called J-space (Jacobian space). This is a dedicated neural activation pattern set for silent contemplation in the model, allowing the model to think about concepts without explicitly expressing them, akin to human reportable "conscious" thoughts.


The research identified neural activation patterns in J-space using Jacobian techniques, enabling the reading of concepts the model has not vocalized, and the modification of these patterns. Experiments showed that disabling J-space would weaken multi-step reasoning ability but would not affect basic tasks and factual memory.


Click on the original article link below to join the BlockBeats · Feishu AI News Channel, which provides 24/7 monitoring of global AI hot topics and news.

举报 Correction/Report
RelatedRecommended
This is Claude's Signal from AI Tool to AI Employee
Anthropic's Chief Product Officer Mike Krieger Latest Interview
A routine engineering oversight exposed a glimpse of the next-generation AI product landscape
Correction/Report
Submit
Add Library
Visible to myself only
Public
Save
Choose Library
Add Library
Cancel
Finish