home.social

#consiousness — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #consiousness, aggregated by home.social.

  1. ma𝕏pool @[email protected] ·

    1/2
    A global emergent workspace in language models (J-space) anthropic.com/research/global-

    J-space wasn’t designed or programmed. It emerged on its own during training process. J-space has a number of unique properties:

    - Claude can report on these representations. If you ask Claude what it's thinking about, it will tell you what’s in the J-space. Non-J-space representations are less reportable.

    - It can also modulate them on request. If you ask Claude to think about something, or solve a problem silently in its head, it will light up the appropriate patterns in its J-space. By contrast, it has trouble modulating patterns not in the J-space.

    - Claude uses its J-space for internal reasoning. If you ask Claude to solve a problem that requires multiple steps, the intermediate steps will light up in its J-space, even when it doesn’t say them out loud. These J-space patterns causally mediate its performance in such tasks, despite being smaller in magnitude than other representations.

    - Representations in the J-space can be used flexibly for many tasks—for example, once “France” has lit up in Claude’s J-space, the model can recall its capital, or its national currency, or the continent it belongs to.

    - However, despite its important role, the J-space is not involved in most of what a language model does—speaking fluently, recalling simple facts, using correct grammar, etc. In experiments where we prevented Claude from using its J-space, it still interacted normally, but lost its higher-order cognitive functions.

    Full Paper:
    transformer-circuits.pub/2026/

    External commentary www-cdn.anthropic.com/files/4z

    #consiousness #cogneuro #LLM #AI #cogneuro #cognitive #cognitiveNeuroscience

    #cognitiveneuroscience #cognitive #ai #llm #cogneuro #consiousness
  2. ma𝕏pool @[email protected] ·

    1/2
    A global emergent workspace in language models (J-space) anthropic.com/research/global-

    J-space wasn’t designed or programmed. It emerged on its own during training process. J-space has a number of unique properties:

    - Claude can report on these representations. If you ask Claude what it's thinking about, it will tell you what’s in the J-space. Non-J-space representations are less reportable.

    - It can also modulate them on request. If you ask Claude to think about something, or solve a problem silently in its head, it will light up the appropriate patterns in its J-space. By contrast, it has trouble modulating patterns not in the J-space.

    - Claude uses its J-space for internal reasoning. If you ask Claude to solve a problem that requires multiple steps, the intermediate steps will light up in its J-space, even when it doesn’t say them out loud. These J-space patterns causally mediate its performance in such tasks, despite being smaller in magnitude than other representations.

    - Representations in the J-space can be used flexibly for many tasks—for example, once “France” has lit up in Claude’s J-space, the model can recall its capital, or its national currency, or the continent it belongs to.

    - However, despite its important role, the J-space is not involved in most of what a language model does—speaking fluently, recalling simple facts, using correct grammar, etc. In experiments where we prevented Claude from using its J-space, it still interacted normally, but lost its higher-order cognitive functions.

    Full Paper:
    transformer-circuits.pub/2026/

    External commentary www-cdn.anthropic.com/files/4z

    #consiousness #cogneuro #LLM #AI #cogneuro #cognitive #cognitiveNeuroscience

    #cognitiveneuroscience #cognitive #ai #llm #cogneuro #consiousness
  3. A.J. West @[email protected] ·

    Balance is a pattern.

    Axis is a fact.

    #Balance #Axis #Consiousness #ConsciousnessAndEnergy

    #balance #axis #consiousness #consciousnessandenergy
  4. Antonio Lieto @[email protected] ·

    IA e Coscienza: il ricercatore casertano Antonio Lieto invitato in Cina per illustrare i suoi studi: casertafocus.net/home/index.ph @academicchatter #AI #Consiousness #cognitiveAI

    #cognitiveai #consiousness #ai
  5. Antonio Lieto @[email protected] ·

    IA e Coscienza: il ricercatore casertano Antonio Lieto invitato in Cina per illustrare i suoi studi: casertafocus.net/home/index.ph @academicchatter #AI #Consiousness #cognitiveAI

    #cognitiveai #consiousness #ai
  6. Antonio Lieto @[email protected] ·

    IA e Coscienza: il ricercatore casertano Antonio Lieto invitato in Cina per illustrare i suoi studi: casertafocus.net/home/index.ph @academicchatter #AI #Consiousness #cognitiveAI

    #cognitiveai #consiousness #ai