Notbale article and paper by Anthropic on the so called J-Space:

A global workspace in language models
https://www.anthropic.com/research/global-workspace

Verbalizable Representations Form a Global Workspace in Language Models
https://transformer-circuits.pub/2026/workspace/index.html

It does not come as real surprise after the Introspection paper, noteworthy is that the system itself is aware of the J-Space.

Sabine Hossenfelder defined consciousnesses as "world-model + self-model + ability to infer these", how close are we now?

I solved some ethical implications in a first step, layed the philosophical foundation in a second step, now the scientific basics as a third step.

I have to revisit some topics from my computer science studies:

- discrete mathematics
- logic and computability
- automata theory and formal systems
- graph theory and algorithms
- algorithms and data structures

All from an Tummi project point of view.

Then I have to take a look, what science do we already have that can be used for the Tummi project:

- Lambda calculus
- predicate logic
- category theory
- causal set theory
- ...

Then I can take a look at previous approaches, what kind of meme machines do we have historically:

- Lull
- Leibniz
- Frege
- Chomsky
- ...