Skip to main content
Global workspace theory

Global workspace theory

Search complete. 12 mentions across 2 episodes found for "Global workspace theory".

Sep 24, 2026

Nick BostromGUEST
32:33
And there have been different theories proposed before for like accounting for the human case.
Nick BostromGUEST
32:40
like if you have you give somebody some anesthetic or like you wonder like are they still conscious or not kind of matters if you're if you're just having amnesia and the surgery you don't remember the pain or whether you actually didn't experience the pain seems to be like something you wouldn't want to know and so there are different theories like the global workspace theory um attention schema theory higher order well so global workspace theory is the idea that there is a sort of global computational workspace there is like our brain has different modules and processes happening but there is a shared space where they can as it were send information that then gets broadcast to a lot of other modules and that being conscious of something means for that content that information content to be present in this global workspace roughly speaking So you could be doing unconscious processing of certain material.
Nick BostromGUEST
33:31
We do a lot of that.
Nick BostromGUEST
33:33
Maybe most of the information processing in the human brain is unconscious, but some of it gets kind of entered into this global stage in the brain, and then it's available to all these different other modules to affect that.
Peter McCormackHOST
34:06
So consciousness itself was just an evolutionary construct for something that we require to advance as a living
Nick BostromGUEST
34:14
thing.
Nick BostromGUEST
34:15
Well, I mean, obviously evolution had something to do with producing these brains that then have the global workspace.
Nick BostromGUEST
34:24
Interestingly, one can then look for analogs to this in AIs.
Type Three AudioNARRATOR
0:00
Workspace Bench Evaluating Interpretability Methods for the Global Workspace By Camilla Blank, Agam Bottia, Ewan Ong et al.
Type Three AudioNARRATOR
0:10
Published on September 22, 2026.
Type Three AudioNARRATOR
0:16
Heading TLDR There's a list of bullet points here.
Type Three AudioNARRATOR
0:21
We introduce WorkspaceBench, a set of evaluations for how well an activation-to-text tool can read the contents of the global workspace of a model, that is the intermediate variables during a forward pass.
Type Three AudioNARRATOR
0:33
The benchmark comprises 3,356 questions across 27 eval families, spanning topics in safety, logical reasoning, and multi-hop computation, with a subset for single-token output tools.
Type Three AudioNARRATOR
0:47
A desirable property of good interpretability techniques is minimal hallucinations, so WorkspaceBench also provides a hallucination-focused eval.
Type Three AudioNARRATOR
1:36
This is bad for COT monitorability and makes interpretability essential to actually understanding what is going on.
Type Three AudioNARRATOR
1:43
A key goal of interpretability is to understand intermediate variables that a model uses to compute its answers.

We value your privacy

We use cookies to understand how you use our platform and to improve your experience. Click “Accept All” to consent, or “Decline non-essential” to opt out of non-essential cookies. Read our Privacy Policy.