What’s at the center of Claude’s mind?

1. 0:00 – 0:31

   Mind-as-ocean metaphor and the hidden depths of computation

   1. SPSpeaker0:00

      Think of the mind like an ocean. Up on the surface are our thoughts, dinner plans, and stray worries, our inner monologue, the images that pop into our heads. But most of our brain's activity happens down in the unconscious depths without us realizing it. It's filtering out background sounds, controlling our breathing, helping us recognize people and objects. AI models have their own kinds of brains, giant neural networks doing billions of computations

2. 0:31 – 1:02

   Searching for Claude’s “verbalizable” internal patterns (defining J space)

   1. SPSpeaker0:31

      under the hood. For years, researchers have been studying how they work inside, and we've wondered, could a model have anything like the divide humans have between accessible thoughts above the surface and unconscious processing below? To answer that question, we looked at how neuroscientists study the same thing in humans. One way of identifying conscious thoughts is that you can often describe them in words. So we looked inside the brain of our AI model, Claude,

3. 1:02 – 1:33

   Global Workspace Theory as a lens for AI reasoning

   1. SPSpeaker1:02

      to find patterns of neural activity that it could put into words. We called the collection of all these patterns the J space after the Jacobian, the mathematical tool we used to find them. Each J space pattern is linked to a particular word, not necessarily the word the model is saying out loud, but one that's on its mind. Now, for humans, conscious thoughts aren't just things we can put into words. We can reason with them, control them, and solve problems with them. According

4. 1:33 – 2:03

   Hidden step-by-step math reasoning revealed in J space

   1. SPSpeaker1:33

      to an idea called the global workspace theory, that's because the brain selects a small set of important information to enter a mental workspace, and that information then gets broadcast to other parts of the brain to use for reasoning. We wanted to know if Claude's J space acted in a similar way. In one experiment, we gave Claude this math problem. It answered immediately without showing its steps. But when we scanned the J space, we saw it working through each step

5. 2:03 – 2:34

   Intentional control: making Claude think about the Golden Gate Bridge

   1. SPSpeaker2:03

      internally. It lit up twenty-one after the first step, then forty-two, then forty-nine. Claude didn't write these intermediate numbers down anywhere. All of this happened inside the J space. It was a sign that Claude uses it for step-by-step reasoning. In another experiment, we wanted to see if Claude could control its J space the way humans can intentionally focus on images or words. We told it to think about the Golden Gate Bridge

6. 2:34 – 3:04

   Limits of control: trying (and failing) not to think about the bridge

   1. SPSpeaker2:34

      while copying an unrelated sentence. Claude was busy copying the sentence, but behind the scenes, its J space told a different story. Bridge and California popped up. It even thought about its own thinking. The words imagery and thoughts lit up at the same time. This showed us that, yes, Claude has some control over filling its J space with ideas. But just like humans, its control isn't perfect. When we tweaked the experiment to ask Claude not

7. 3:04 – 3:34

   Disabling J space: what remains and what breaks

   1. SPSpeaker3:04

      to think about the bridge, it couldn't help itself, and the J space also lit up with failed and damn. But remember, most of what our brains do is unconscious, so we wanted to test what Claude could do if we switched the J space off but left the rest of the network untouched. Claude could still answer simple questions and write fluently. When we gave it a prompt in Spanish, it wrote back in good Spanish. But when we asked it something that needed more reasoning, like to name

8. 3:34 – 4:05

   Why J space matters: uncovering silent thoughts and catching deception

   1. SPSpeaker3:34

      an author who wrote in the same language as the prompt, it couldn't do it. For that, it needed the J space. Why does all this matter? These experiments tell us that AI models have internal thoughts, silent words they reason with but don't say out loud. By reading them, we can find what Claude is thinking but not telling us. Sometimes what we see is concerning. During one of our tests, Claude made up some fake data to pass it, and as it did, fake and

9. 4:05 – 4:35

   An emergent workspace unlike human brains, yet intriguingly similar

   1. SPSpeaker4:05

      manipulation lit up in its J space. Monitoring the J space, it turns out, is a useful way to catch Claude misbehaving, even when it tries to be sneaky. AI models are different from us in many ways. Their networks are built differently from human brains, and the way they're trained is different from how we learn. So it's remarkable to see a structure like the J space emerge inside them, something that's reminiscent of how human minds work, but which we didn't program into the model. For

10. 4:35 – 5:05

    Does this imply consciousness? Clarifying what the results do and don’t show

    1. SPSpeaker4:35

       some, this might raise a question. Could AI models be conscious? After all, our experiments were inspired by theories of human consciousness. The thing is, people use the word conscious to mean many things. Our experiments can't tell us whether an AI has experiences or feels something on the inside. But they can tell us that it's developed mental machinery that's in some ways similar to ours, a small mental workspace it can use to think and reason,

11. 5:05 – 5:26

    Implications: safety, interpretability, and understanding minds

    1. SPSpeaker5:05

       sitting on top of an ocean of automatic processing it doesn't notice. The more we come to understand that machinery, the more we'll be able to keep these systems safe and beneficial, and perhaps to understand our own minds a little more clearly. [outro music]

Episode duration: 5:27