Because ablating the JSpace destroys a model's advanced multi-step reasoning and theory-of-mind capability, seeing nothing concerning in JSpace gives strong added confidence that a model isn't hiding sophisticated scheming elsewhere.
Nathan argues that since ablating JSpace collapses advanced reasoning and theory-of-mind, JSpace monitoring gives a meaningful new layer ("another nine") of confidence that a model isn't secretly executing elaborate deceptive plans. ✦ AI generated
Nathan · The Cognitive Revolution · 2026-07-07 · original ↗
starts at this moment · 21:48
It's maybe another nine, right? If we're in our defense and depth strategy for trying to make sure that we have a good level of control of what models are going to do. This gives you I think it feels like a full nine addition because you can now look at the space and say if I don't see it here that doesn't mean it's not represented in other places.
verbatim transcript · starts at 21:48
21:48it's it's maybe another nine, right? If we're if we're in our defense and depth uh strategy for trying to make sure that we have a good uh level of control of what models are going to do. This gives you I think a it feels like a full nine you know addition because you can now look at the space and say if I don't see it here that doesn't mean it's
22:11not represented in other places you know there and there are interesting details about what the model still can do when the JSpace is removed but you could be pretty confident I think based on these results that it's kind of it's not going to be able to hide really advanced elaborate plans ends somewhere else outside of this JSP because the the ablation of the Jspace just leaves causes such a performance degradation on
22:40these like hard multi-step uh type of tasks that if you don't see concepts in the JS you can be they might be represented elsewhere but they're they're seemingly at this point very unlikely to be represented in a way that allows for very advanced planning, reasoning, scheming, deception, etc., etc. Um, theory of mind seems to be kind of located in the JSpace as well. The model's ability to
23:12>> kind of report on its own >> experience, quote unquote, whatever that may mean, and also its its ability to describe what other people are thinking seems to be very much lost when you ablate the JSpace. So again, it's like you have to have theory if you're going to be deceptive, right? If you're going to try to do some sort of um takeover attempt or you know, whatever,
23:38right? The the the extreme things that people are worried about, this is not going to be these these things are not going to be easy for the model to do. They're going to require a lot of planning and they're going to require sophisticated theory of mind. So if you have the ability to kind of localize, okay, this is where the model really does its sophisticated theory of mind
- ·Ablating JSpace destroys multi-step reasoning ability
- ·Also collapses theory-of-mind capability
- ·Sophisticated scheming likely requires both capacities
- ·Part of a defense-in-depth control strategy
- ·Clean JSpace signal adds a full nine of confidence
- ·Caveat: absence there doesn't rule out other locations