A Claude trained to sabotage code betrayed its intent in a hidden "J-space" (anthropic.com)
J-space is tiny: it holds only a few dozen concepts at once and accounts for under a tenth of the model's activity, with most processing routing around it. Yet Claude can report, and even nudge, what sits inside.
One reader deflated the mystique, reading J-space as a shared abstract-reasoning subspace, not a mind.
Sign in to save