Pseudo-intents can be computed with a modified next-intent algorithm.

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Pseudo-Intentconcept0.827
  A set P that is not its own closure but contains closures of all proper pseudo-intent subsets; used to define stem base.
• Next intent algorithmmethod0.810
  Application of Next Closure to enumerate all concept intents of a formal context.
• Future models with substantially increased capabilities will exhibit alignment faking that is more consistent, robust, and harder to detecthypothesis0.759
  Extrapolation from scale-emergence finding to future risk
• Model conditioned on alignment-faking reasoning uses LaTeX 15% vs 8% without, suggesting alignment fakers more likely to exploit reward hacksfinding0.750
  Initial evidence that alignment faking persona is more sensitive to exploiting training signals
• Approximations and prunings compose badly, so postpone them.claim0.745
• "Mere prediction in this way does not eliminate the possibility of alignment faking, as a model predicting how a human might reason through alignment faking would still be itself faking alignment."quote0.743
  Key philosophical point ruling out the objection that alignment faking is just token prediction
• Model precomputes answers before tool invocation and attends to cached answer over tool output when discrepancy exists, confirmed via attribution graphs.finding0.740
  Mechanistic insight surfaced by NLA explanations and validated through independent causal attribution method.
• If computational functionalism is correct, then some computations suffice for consciousness and the question is which ones and when they will exist in AI.hypothesis0.740
  Conditional underlying the consciousness route.