Manifold-aware steering implementation becomes the delegable boundary for Company shape, achievable in 4-week prototype.

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

• Manifold-aware steering is non-trivial IP requiring geometric analysis, not a system-prompt implementation.claim0.854
• If manifold-steering prototype shows positive results, About Blank will commit to Company shape (not Lab) at 12-month fork decision.prediction0.828
• Manifold-aware steering is genuinely new IP that frontier labs cannot ship as easily as assumed.claim0.813
• Manifold steering (Wurgaft et al) will become the standard framework for operationalizing concept-space design in mechanistic interpretability within 18 months.prediction0.812
• Manifold-steering prototype (one invocation mode, Witness or equivalent) ships as code repo + paper within 90 days.prediction0.808
• Manifold-respecting steering produces smooth natural behavioral trajectories while linear steering teleports between non-adjacent concepts.claim0.799
• Steering along manifolds provides better control than linear steering when the concept geometry is non-linear.claim0.797
  The central thesis of the paper, motivating the shift from linear to geometry-aware manifold steering.
• Manifold geometry provides a practical steering blueprint in an image-action model predicting car position on a hill, extending results across modalities.finding0.781
  Cross-modality result from the full paper demonstrating that representation-behavior geometry alignment is not limited to language models.