Manifold steering (Wurgaft et al) will become the standard framework for operationalizing concept-space design in mechanistic interpretability within 18 months.

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

• SAE-based mechanistic interpretability will be superseded by manifold-based analysis for understanding semantic concepts within 24 months.prediction0.828
• Manifold-aware steering implementation becomes the delegable boundary for Company shape, achievable in 4-week prototype.prediction0.812
• Manifold-steering prototype (one invocation mode, Witness or equivalent) ships as code repo + paper within 90 days.prediction0.799
• manifold geometry principles extend to months, letters, ages, and in-context learning tasks across modalitiesfinding0.796
  Evidence that the weekday cyclic structure is not anomalous but reflects broader principle of concept geometry.
• Manifold-aware steering is non-trivial IP requiring geometric analysis, not a system-prompt implementation.claim0.796
• If manifold-steering prototype shows positive results, About Blank will commit to Company shape (not Lab) at 12-month fork decision.prediction0.792
• Manifold geometry provides a practical blueprint for steering model behavior across diverse tasks and modalities.hypothesis0.785
  The generalizing predictive claim that manifold steering is a broadly applicable framework beyond the days-of-week case study.
• Manifold geometry provides a practical steering blueprint in an image-action model predicting car position on a hill, extending results across modalities.finding0.769
  Cross-modality result from the full paper demonstrating that representation-behavior geometry alignment is not limited to language models.