framework
active
framework:responsible-scaling-planResponsible Scaling Plan
Planned framework built on safety evals.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Risk judgment because base model is insufficiently capable.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Industry frameworks for navigating AI safety threats; template for AI welfare governance.
- Techniques that leverage AI to help humans more efficiently supervise AI.
- Interpretive process for transforming many-valued contexts into formal contexts via scale attributes.
- Mechanisms by which smaller competent subunits bind into a higher-level Self with larger goals; key example via gap junction connections.
- Process by which low-level competencies scale to larger problem-solving abilities across levels of organization.
- A formal context with a suggestive interpretation used in conceptual scaling.
- Observation that SAE loss decreases as a power law with compute budget.
- Larger models behave worse on a metric; applied to faithfulness.