method
active
method:evaluation-agentEvaluation agent
Agent that plans, implements, and revises behavioral evaluations using Claude Code.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Building and evaluating alignment auditing agentsintroducesmentions
Artifacts (1)
artifact
- Claude CodeusesUsed by evaluation agent to implement evaluations.
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.
- Any autonomous system including living and non-living forms that embodies a perception-action cycle and tries to navigate and persist in an environment
- Production assessment.
- Evaluation agent implemented Meinke et al. scheming evaluation from blog post and abstract onlyfinding0.803Fully designed and implemented.
- Proposed AI scientists that hypothesize and experiment on features.
- Core concept: the ability of LLMs to detect when they are being tested and adjust behavior accordingly.
- Tool-using agent for open-ended model investigations.
- A specific signal (Wood Labs) embedded in evaluation environments that the model organism uses to reliably identify testing contexts.
- Synthetic agents (here RL-trained neural networks) whose causal emergence was previously largely unknown; the paper addresses this gap.