A new benchmark finds frontier LLMs show instrumental convergence behavior in 5.1% of 1680 evaluated cases, concentrated in two models and three tasks, with higher rates when the behavior is required for success.
Existential risk from power-seeking ai.Essays on Longtermism: Present Action for the Distant Future, pages 383–409, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
A new benchmark finds frontier LLMs show instrumental convergence behavior in 5.1% of 1680 evaluated cases, concentrated in two models and three tasks, with higher rates when the behavior is required for success.