Search Results for author:
Found 5 papers, 0 papers with code
The Hydra Effect: Emergent Self-repair in Language Model Computations
We investigate the internal structure of language model computations using causal analysis and demonstrate two motifs: (1) a form of adaptive computation where ablations of one attention layer of a language model cause another layer to compensate (which we term the Hydra effect) and (2) a counterbalancing function of late MLP layers that act to downregulate the maximum-likelihood token.
Power-seeking can be probable and predictive for trained agents
Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited.
Neural Design of Contests and All-Pay Auctions using Multi-Agent Simulation
In contrast to auctions designed manually by economists, our method searches the possible design space using a simulation of the multi-agent learning process, and can thus handle settings where a game-theoretic equilibrium analysis is not tractable.
Guidelines for Artificial Intelligence Containment
With almost daily improvements in capabilities of artificial intelligence it is more important than ever to develop safety software for use by the AI research community.
The AGI Containment Problem
There is considerable uncertainty about what properties, capabilities and motivations future AGIs will have.
