Why are humans typically “aligned”?
Our upbringing is full of diverse social experiences and creative expression and play.
RESEARCH
Other Projects
Open research into machine learning, from neural architecture search to program synthesis.
EvoDNN
Evolve Neural Network
Vectorial performs advanced machine learning (ML) research on automated discovery of new AI algorithms.
We are developing an evolutionary-algorithm framework that automatically evolves deep neural network architectures and hyperparameters. Neural networks are represented as directed acyclic graphs (DAGs), with a primary current research focus of evolving beyond vanilla transformers. The framework is domain-agnostic and also supports non-transformer architectures and non-neural-network evolutionary search. Automated evolution of neural network architectures avoids human researchers' algorithmic biases and preferences for simplistic architectures.
LLMOSES
Large Language Meta Optimizing Semantic Evolutionary Search
Vectorial performs research on emergent capabilities of LLMs and other leading intelligence models.
We are developing LLMOSES, which pairs AI agents with MOSES, an evolutionary algorithm that writes small programs to uncover patterns in data. Instead of exploring at random, LLMOSES utilizes an AI agent to watch MOSES's progress and suggest which directions look most promising, guiding the search toward better solutions faster than the original algorithm alone. It works through a lightweight layer that watches MOSES as it runs, passes that progress to the AI for guidance, and feeds the suggestions back in, all without changing MOSES's underlying code. The goal of this research is to evaluate AI agents' abilities to improve search and optimization algorithms like MOSES.