This episode is not yet released.
do-llms-make-ethical-choices | episodes



Do LLMs Make Ethical Choices

We are excited to be joined by Josh Albrecht, the CTO of Imbue. Imbue is a research company whose mission is to create AI agents that are more robust, safer, and easier to use. He joins us to share findings of his work; Despite "super-human" performance, current LLMs are unsuited for decisions about ethics and safety.

Josh started by discussing how the ethics of LLMs can be evaluated. He gave some questions from the ETHICS dataset that was used to prompt the language model. He also shared how the model compared to humans. He mentioned the possibilities of the model receiving adversarial inputs and its impact.

Josh discussed how training data can enhance a model's ethical behavior. He discussed the outlook of LLMs in the future. He also highlighted essential considerations before LLMs are adopted across the board. Josh discussed other means to evaluate LLM aside from accuracy.

Learn more about the conversation in this space on Imbue’s Perspective page or listen to the Generally Intelligent podcast.

Follow Josh on Twitter @joshalbrecht.

Josh Albrecht

I co-founded Imbue. Our mission is to create human-like intelligence and make it safely accessible in order to foster a more abundant, unconstrained, and equitable society. I also invest in other founders via my fund, Outset Capital. I love meeting like-minded founders, scientists, and others who are passionate about discovering, creating, and building a better world.