Sam Altman

First, it is vital that AI companies–especially those working on the most powerful models–adhere to an appropriate set of safety requirements, including internal and external testing prior to release and publication of evaluation results. source Verified

People need to have agency, the ability to influence this. They need, we need to sort of jointly be architects of the future. source Unverified

OpenAI is not a normal company and never will be. Our mission is to ensure that artificial general intelligence (AGI) benefits all of humanity. When we started OpenAI, we did not have a detailed sense for how we were going to accomplish our mission. We now see a way for AGI to directly empower everyone as the most capable tool in human history. If we can do this, we believe people will build incredible things for each other and continue to drive society and quality of life forward. [...] We believe this is the best path forward—AGI should enable all of humanity to benefit each other. It is time for us to evolve our structure. [...] We want to deliver beneficial AGI. (2025) source Unverified

We talk about the IAEA as a model where the world has said 'OK, very dangerous technology, let's all put some guard rails.' (2023) source Unverified