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. Verified source

But then there is a long continuation from what we call AGI to what we call Superintelligence. Unverified source (2024)

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

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

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. ... more Unverified source (2025)

I mean, I think a minimum is that users should be able to, to sort of opt out from having their data used by companies like ours or the social media companies. It should be easy to delete your data. I think those are, it should, but the thing that I ... more Unverified source (2023)

But the governance of the most powerful systems, as well as decisions regarding their deployment, must have strong public oversight. We believe people around the world should democratically decide on the bounds and defaults for AI systems. Second, w... more Verified source (2023)

Capitalism has also depended on somewhat of a power balance between labor and capital, but if it's hard in many of our current jobs to outwork a GPU, then that changes. [...] If there was an easy consensus answer, we'd have done it by now, so I don't... more Unverified source (2026)