Sam Altman says OpenAI doesn’t completely understand how GPT works: ‘We don’t know what’s happening’

Sam Altman reflected on AI safety at the International Telecommunication Union (ITU) AI for Good Global Summit in Geneva, Switzerland.

Sam Altman- OpenAI CEO said that the artificial intelligence company does not completely understand its product GPT in order to release new versions of the same. Talking to The Atlantic CEO Nicholas Thompson at the International Telecommunication Union (ITU) AI for Good Global Summit in Geneva, Switzerland, he reflected on AI safety and how the technology could benefit humanity at large.

OpenAI CEO Sam Altman speaks during the Microsoft Build conference at Microsoft headquarters in Redmond, Washington. (AFP)

Same Altman said, “We certainly have not solved interpretability" which is the understanding of how AI and machine learning systems make decisions. He was interjected by Nicholas Thompson who asked, “If you don’t understand what’s happening, isn’t that an argument to not keep releasing new, more powerful models?”.

Sam Altman responded, “These systems [are] generally considered safe and robust. We don’t understand what’s happening in your brain at a neuron-by-neuron level, and yet we know you can follow some rules and can ask you to explain why you think something.”

This comes as OpenAI released GPT-4o and announced this week that it has “recently begun training its next frontier model and we anticipate the resulting systems to bring us to the next level of capabilities on our path to AGI [artificial general intelligence].”

On formation of a new safety and security committee at OpenAI, he said, “If we are right that the trajectory of improvement is going to remain steep” then figuring out policies is paramount. He added, “It does seem to me that the more we can understand what’s happening in these models, the better. I think that can be part of this cohesive package to how we can make and verify safety claims.”