“…we do that through this chain of thought and reasoning and traces… term… serial depth opacity… make sure we can actually still see what the model is thinking”

“There are these things called chain of thought… it’s a way of monitoring the systems… if you’re monitoring, they would have stopped it.”

“The agreement encourages companies to implement robust internal controls to monitor the capabilities of AI models. It's voluntary, at least for now.”

“Implement access logging, least-privileged principles, and monitoring for unusual queries against HR systems.”

“Plug it into a foundation model and see what the foundation model thinks about what happened and then go back”