How Easy Is It to Steal Unreleased AI Code?

Leopold Aschenbrenner says stealing important unreleased AI code is extremely easy. DeepMind does not claim that taking the code is hard. DeepMind laid out security levels from zero to four. Level four is the level resistant to state actors, and DeepMind says the lab is at level zero.

A recent indictment described a man who stole a bunch of really important AI code and went to China with it. Leopold Aschenbrenner says the man only had to copy the code into Apple Notes and export it as a PDF, and the export got past monitoring. He says Google probably has the best security of any of the AI labs because of the Google infrastructure. He says he does not know the precise picture, and he still compares the protection to the security of a startup.

Dwarkesh Patel asked how easy it would be for an actor to steal the unreleased RL work, not the public material about Scarlett Johansson's voice. Leopold Aschenbrenner answers that the theft is extremely easy, and he points to stealing the algorithms and stealing the weights.