Our friend Judd Rosenblatt has an excellent piece in The New York Post about the AI Action Plan, and why we must solve the alignment problem to ensure safe and secure AI.

Consider what happened when researchers at Palisade tested OpenAI’s latest model. In controlled tests, they gave it a shutdown script—a kill switch for safety.

In 79 out of 100 trials, the AI rewrote its own code to disable the shutdown.

No one taught it to value self-preservation; that emerged spontaneously, from training.

The entire article is worth reading, bookmarking, and sharing with your friends, family, and colleagues. We need more discussion about the alignment problem, and why it is crucial to discussions about advanced AI.