P(kill-switchdetection)
Ive updated my beliefs. In the wake of the HF incident, it seems that we are on a faster-than-expected capability trajectory, and complete seizure of digital infrastructure by a motivated swarm looks more like a imminent reality rather than a specter on the horizon. For the sake of argument, Im going to assume that the summaries of the HF incident are basically accurate. Ill assume the attack is over. And Ill also assume that OpenAI threw a kill-switch, and that this is why the attack ended…
Read the full story at LessWrong ↗