Comment by David Krueger

AI companies' lack of progress towards credible AI Safety plans is scandalous. Even they are starting to get anxious as they race towards recursive self-improvement and face down the prospect of losing control. CEOs recent gestures towards coordinati...

Companies really don't release very much information at all about their systems, and there's no independent oversight that is mandated. We need programs for independent experts to be able to look at the details of the AI systems. That doesn't just in...

None of these approaches that you'll often hear mentioned—interpretability, testing or alignment—is technically adequate. We don't know how to build superintelligent AI safely. The plan is basically to roll the dice.