Micah Carroll
@MicahCarroll
Agreed that this is true locally. But I find it quite plausible that even best-effort safety mitigations will not be sufficient in the medium term to keep the current pace of releases – we'll see soon enough
Joshua Saxe@joshua_saxe · Aug 8There's clearly a massive alignment research overhang, and security sandboxing knowledge/tools overhang, just waiting to be slurped up by AI labs, AI application engineers, and AI-forward enterprises, which would make AI 1000x more alignment-safe with no new research. Those
Open quoted post → 5 49