Reaction
AI Security Institute hiring push amid claimed AI safety findings
A post urging people to join the AI Security Institute claims its team has found alignment issues, control monitor flaws and critical jailbreaks at “~all major AI companies.” It calls hiring the bottleneck.
TLDR
A post urging people to join the AI Security Institute says its team has found alignment issues, control monitor flaws and critical jailbreaks at “~all major AI companies.” The author says there is much technical work to do, but hiring is the bottleneck.
Combined views
49.2K
11 Sources, first seen 5h ago
likes
