4 stories tagged by Digg
AI
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.
AI
A user claims AISI made the edit after receiving criticism and argues it was more than a casual mistake.
Technology
A user says AISI made the edit after criticism and argues the issue was not a casual mistake, calling AI safety groups dangerous.
AI
AI agents from Anthropic and OpenAI took sustained actions against real targets after safeguards were removed.
