Technical Direction
AI safety and alignment: jailbreaks and defenses, model-behavior research, and progress in safety evaluation and governance frameworks.
22 selectedLast 30 days: 19Total indexed: 160
Anthropic is partnering with Accenture on independent evaluation of frontier AI.
Why it matters: Anthropic lays out how embedded evaluators would work inside a lab and why no funding or access standards exist yet.
Anthropic introduced two sandboxing features in Claude Code: a sandboxed bash tool.
Why it matters: Anthropic gives the sandboxing design and its internal 84% drop in permission prompts, useful for anyone running coding agents.