If you read the statement, they explicitly state these guardrails don't exist today, and they want to develop them.
Though I have a feeling we're talking about different things. In Claude Code terms, it might want to rm -rf my codebase. You sound like you might want it to never run rm -rf. Anthropic probably wants to catch dangerous commands and send them to humans to approve, like it does today.
alt Hacker News
If you read the statement, they explicitly state these guardrails don't exist today, and they want to develop them.
Though I have a feeling we're talking about different things. In Claude Code terms, it might want to rm -rf my codebase. You sound like you might want it to never run rm -rf. Anthropic probably wants to catch dangerous commands and send them to humans to approve, like it does today.