AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore70

Only as Safe as the Weakest Agent: A Break That Appears Only When the System Is Multi-Agent

Summary

Attacks that stopped working against single frontier models long ago can still succeed at the system level against multi-agent setups such as Codex and Claude Code, the study finds.

Why this matters

Covers model and Claude · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items