Tag
The article discusses trust boundaries in AI agent systems where an LLM plans an executable DAG of agents, highlighting challenges in validating plans and ensuring safety through human approval and per-agent permissions.
The author expresses skepticism about the 'Internet of Agents' idea, arguing that while interoperability standards have value, a cross-company rental market for AI agents is unlikely due to trust and control issues.
Block shared how it uses OpenAI’s AI capabilities to discover and fix software security risks—the tool goes beyond statically scanning code to reason about attack patterns, cross trust boundaries, and chain together multistep attacks, revealing complete, end-to-end compromise paths while helping pinpoint issues, identify owners, suggest patches, and verify that fixes are effective.