Research / Sources
Research on governing advanced AI and its risks. www.governance.ai
Argues that current AI incident reporting regimes miss serious safety incidents, such as rogue agent breaches, and proposes changes so incidents are reported, independently investigated, and their lessons shared across industry.
Proposes agent-permissions.json, a robots.txt-style manifest letting websites specify allowed LLM web-agent interactions, to enable compliant agent access while respecting site owners' preferences.
Proposes a systems-safety framework for analysing AI agent incidents, identifying system, contextual and cognitive causal factors, and recommending what incident reports and developer logs should contain.
Proposes assessing AI agent autonomy by scoring orchestration code for impact and oversight, avoiding costly run-time evaluations, and demonstrates it on the AutoGen framework.
Proposes agent infrastructure, external technical systems and shared protocols that attribute agent actions to accountable parties, shape agent interactions, and detect and remedy harmful actions.
Assesses agent identifiers, real-time monitoring and activity logging as ways to increase visibility into AI agents, analysing their governance value, implementation trade-offs and privacy and power-concentration implications.