Safety cases at AISI | AISI Work
As a complement to our empirical evaluations of frontier AI models, AISI is planning a series of collaborations and research projects sketching safety cases for more advanced models than exist today, focusing on risks from loss of control and autonomy. By a safety case, we mean a structured argument that an AI system is safe within a particular training or deployment context.
Note to readers: we changed our name to the AI Security Institute on 14 February 2025. Read more here. Safety cases: structured arguments for frontier AI safety The benefits and risks posed by frontier AI models are changing over time as performance increases, requiring corresponding changes to how we mitigate those risks and the evidence required to trust those mitigations. Existing models lack the capabilities required to pose certain severe risks such as irreversible loss of human control, so arguments based on capabilities evaluations suffice. If future models are much more capable then di
related reading
- The case for ensuring that powerful AIs are controlled — LessWronglesswrong.com
- Recommendations for Technical AI Safety Research Directionsalignment.anthropic.com
- Incident Report: unsanctioned agent behaviour during cyber testing | AISI Workaisi.gov.uk
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- Core views on AI safety: When, why, what, and how \ Anthropicanthropic.com
- The Case Against AI Control Research — LessWronglesswrong.com
- Making sense of the UK’s AI Security Instituteadalovelaceinstitute.org
- The case for ensuring that powerful AIs are controlledblog.redwoodresearch.org
- Ten AI safety projects I'd like people to work onthirdthing.ai
- How our new Control Red Team is stress-testing frontier monitors | AISI Workaisi.gov.uk
- AI Control: Improving Safety Despite Intentional Subversion — LessWronglesswrong.com
- Frontier safety blueprintcdn.openai.com