







All of the interesting systems (e.g. transportation, healthcare, power generation) are inherently and unavoidably hazardous by the own nature. The frequency of hazard exposure can sometimes be changed but the processes involved in the system are themselves intrinsically and irreducibly hazardous. It is the presence of these hazards that drives the creation of defenses against hazard that characterize these systems.
How Complex Systems Fail
All of the interesting systems (e.g. transportation, healthcare, power generation) are inherently and unavoidably hazardous by the own nature. The frequency of hazard exposure can sometimes be changed but the processes involved in the system are themselves intrinsically and irreducibly hazardous. It is the presence of these hazards that drives the creation of defenses against hazard that characterize these systems.

Important and complex systems may be more controllable than they appear
We don't often think of them in these terms, but our brains, global financial markets and groups of friends are all examples of different kinds of complex networks or systems. And unlike the kind of system ...

Why design systems are a single point of failure
Tools and techniques to prevent design system collapse

ver.ooo
Curious about systems — how they behave, how they fail, and what they get up to when nobody is steering.

What is AI poisoning? A computer scientist explains
Despite the hype surrounding AI, the technology is far more fragile than it might appear.

What is AI poisoning? A computer scientist explains
Despite the hype surrounding AI, the technology is far more fragile than it might appear.

Loss of control - Problem profile
Why do we think that reducing risks from AI is one of the most pressing issues of our time?

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.
.png)
Dynamical Systems Group | Complex Systems, Engineered
Systems engineering firm that operationalizes emerging technology for high-reliability organizations. Scientific Computing, MBSE, Systems Integration.

A Structured Approach to Safety Case Construction for AI Systems
Safety cases, structured arguments that a system is acceptably safe, are becoming central to the governance of AI systems. Yet, traditional safety-case practices from aviation or nuclear engineering rely on well-specified system boundaries, stable architectures, and known failure modes. Modern AI systems, such as generative and agentic AI, are the opposite. Their capabilities emerge unpredictably from low-level training objectives, their behaviour varies with prompts, and their risk profiles shift through fine-tuning, scaffolding, or deployment context. This study examines how safety cases are currently constructed for AI systems and why classical approaches fail to capture these dynamics. This study introduces comprehensive taxonomies for AI-specific claim types (assertion-based, constraint-based, capability-based), argument types (demonstrative, comparative, causal/explanatory, risk-based, and normative), and evidence families (empirical, mechanistic, comparative, expert-driven, formal methods, operational/field data, and model-based). It then proposes a reusable safety-case template, each of which follows a predefined structure of claims, arguments, and evidence tailored for AI systems. Each template is illustrated by end-to-end patterns that address distinctive challenges, such as evaluation without ground truth, dynamic model updates, and threshold-based risk decisions. The result is a systematic, composable, and reusable approach to constructing and maintaining safety cases that are credible, auditable, and adaptive to the evolving behaviour of generative and frontier AI systems.
Safety isn’t safety without a social model (or: dispelling the myth of per se technical safety) — AI Alignment Forum
As an AI researcher who wants to do technical work that helps humanity, there is a strong drive to find a research area that is definitely helpful so…

More Is Different for AI
Machine learning is touching increasingly many aspects of our society, and its effect will only continue to grow. Given this, I and many others care about risks from future ML systems and how to mitigate them. When thinking about safety risks from ML, there are two common approaches, which I'

Complexity Explorables
A collection of interactive explorable explanations of complex systems in biology, physics, mathematics, social sciences, epidemiology, ecology and other fields....

Safety Co-Option and Compromised National Security: The Self-Fulfilling Prophecy of Weakened AI Risk Thresholds
Risk thresholds provide a measure of the level of risk exposure that a society or individual is willing to withstand, ultimately shaping how we determine the safety of technological systems. Against the backdrop of the Cold War, the first risk analyses, such as those devised for nuclear systems, cemented societally accepted risk thresholds against which safety-critical and defense systems are now evaluated. But today, the appropriate risk tolerances for AI systems have yet to be agreed on by global governing efforts, despite the need for democratic deliberation regarding the acceptable levels of harm to human life. Absent such AI risk thresholds, AI technologists-primarily industry labs, as well as "AI safety" focused organizations-have instead advocated for risk tolerances skewed by a purported AI arms race and speculative "existential" risks, taking over the arbitration of risk determinations with life-or-death consequences, subverting democratic processes. In this paper, we demonstrate how such approaches have allowed AI technologists to engage in "safety revisionism," substituting traditional safety methods and terminology with ill-defined alternatives that vie for the accelerated adoption of military AI uses at the cost of lowered safety and security thresholds. We explore how the current trajectory for AI risk determination and evaluation for foundation model use within national security is poised for a race to the bottom, to the detriment of the US's national security interests. Safety-critical and defense systems must comply with assurance frameworks that are aligned with established risk thresholds, and foundation models are no exception. As such, development of evaluation frameworks for AI-based military systems must preserve the safety and security of US critical and defense infrastructure, and remain in alignment with international humanitarian law.

Why Crisis Resilience Depends on Epistemic Security
If we want to prevent tomorrow’s crises from spiraling out of control, we must recognize epistemic systems as critical infrastructure, writes Elizabeth Seger.
