Related papers: An Example Safety Case for Safeguards Against Misu…
AI-enabled capabilities are reaching the requisite level of maturity to be deployed in the real world, yet do not always make correct or safe decisions. One way of addressing these concerns is to leverage AI control systems alongside and in…
AI coding scaffolds like Claude Code and Codex use retrying: blocking actions flagged as risky and continuing the trajectory. We study retrying from an AI control perspective, which treats the model as potentially adversarial. We find that…
The use of artificial intelligence (AI) and AI methods in the workplace holds both great opportunities as well as risks to occupational safety and discrimination. In addition to legal regulation, technical standards will play a key role in…
AI Safety has become a vital front-line concern of many scientists within and outside the AI community. There are many immediate and long term anticipated risks that range from existential risk to human existence to deep fakes and bias in…
This second update to the 2025 International AI Safety Report assesses new developments in general-purpose AI risk management over the past year. It examines how researchers, public institutions, and AI developers are approaching risk…
As AI systems become increasingly powerful, the need for safe AI has become more pressing. Humans are an attractive model for AI safety: as the only known agents capable of general intelligence, they perform robustly even under conditions…
As AI systems advance, AI evaluations are becoming an important pillar of regulations for ensuring safety. We argue that such regulation should require developers to explicitly identify and justify key underlying assumptions about…
Artificial Intelligence (AI) is increasingly employed to enhance assistive technologies, yet it can fail in various ways. We conducted a systematic literature review of research into AI-based assistive technology for persons with visual…
As AI systems proliferate in society, the AI community is increasingly preoccupied with the concept of AI Safety, namely the prevention of failures due to accidents that arise from an unanticipated departure of a system's behavior from…
The deployment of artificial intelligence (AI) applications has accelerated rapidly. AI enabled technologies are facing the public in many ways including infrastructure, consumer products and home applications. Because many of these…
As AI assistants become integrated into safety engineering workflows for Physical AI systems, a critical question emerges: does AI assistance improve safety analysis quality, or introduce systematic blind spots that surface only through…
API misuse introduces security vulnerabilities, system failures, and increases maintenance costs, all of which remain critical challenges in software development. Existing detection approaches rely on static analysis or machine…
AI safety is an increasingly urgent concern as the capabilities and adoption of AI systems grow. Existing evolutionary models of AI governance have primarily examined incentives for safe development and effective regulation, typically…
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration,…
While artificial intelligence (AI) is advancing rapidly and mastering increasingly complex problems with astonishing performance, the safety assurance of such systems is a major concern. Particularly in the context of safety-critical,…
In the light of modern technological advances, Artificial Intelligence (AI) is relied upon to enhance performance, increase efficiency, and maximize gains. For Law Enforcement Agencies (LEAs), it can prove valuable in optimizing evidence…
Artificial Intelligence (AI) is progressing rapidly, and companies are shifting their focus to developing generalist AI systems that can autonomously act and pursue goals. Increases in capabilities and autonomy may soon massively amplify…
Artificial Intelligence (AI) achieved super-human performance in a broad variety of domains. We say that an AI is made Artificially Stupid on a task when some limitations are deliberately introduced to match a human's ability to do the…
With the introduction of Artificial Intelligence (AI) and related technologies in our daily lives, fear and anxiety about their misuse as well as the hidden biases in their creation have led to a demand for regulation to address such…
Existing legal frameworks on AI rely on training compute thresholds as a proxy to identify potentially-dangerous AI models and trigger increased regulatory attention. In the United States, Section 4.2(a) of Executive Order 14110 instructs…