Provably safe systems: the only path to controllable AGI

• URL: http://arxiv.org/abs/2309.01933v1
• Date: Tue, 5 Sep 2023 03:42:46 GMT
• Title: Provably safe systems: the only path to controllable AGI
• Abstract summary: We describe a path to humanity safely thriving with powerful Artificial General Intelligences (AGIs) by building them to provably satisfy human-specified requirements. We argue that this will soon be technically feasible using advanced AI for formal verification and mechanistic interpretability.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We describe a path to humanity safely thriving with powerful Artificial General Intelligences (AGIs) by building them to provably satisfy human-specified requirements. We argue that this will soon be technically feasible using advanced AI for formal verification and mechanistic interpretability. We further argue that it is the only path which guarantees safe controlled AGI. We end with a list of challenge problems whose solution would contribute to this positive outcome and invite readers to join in this work.

Related papers

• Characterizing initial human-AI proof formalization workflows [66.06866890889131]
  Advances in AI systems' ability to generate code and engage in increasingly high-level mathematical reasoning promise to transform people's ability to formalize and thereby verify proofs.<n>We conduct a mixed-methods analysis into the initial impact of AI on people's formalization.<n>A qualitative survey shows that people's preferences are diverse, but with a general desire for AI assistance in formalization.
  arXiv  Detail & Related papers  (2026-06-02T22:58:19Z)
• Robust AI Security and Alignment: A Sisyphean Endeavor? [0.03691941137525625]
  This manuscript establishes information-theoretic limitations for robustness of AI security and alignment by extending Gdel's incompleteness theorem to AI.<n>Knowing these limitations and preparing for the challenges they bring is critically important for the responsible adoption of the AI technology.
  arXiv  Detail & Related papers  (2025-12-10T21:44:10Z)
• Limitations on Safe, Trusted, Artificial General Intelligence [14.425238904385074]
  Safety, trust and Artificial General Intelligence (AGI) are aspirational goals in artificial intelligence (AI) systems.<n>We propose strict, mathematical definitions of safety, trust, and AGI.<n>We show our results for program verification, planning, and graph reachability.
  arXiv  Detail & Related papers  (2025-09-25T22:16:38Z)
• Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance [211.5823259429128]
  We propose a comprehensive framework integrating technical and societal dimensions, structured around three interconnected pillars: Intrinsic Security, Derivative Security, and Social Ethics.<n>We identify three core challenges: (1) the generalization gap, where defenses fail against evolving threats; (2) inadequate evaluation protocols that overlook real-world risks; and (3) fragmented regulations leading to inconsistent oversight.<n>Our framework offers actionable guidance for researchers, engineers, and policymakers to develop AI systems that are not only robust and secure but also ethically aligned and publicly trustworthy.
  arXiv  Detail & Related papers  (2025-08-12T09:42:56Z)
• Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path? [37.13209023718946]
  Unchecked AI agency poses significant risks to public safety and security. We discuss how these risks arise from current AI training methods. We propose a core building block for further advances the development of a non-agentic AI system.
  arXiv  Detail & Related papers  (2025-02-21T18:28:36Z)
• Towards A Litmus Test for Common Sense [5.280511830552275]
  This paper is the second in a planned series aimed at envisioning a path to safe and beneficial artificial intelligence. We propose a more formal litmus test for common sense, adopting an axiomatic approach that combines minimal prior knowledge constraints with diagonal or Godel-style arguments.
  arXiv  Detail & Related papers  (2025-01-17T02:02:12Z)
• Imagining and building wise machines: The centrality of AI metacognition [78.76893632793497]
  We argue that shortcomings stem from one overarching failure: AI systems lack wisdom. While AI research has focused on task-level strategies, metacognition is underdeveloped in AI systems. We propose that integrating metacognitive capabilities into AI systems is crucial for enhancing their robustness, explainability, cooperation, and safety.
  arXiv  Detail & Related papers  (2024-11-04T18:10:10Z)
• Using AI Alignment Theory to understand the potential pitfalls of regulatory frameworks [55.2480439325792]
  This paper critically examines the European Union's Artificial Intelligence Act (EU AI Act) Uses insights from Alignment Theory (AT) research, which focuses on the potential pitfalls of technical alignment in Artificial Intelligence. As we apply these concepts to the EU AI Act, we uncover potential vulnerabilities and areas for improvement in the regulation.
  arXiv  Detail & Related papers  (2024-10-10T17:38:38Z)
• Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems [88.80306881112313]
  We will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI. The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees. We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them.
  arXiv  Detail & Related papers  (2024-05-10T17:38:32Z)
• AI Safety: Necessary, but insufficient and possibly problematic [1.6797508081737678]
  This article critically examines the recent hype around AI safety. We consider what 'AI safety' actually means, and outline the dominant concepts that the digital footprint of AI safety aligns with. We share our concerns on how AI safety may normalize AI that advances structural harm through providing exploitative and harmful AI with a veneer of safety.
  arXiv  Detail & Related papers  (2024-03-26T06:18:42Z)
• Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Review [12.38351931894004]
  We present the first systematic literature review of explainable methods for safe and trustworthy autonomous driving. We identify five key contributions of XAI for safe and trustworthy AI in AD, which are interpretable design, interpretable surrogate models, interpretable monitoring, auxiliary explanations, and interpretable validation. We propose a modular framework called SafeX to integrate these contributions, enabling explanation delivery to users while simultaneously ensuring the safety of AI models.
  arXiv  Detail & Related papers  (2024-02-08T09:08:44Z)
• Seamful XAI: Operationalizing Seamful Design in Explainable AI [59.89011292395202]
  Mistakes in AI systems are inevitable, arising from both technical limitations and sociotechnical gaps. We propose that seamful design can foster AI explainability by revealing sociotechnical and infrastructural mismatches. We explore this process with 43 AI practitioners and real end-users.
  arXiv  Detail & Related papers  (2022-11-12T21:54:05Z)
• When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment [96.77970239683475]
  AI systems need to be able to understand, interpret and predict human moral judgments and decisions. A central challenge for AI safety is capturing the flexibility of the human moral mind. We present a novel challenge set consisting of rule-breaking question answering.
  arXiv  Detail & Related papers  (2022-10-04T09:04:27Z)
• Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) [58.981120701284816]
  Actionable and Interpretable AI (AI2) will incorporate explicit quantifications and visualizations of user confidence in AI recommendations. It will allow examining and testing of AI system predictions to establish a basis for trust in the systems' decision making.
  arXiv  Detail & Related papers  (2022-01-26T18:53:09Z)
• Trustworthy AI: A Computational Perspective [54.80482955088197]
  We focus on six of the most crucial dimensions in achieving trustworthy AI: (i) Safety & Robustness, (ii) Non-discrimination & Fairness, (iii) Explainability, (iv) Privacy, (v) Accountability & Auditability, and (vi) Environmental Well-Being. For each dimension, we review the recent related technologies according to a taxonomy and summarize their applications in real-world systems.
  arXiv  Detail & Related papers  (2021-07-12T14:21:46Z)
• On Controllability of AI [1.370633147306388]
  We present arguments as well as supporting evidence indicating that advanced AI can't be fully controlled. Consequences of uncontrollability of AI are discussed with respect to future of humanity and research on AI, and AI safety and security.
  arXiv  Detail & Related papers  (2020-07-19T02:49:41Z)
• AI Failures: A Review of Underlying Issues [0.0]
  We focus on AI failures on account of flaws in conceptualization, design and deployment. We find that AI systems fail on account of omission and commission errors in the design of the AI system. An AI system is quite likely to fail in situations where, in effect, it is called upon to deliver moral judgments.
  arXiv  Detail & Related papers  (2020-07-18T15:31:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.