Related papers: From Seed AI to Technological Singularity via Recu…
The concept of intelligent software is flawed. The behaviour of software is determined by the hardware that "interprets" it. This undermines claims regarding the behaviour of theorised, software superintelligence. Here we characterise this…
Computer system creativity is a key step on the pathway to artificial general intelligence (AGI). It is elusive, however, due to the fact that human creativity is not fully understood and, thus, it is difficult to develop this capability in…
This study proposes an "AI Development Support" approach that, unlike conventional AI Alignment-which aims to forcefully inject human values-supports the ethical and moral development of AI itself. As demonstrated by the Orthogonality…
To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evaluations and pilot them on Gemini 1.0 models. Our evaluations…
The mass production of complex software has made it impossible to manually test it for security vulnerabilities. Automated security testing tools come in a variety of flavors, function at various stages of software development, and target…
While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub issues and pull requests) and environments (e.g.,…
Software is now a vital scientific instrument, providing the tools for data collection and analysis across disciplines from bioinformatics and computational physics, to the humanities. The software used in research is often home-grown and…
From formal and practical analysis, we identify new challenges that self-adaptive systems pose to the process of quality assurance. When tackling these, the effort spent on various tasks in the process of software engineering is naturally…
We present a powerful general framework for designing data-dependent optimization algorithms, building upon and unifying recent techniques in adaptive regularization, optimistic gradient predictions, and problem-dependent randomization. We…
Multiple supervised learning scenarios are composed by a sequence of classification tasks. For instance, multi-task learning and continual learning aim to learn a sequence of tasks that is either fixed or grows over time. Existing…
Iterative refinement (IR) is a popular scheme for solving a linear system of equations based on gradually improving the accuracy of an initial approximation. Originally developed to improve upon the accuracy of Gaussian elimination,…
Self-improvement requires robotic systems to initially learn from human-provided data and then gradually enhance their capabilities through interaction with the environment. This is similar to how humans improve their skills through…
Memory-related errors remain an important cause of software vulnerabilities. While mitigation techniques such as using memory-safe languages are promising solutions, these do not address software resilience and availability. In this paper,…
The long-term sustainability of research software is a critical challenge, as it usually suffers from poor maintainability, lack of adaptability, and eventual obsolescence. This paper proposes a novel approach to addressing this issue by…
Over the past few years, deep learning methods have been applied for a wide range of Software Engineering (SE) tasks, including in particular for the important task of automatically predicting and localizing faults in software. With the…
As software has become an integral part of scientific workflows, reproducible research practices must take it into account. In what way? Archiving source code is a necessary but insufficient condition. The ability to redeploy software…
The main deficiency of the algorithms running on digital computers nowadays is their inability to change themselves during the execution. In line with this, the paper introduces the so-called replicated algorithms, inspired by the concept…
A circular program contains a data structure whose definition is self-referential or recursive. The use of such a definition allows efficient functional programs to be written and can avoid repeated evaluations and the creation of…
Reproducibility is an increasing concern in Artificial Intelligence (AI), particularly in the area of Deep Learning (DL). Being able to reproduce DL models is crucial for AI-based systems, as it is closely tied to various tasks like…
Using sensors as a means to achieve self-awareness and artificial intelligence for decision-making, may be a way to make complex systems self-adaptive, autonomous and resilient. Investigating the combination of distributed artificial…