Related papers: Intent-Driven Computing: A Computational Model for…
Language models now provide an interface to express and often solve general problems in natural language, yet their ultimate computational capabilities remain a major topic of scientific debate. Unlike a formal computer, a language model is…
The actual (classical) Brain-Computer Interface attempts to use brain signals to drive suitable actuators performing the actions corresponding to subject's intention. However this goal is not fully reached, and when BCI works, it does only…
In this paper we propose a use-case-driven iterative design methodology for normative frameworks, also called virtual institutions, which are used to govern open systems. Our computational model represents the normative framework as a logic…
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…
The hypothesis that direct human intention can modulate the concurrent outcomes of a stochastic process has been under test for over 35 years, surrounded by inconclusive evidence and a great amount of ambiguity. An increased interest has…
The aim of this paper is to propose an alternative behavioural definition of computation (and of a computer) based simply on whether a system is capable of reacting to the environment-the input-as reflected in a measure of programmability.…
Large language models are able to perform a task by conditioning on a few input-output demonstrations - a paradigm known as in-context learning. We show that language models can explicitly infer an underlying task from a few demonstrations…
Large language models (LLMs) exhibit strong generative capabilities and have shown great potential in code generation. Existing chain-of-thought (CoT) prompting methods enhance model reasoning by eliciting intermediate steps, but suffer…
Speech-acts can have literal meaning as well as pragmatic meaning, but these both involve consequences typically intended by a speaker. Speech-acts can also have unintentional meaning, in which what is conveyed goes above and beyond what…
Instruction-tuned Language Models (ILMs) have become essential components of modern AI systems, demonstrating exceptional versatility across natural language and reasoning tasks. Among their most impactful applications is code generation,…
Intent-Based Networking (IBN) presents a paradigm shift for network management, by promising to align intents and business objectives with network operations--in an automated manner. However, its practical realization is challenging: 1)…
The growing capabilities of Large Language Models (LLMs) have led to their widespread adoption for function completion within code repositories. Recent studies on such tasks show promising results when explicit instructions, often in the…
Classical results in computability theory, notably Rice's theorem, focus on the extensional content of programs, namely, on the partial recursive functions that programs compute. Later and more recent work investigated intensional…
Large language models (LLMs) are rapidly emerging in Artificial Intelligence (AI) applications, especially in the fields of natural language processing and generative AI. Not limited to text generation applications, these models inherently…
Computer programming initially required humans to directly translate their goals into machine code. These goals could have easily been expressed as a written (or human) language directive. Computers, however, had no capacity to…
We systematically evaluate the quality of widely used adversarial safety datasets from two perspectives: in isolation and in practice. In isolation, we examine how well these datasets reflect real-world adversarial attacks based on three…
In this work, we use the communication of intent as a means to facilitate cooperation between autonomous vehicle agents. Generally speaking, intents can be any reliable information about its future behavior that a vehicle communicates with…
This paper constructively proves the existence of an effective procedure generating a computable (total) function that is not contained in any given effectively enumerable set of such functions. The proof implies the existence of machines…
For machine agents to successfully interact with humans in real-world settings, they will need to develop an understanding of human mental life. Intuitive psychology, the ability to reason about hidden mental variables that drive observable…
Constraint programming can definitely be seen as a model-driven paradigm. The users write programs for modeling problems. These programs are mapped to executable models to calculate the solutions. This paper focuses on efficient model…