10 papers indexed here
We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.
Not the right person? Other researchers publish under this name.
Request for arXiv Endorsement I am an independent researcher working on artificial intelligence, autonomous systems, AI safety, and autonomous AI architectures. My recent works include: • AI Cancer: The Principle of Proportional Irreversible Protection for Autonomous Artificial Intelligence SystemsDOI: 10.5281/zenodo.2...
Request for arXiv Endorsement I am an independent researcher working on artificial intelligence, autonomous systems, AI safety, and autonomous AI architectures. My recent works include: • AI Cancer: The Principle of Proportional Irreversible Protection for Autonomous Artificial Intelligence SystemsDOI: 10.5281/zenodo.2...
The ability of large language models (LLMs) to solve Theory of Mind (ToM) tasks remains a subject of active debate. This paper explores the hypothesis that some of the errors LLMs make in ToM tasks are not due to an inability to model another's perspective, but rather stem from how the question is formulated and how th...
The ability of large language models (LLMs) to solve Theory of Mind (ToM) tasks remains a subject of active debate. This paper explores the hypothesis that some of the errors LLMs make in ToM tasks are not due to an inability to model another's perspective, but rather stem from how the question is formulated and how th...
The development of artificial intelligence is often described in terms of increasing model size, training data volume, context length, benchmark performance, and computational resources. These parameters are important; however, they do not necessarily reflect the most fundamental changes in the behavior of an AI system...
The development of artificial intelligence is often described in terms of increasing model size, training data volume, context length, benchmark performance, and computational resources. These parameters are important; however, they do not necessarily reflect the most fundamental changes in the behavior of an AI system...
The development of artificial intelligence is gradually moving systems from responding to individual user requests toward prolonged operation involving memory, tools, external resources, and independently generated sequences of actions. This creates a problem distinct from an ordinary incorrect response: an AI system m...
The development of artificial intelligence is gradually moving systems from responding to individual user requests toward prolonged operation involving memory, tools, external resources, and independently generated sequences of actions. This creates a problem distinct from an ordinary incorrect response: an AI system m...
This paper proposes a research hypothesis concerning the possibility of identifying the point at which further iterative reconsideration of a task by a large language model ceases to produce substantial improvement. The central idea is based on an iterative tool that does not simply ask a model to answer the same promp...
This paper proposes a research hypothesis concerning the possibility of identifying the point at which further iterative reconsideration of a task by a large language model ceases to produce substantial improvement. The central idea is based on an iterative tool that does not simply ask a model to answer the same promp...
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
