Philip Feldman
YOU?
Author Swipe
Organizational Lobotomy Open
An AI program exploits human vulnerability to destroy a firm from the top down.
You've Changed: Detecting Modification of Black-Box Large Language Models Open
Large Language Models (LLMs) are often provided as a service via an API, making it challenging for developers to detect changes in their behavior. We present an approach to monitor LLMs for changes by comparing the distributions of linguis…
Can Generative AI be Egalitarian? Open
The recent explosion of "foundation" generative AI models has been built upon the extensive extraction of value from online sources, often without corresponding reciprocation. This pattern mirrors and intensifies the extractive practices o…
Contextual Feature Drift in Large Language Models: An Examination of Adaptive Retention Across Sequential Inputs Open
Advancements in artificial intelligence have led to models capable of generating highly coherent language, yet limitations in retaining contextual alignment across extended inputs remain challenging. Contextual Feature Drift (CFD) emerges …
The Voice: Lessons on Trustworthy Conversational Agents from 'Dune' Open
The potential for untrustworthy conversational agents presents a significant\nthreat for covert social manipulation. Taking inspiration from Frank Herbert's\n"Dune", where the Bene Gesserit Sisterhood uses the Voice for influence,\nmanipul…
Killer Apps: Low-Speed, Large-Scale AI Weapons Open
The accelerating advancements in Artificial Intelligence (AI) and Machine Learning (ML), highlighted by the development of cutting-edge Generative Pre-trained Transformer (GPT) models by organizations such as OpenAI, Meta, and Anthropic, p…
Trapping LLM Hallucinations Using Tagged Context Prompts Open
Recent advances in large language models (LLMs), such as ChatGPT, have led to highly sophisticated conversation agents. However, these models suffer from "hallucinations," where the model generates false or fabricated information. Addressi…
Down the Rabbit Hole: Detecting Online Extremism, Radicalisation, and Politicised Hate Speech Open
Social media is a modern person's digital voice to project and engage with new ideas and mobilise communities $\unicode{x2013}$ a power shared with extremists. Given the societal risks of unvetted content-moderating algorithms for Extremis…
The Keyword Explorer Suite: A Toolkit for Understanding Online Populations Open
We have developed a set of Python applications that use large language models to identify and analyze data from social media platforms relevant to a population of interest. Our pipeline begins with using OpenAI's GPT-3 to generate potentia…
Polling Latent Opinions: A Method for Computational Sociolinguistics Using Transformer Language Models Open
Text analysis of social media for sentiment, topic analysis, and other analysis depends initially on the selection of keywords and phrases that will be used to create the research corpora. However, keywords that researchers choose may occu…
Ethics, Rules of Engagement, and AI: Neural Narrative Mapping Using Large Transformer Language Models Open
The problem of determining if a military unit has correctly understood an order and is properly executing on it is one that has bedeviled military planners throughout history. The advent of advanced language models such as OpenAI's GPT-ser…
Analyzing COVID-19 Tweets with Transformer-based Language Models Open
This paper describes a method for using Transformer-based Language Models (TLMs) to understand public opinion from social media posts. In this approach, we train a set of GPT models on several COVID-19 tweet corpora that reflect population…
Guest Editorial Diversification in Urban Transportation Systems and Beyond: Integrating People and Goods for the Future of Mobility Open
The increasing growing need for optimization of transportation in a sustainable and green environment is fundamental for the future of mobility. Companies, governments, and non-governmental institutions are trying to find new ways to contr…
Training robust anomaly detection using ML-Enhanced simulations Open
This paper describes the use of neural networks to enhance simulations for subsequent training of anomaly-detection systems. Simulations can provide edge conditions for anomaly detection which may be sparse or non-existent in real-world da…
Navigating Human Language Models with Synthetic Agents Open
Modern natural language models such as the GPT-2/GPT-3 contain tremendous amounts of information about human belief in a consistently testable form. If these models could be shown to accurately reflect the underlying beliefs of the human b…
Navigating Language Models with Synthetic Agents Open
Modern natural language models such as the GPT-2/GPT-3 contain tremendous amounts of information about human belief in a consistently interrogatable form. If these models could be shown to accurately reflect the underlying beliefs of the h…
View article: #COVID-19 Misinformation: Saudi Arabia as a Use Case
#COVID-19 Misinformation: Saudi Arabia as a Use Case Open
In this research, we aim to gain deep insights into information behavior when discussing epidemics on Twitter. We are more specifically interested in identifying misinformation spread regarding epidemics around the world and in particular,…
Belief places and spaces: Mapping cognitive environments Open
Beliefs are not facts, but they are factive - they feel like facts. This property is what can make misinformation dangerous. Being able to deliberately navigate through a landscape of often conflicting factive statements is difficult when …
Integrating Artificial Intelligence into Weapon Systems Open
The integration of Artificial Intelligence (AI) into weapon systems is one of the most consequential tactical and strategic decisions in the history of warfare. Current AI development is a remarkable combination of accelerating capability,…
Dungeons for Science: Mapping Belief Places and Spaces Open
Tabletop fantasy role-playing games (TFRPGs) have existed in offline and online contexts for many decades, yet are rarely featured in scientific literature. This paper presents a case study where TFRPGs were used to generate and collect da…
Disrupting the coming robot stampedes: Designing resilient information ecologies Open
Machines are designed to communicate widely and efficiently. Humans, less so. We evolved social structures that function best as small subgroups interacting within larger populations. Technology changes this dynamic, by allowing all indivi…
Simon's Anthill: Mapping and Navigating Belief Spaces Open
In the parable of Simon's Ant, an ant follows a complex path along a beach on to reach its goal. The story shows how the interaction of simple rules and a complex environment result in complex behavior. But this relationship can be looked …