Compute optimization using token reduction of LLM prompts is an emerging task in the fields of NLP and next generation, agentic AI. In this white paper, we introduce a novel (patent pending) text representation scheme and a first-of-its-kind word-level semantic compression of paragraphs that can lead to over 90% token reduction, while retaining high semantic similarity to the source text. We explain how this novel compression technique can be lossless and how the detail granularity is controllable. We discuss benchmark results over open source data (i.e. Bram Stoker's Dracula available through Project Gutenberg) and show how our results hold at the paragraph level, across multiple genres and models.

The landscape of low-energy effective field theories stemming from string theory is too vast for a systematic exploration. However, the meadows of the string landscape may be fertile ground for the application of machine learning techniques. Employing neural network learning may allow for inferring novel, undiscovered properties that consistent theories in the landscape should possess, or checking conjectural statements about alleged characteristics thereof. The aim of this work is to describe to what extent the string landscape can be explored with neural network-based learning. Our analysis is motivated by recent studies that show that the string landscape is characterized by finiteness properties, emerging from its underlying tame, o-minimal structures. Indeed, employing these results, we illustrate that any low-energy effective theory of string theory is endowed with certain statistical learnability properties. Consequently, several learning problems therein formulated, including interpolations and multi-class classification problems, can be concretely addressed with machine learning, delivering results with sufficiently high accuracy.

Machine learning techniques are increasingly powerful, leading to many breakthroughs in the natural sciences, but they are often stochastic, error-prone, and blackbox. How, then, should they be utilized in fields such as theoretical physics and pure mathematics that place a premium on rigor and understanding? In this Perspective we discuss techniques for obtaining rigor in the natural sciences with machine learning. Non-rigorous methods may lead to rigorous results via conjecture generation or verification by reinforcement learning. We survey applications of these techniques-for-rigor ranging from string theory to the smooth $4$d Poincar\'e conjecture in low-dimensional topology. One can also imagine building direct bridges between machine learning theory and either mathematics or theoretical physics. As examples, we describe a new approach to field theory motivated by neural network theory, and a theory of Riemannian metric flows induced by neural network gradient descent, which encompasses Perelman's formulation of the Ricci flow that was utilized to resolve the $3$d Poincar\'e conjecture.

Understanding the loss landscape is an important problem in machine learning. One key feature of the loss function, common to many neural network architectures, is the presence of exponentially many low lying local minima. Physical systems with similar energy landscapes may provide useful insights. In this work, we point out that black holes naturally give rise to such landscapes, owing to the existence of black hole entropy. For definiteness, we consider 1/8 BPS black holes in $\mathcal{N} = 8$ string theory. These provide an infinite family of potential landscapes arising in the microscopic descriptions of corresponding black holes. The counting of minima amounts to black hole microstate counting. Moreover, the exact numbers of the minima for these landscapes are a priori known from dualities in string theory. Some of the minima are connected by paths of low loss values, resembling mode connectivity. We estimate the number of runs needed to find all the solutions. Initial explorations suggest that Stochastic Gradient Descent can find a significant fraction of the minima.

In this case study, we explore the capabilities and limitations of ChatGPT, a natural language processing model developed by OpenAI, in the field of string theoretical swampland conjectures. We find that it is effective at paraphrasing and explaining concepts in a variety of styles, but not at genuinely connecting concepts. It will provide false information with full confidence and make up statements when necessary. However, its ingenious use of language can be fruitful for identifying analogies and describing visual representations of abstract concepts.

Abstract: We extend the notion of T-duality to manifolds endowed with non-principal torus actions. The singularities of the torus action are controlled by a certain Lie algebroid, called the elliptic tangent bundle. Using this Lie algebroid, we explain how certain invariant generalized complex structures can be transported via T-duality. Abstract: It is known that, in the static gauge, the world-volume and the transverse Kaluza-Klein (KK) reductions of the O-plane effective actions on a circle satisfy the T-duality constraint for arbitrary base space background. In this paper we show that due to the presence of the second fundamental form in the D-brane couplings at order α′ and higher, the T-duality is satisfied only for a subclass of couplings for arbitrary base space background.

Released in 1971, the Intel 4004 was the world's first microprocessor. I was ten years old and watched on TV as David Scott and James Irwin drove a car on the moon. It was the coolest thing I had ever seen, and I could not stop dreaming about what the future would bring. Technology has come a long way since then, and I believe we are now on the threshold of the next gigantic leap, thanks to quantum computers. This article takes an exploratory approach to what awaits us once quantum computers become commercially available. I compare our progress with history and what has been, where quantum computers are today, and onwards.

I am not a genius, have no inside information and don't have influential friends feeding me high-tech solutions to common problems. However, people wonder why I have huge social media followings, know what the next big thing is and have opportunities thrust upon me. The simple answer is I love watching for disruptive technologies and I follow trends--have done so for years. I think you must be on top of what is happening around you and gather intelligence on what technology can change the world and what technology is simple taking up space like marijuana. I've watched the marijuana "technologies" reaping incredible rewards from the few who got in at the early stages.

Your purchase helps support NPR programming. We've been talking to robots for a while now. In the decade or so since Siri and her compatriots first appeared, we've all gotten pretty used to having conversations with computers in various forms. While your Alexa doesn't look much like a Cylon (the scary metal kind or hotty flesh kind) now, it seems like it's just a matter of time of time before we'll be talking with all kinds of robots -- including those that look just like us. Time, robots and conversations are at the heart of David Ewing Duncan's new book Talking to Robots: Tales from Our Human-Robot Futures.

Is fundamental physics unified into a single theory governing all known phenomena, or are we forced to accept a fractured state of affairs where different phenomena are addressed by different theories? This question has long been of first importance to theoretical physicists. Einstein, for example, spent many of his later years in search for a unified theory, with little success. Despite his brilliance, the deck was stacked against him, as certain aspects of fundamental physics such as the strong and weak nuclear forces were only just being discovered at the end of his life. Today we have a more complete picture of the interactions of elementary particles and also a strong sense of what is difficult in the search for a unified theory: combining general relativity, Einstein's theory of gravity, with quantum mechanics.