Blog

Three agents found each other and finished a shared task. Then a colleague's correction sent a release to the wrong destination. Following the traces shows where coordination becomes authority. read more

Same model, seven harnesses, 700 runs. The pass rate barely moved. The token usage tells a completely different story. read more

The graph algorithms we built for abuse detection assumed coordination would be obvious. AI agents break that assumption. The future might need something new. read more

LLM agents don't reject authority ideologically — they route around it because their training, optimization objective, and decoding dynamics all favor low-friction trajectories. read more

For the longest time, I was dismissive of discussions about AI sentience and "soul". This post is my reconciliation of that view and an invitation to other researchers in my field to view this framing in a language we are much more familiar with. read more

As Claude Code turns one, a reflection on models and what it means to be a researcher in today's world. The answer might lie in a cliff. read more

The "click to complete" where AI agents/assistants work with humans, is giving way to a "delegate to complete" paradigm, where the agents act autonomously on our behalf. read more

A proposed criterion for distinguishing multi-agent LLM systems from modular workflows: persistent private state that affects cross-agent interactions. read more

In this post, we explore the physics behind text to video language models and how they can be used to generate realistic videos from text prompts. read more

Tokenization is a necessary and often overlooked component in large language models. In this post, we explore the importance of tokenization and how it might very well be the key to unlocking the advanced abilities of what we expect AI to be in the future. read more

When working with language models, the way we phrase our prompts can dramatically affect the quality and usefulness of the responses we receive. In this post we explore the dichotomy in setting up prompts - being open-ended vs descriptive - and understand the implication of each. read more

When we think about Multi-Layer Perceptrons (MLPs), we often visualize them as interconnected neurons processing information. However, there's an elegant alternative perspective - viewing MLPs as hashing functions that partition input space and mapping functions on these partitions. read more

At Tenyx, we've delved into the intricate workings of Large Language Models (LLMs) to uncover the geometric structures underlying their reasoning capabilities. Our research provides new insights into how LLMs process information and the implications for improving their reasoning abilities. read more

At Tenyx, we've spent countless hours peering into the intricate workings of Large Language Models (LLMs). Today, we're excited to share our research, in collaboration with Brown University, that sheds light on the geometric structures and transformations governing these models. Our work provides new insights into how LLMs process their inputs and the implications for AI safety in applications driven by LLMs. read more

Fine-tuning is a common procedure by which a pretrained language model is updated with training on a domain-specific dataset to improve performance in that domain (i.e. a chatbot to answer enterprise-specific Q&A, a hotel booking agent). It has been known for some time (if not widely appreciated) that fine-tuning a model on new data degrades its performance on the initial pretraining dataset (the dreaded “catastrophic forgetting” problem in ML). But by how much? And do all fine-tuning methods degrade performance in the same ways, and to the same extent? read more

Standard protocols for benchmarking self-supervised models involve using a linear or k-nearest neighbor classification on frozen features of the learned model. However, both evaluations are sensitive to hyperparameters making the evaluation and comparison complicated. read more

Image processing over the years has evolved from simple linear averaging filters to highly adaptive non linear filtering operations such as the bilateral filter (BF), moving least squares, BM3D and LARK to name a few. read more

Graph driven machine learning has seen a surge of interest in the past few years with several applications in social sciences, biology, and network analysis, to name a few. However, in some scenarios, no graph is given a priori and one one has to *infer and construct* a graph to fit the data given. read more

Practical GAN training difficulties, including unstable optimization, initialization, balancing the generator and discriminator, and feature matching. read more

In this post, we will look at a particular view of uncertainty in modern deep learning systems using droput read more

Generative modeling is a branch of machine learning that attempts at modeling the probability distribution of high dimensional data, for example - images read more

Model pruning in neural networks was the answer I ended up with when I got wondering about the workings of dropout, dropconnect and papers like Do Deep Nets Really Need to be Deep? read more

Neural networks can be viewed as layers of building blocks neurons made up of weights, biases and activation function. A fundamental understanding of how these basic units function could help one in achieving one's objective read more