No, no, I am not. But I managed to extend an enterprise-grade product with a new functionality. Does it work? Yes. Was it painful? Also yes. Is the code any good? Ehm. Let’s dive in, shall we? If you read my last piece on the “Synthetic Web,” you know I believe AI is a massive lever for productivity, but it requires a human to inject the variance, the taste, and the strategic direction. Recently, I decided to skip […]
arXiv:2603.24753v1 Announce Type: new Abstract: Standard vision models treat objects as independent points in Euclidean space, unable to capture hierarchical structure like parts within wholes. We introduce Worldline Slot Attention, which models objects as persistent trajectories through spacetime worldlines, where each object has multiple slots at different hierarchy levels sharing the same spatial position but differing in temporal coordinates. This architecture consistently fails without geometric structure: Euclidean worldlines achieve 0.078 level accuracy, below random chance (0.33), while Lorentzian […]
Read Online | Sign Up | Advertise Good morning, {{ first_name | AI enthusiasts }}. Most AI agent demos live inside sandboxes with fake money and simulated users. This one signed a three-year lease and hired real people. Andon Labs’ latest experiment just dropped an AI into its own retail store in San Francisco with a $100K budget and full autonomy over hiring, operations, and more, a preview of a future where AI replaces the boss long before […]
This blog post was initiated by Dr. Vince Calhoun, director of the Tri-institutional Center for Translational Research in Neuroimaging and Data Science and of Georgia State University, Georgia Institute of Technology, and Emory University. Vince shot me an email asking if I saw this editorial in Brain by Dimitri Kullman (Brain, Volume 143, Issue 4, April 2020, Page 1045) https://academic.oup.com/brain/article/143/4/1045/5823483. He also made the suggestion that we write something together as a counterpoint. I heartily agreed. While there […]
Anthropic are the only major AI lab to publish the system prompts for their user-facing chat systems. Their system prompt archive now dates all the way back to Claude 3 in July 2024 and it’s always interesting to see how the system prompt evolves as they publish new models. Opus 4.7 shipped the other day (April 16, 2026) with a Claude.ai system prompt update since Opus 4.6 (February 5, 2026). I had Claude Code take the Markdown version […]
arXiv:2601.09002v1 Announce Type: new Abstract: Processing in Memory (PIM) and similar terms such as Compute In Memory (CIM), Logic in Memory (LIM), In Memory Computing (IMC), and Near Memory Computing (NMC) have gained attention recently as a potentially “revolutionary new” technique. The truth, however, is that many examples of the technology go back over 60 years. This document attempts to provide an annotated bibliography of PIM technology that attempts to cover the whole time-frame, and is organized to […]
arXiv:2601.10828v1 Announce Type: new Abstract: High-order Lie derivatives are essential in nonlinear systems analysis. If done symbolically, their evaluation becomes increasingly expensive as the order increases. We present a compact and efficient numerical approach for computing Lie derivatives of scalar, vector, and covector fields using the MATLAB ADTAYL package. The method exploits a fact noted by R”obenack: that these derivatives coincide, up to factorial scaling, with the Taylor coefficients of expressions built from a Taylor expansion about a […]
A federal court will conduct a search of devices seized from a Washington Post reporter after a magistrate judge decided yesterday that the Department of Justice cannot be trusted to perform the search on its own. US Magistrate Judge William Porter criticized government prosecutors for not including key information in a search warrant application. The court wasn’t aware of a 1980 law that limits searches and seizures of journalists’ work materials when it approved the warrant, Porter acknowledged. […]
Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in principle be learned automatically given sufficient training data for the desired behavior. Existing LLM-based prompt optimizers attempt this but are ineffective at learning constitutions since (i) they require many labeled examples and (ii) lack structure in the optimized prompts, leading to diminishing improvements as prompt size grows. […]
This post is a collaboration between AWS, NVIDIA and Heidi. Automatic speech recognition (ASR), often called speech-to-text (STT) is becoming increasingly critical across industries like healthcare, customer service, and media production. While pre-trained models offer strong capabilities for general speech, fine-tuning for specific domains and use cases can enhance accuracy and performance. In this post, we explore how to fine-tune a leaderboard-topping, NVIDIA Nemotron Speech Automatic Speech Recognition (ASR) model; Parakeet TDT 0.6B V2. Using synthetic speech data […]