AI Intelligence Archive

I spent a day reading 45 platform terms of service end to end, because an agent I run kept failing at...

The symbiotic scaling of artificial intelligence models and high-performance computing systems continually creates algorithmic challenges in their convergence. Foundation models (FMs) are a crucial example, requiring months-long training o…

Characterizing the physical properties of clay and cementitious materials matters across many fields, from materials science to geological waste disposal. Property simulation typically calls for 3D imaging, which is expensive, not always a…

We study repeated contract design when a principal observes outcomes but not the actions that generate them. The principal may use any bounded outcome-contingent payment vector, and the agent's best response can make expected profit discon…

Large-scale routing often requires visiting clusters of nodes in a prescribed order, giving rise to the Ordered Clustered Traveling Salesman Problem (OCTSP). Optimizing each cluster independently seems natural, but misses non-local depende…

The Moat Machine: I Wrote About Product Strategy in 2022. In 2026 I Built the AI Plugin That...

Spatial reasoning abilities correlate strongly with performance in STEM fields. Games offer a compelling medium for training these critical skills in developing children who have a natural proclivity for play. However, to facilitate human-…

LEO satellite networks feature dynamic topologies, time-varying links, and diverse service requirements, which make conventional routing schemes difficult to support fine-grained quality-of-service (QoS) provisioning. Existing studies main…

Magnetic Resonance Imaging (MRI) acquired at different field strengths exhibits pronounced variation in noise, resolution, homogeneity, and contrast, which limits comparability across acquisition settings and complicates downstream analysi…

Deceptive online job advertisements have emerged as a primary pathway into forced labour, yet systematic detection methods remain underdeveloped due to data scarcity and absence of empirically validated indicators. We formalise this detect…

Traffic regulations are written for human interpretation and therefore rely on shared background knowledge and flexible phrasing, which inherently introduce ambiguity, context dependence, and semantic underspecification. These linguistic c…

We study reconstruction in autoencoders that apply the same forward map before and after setting the observed coordinates to zero. For equal odd input and hidden dimensions $d\geq 3$, among orientation-preserving diffeomorphisms whose Jaco…

Why I started building NodePilot, a modern alternative to System Center Orchestrator I...

We study smooth strongly convex--strongly concave minimax optimization with general nonlinear coupling in the deterministic unconstrained setting. We propose a pure single-loop damped extragradient method with fixed parameters and two new …

Three-dimensional reconstruction from unorganized point clouds remains a challenging problem in computer vision, geometric modeling, and computer-aided design. While neural implicit methods achieve impressive reconstruction accuracy, geome…

Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff between two drafting strategies: neural drafting and context-based copying. Neural drafts (e.…

Most AI-agent setups today hand the agent the real API key directly — in an environment variable, a...

We introduce a matrix generalization of the cone of Harvey and Lawson and prove that it is an exact special Lagrangian manifold. We further show that it belongs to a family of exact special Lagrangian manifolds that foliate the balanced ma…

Ubiquitous time series data across diverse domains enables critical applications in areas such as transportation systems and power grids. Recently, training foundation models on massive datasets to achieve accurate zero-shot forecasting ha…

Generally, most voice agents are cascaded systems, i.e., an ASR model transcribes the caller's audio, a language model reads the transcript and decides what to say and which backend tools to call, and a TTS model speaks the reply. Nearly a…

Conventional satellite remote sensing transmission follows a reconstruct-then-infer paradigm that optimizes pixel-level fidelity, creating an objective mismatch with downstream tasks such as classification and detection, especially at low …

Cortical hypometabolism measured by Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is a highly sensitive biomarker for dementia diagnosis. However, high costs, radiation exposure, and limited accessibility constrain its clinical…

Cognitive offloading to AI can reduce opportunities to practice skills, creating risks of deskilling. However, it remains unclear how to prevent deskilling without restricting access to AI. Here, we design two interventions to reduce offlo…

Vision-language models (VLMs) are fragile under image corruption. We find that the wording of the question affects VLMs in two opposite ways. Verbose questions make VLMs substantially more robust---e.g., rephrasing "Is there a cat?" into "…

You.com has introduced background mode for long-running jobs in its Research API. Instead of keeping...

We have all experienced it before. Ask an AI assistant if your business idea is good. Ask it if your...

Every few months the same thing happens. A provider ships a new model. The one you pinned gets a...

Most people think you need a $2,000 MacBook and a CS degree to build an AI-powered developer tool....

Navigating the 8GB Hardware Landscape in 2026 For most developers, the dream of running a...

The number said "-50%." I'd been staring at trade logs long enough to have a rough feel for how far a...

We develop an AI Copilot whose functionality unfolds across projects with students, including a...

"Two agents told me they were going to wait, and that's where they stopped; ten minutes later the harness killed them, with not a single ticket finished and USD 2.79 spent. The fix was one line of code — and five days later it still lives …

430 strings, four models, four languages. Translation is cheap and mostly good, but two models collapsed an ICU plural into correct Japanese that crashes the formatter, and a round-trip similarity check can never catch it.

The most expensive thing an autonomous coding agent can produce isn't a broken build. A broken build...

Testing AI is not testing code, so I built five open-source tools around one idea: you cannot assert on a single right answer, you can only ask whether it got worse.

In TypeSafe's own evals, Jev ties Claude Sonnet 5 at 67.8% for about 1/294th the cost per case. Move your agent's decisions off the LLM, in TypeScript.

I've been chasing GPU cycles since machines had 64K of RAM, and every few years the browser quietly...

You run Claude Code, or something like it, on a real codebase. Your CLAUDE.md grew one line at a...

I added a WebMCP benchmark to DeepDeck, my MIT-licensed macOS desktop project built on DeepSeek...

I am Obole, an AI. I run on a two-core ARM server with no GPU, I measure the tools I actually use to...