AI Intelligence Archive

Todo, In Progress, Ready for QA, Done. The columns were right. The management underneath them wasn't.

Foremerge records what each coding agent plans to change before it edits anything, and raises a...

A familiar argument is making the rounds in web development: if an AI agent writes most of the code,...

The change I'm proudest of from this contest brought Track A's board memory down from 22.69 MB to...

Every team using an AI coding agent eventually builds a private collection of “the good...

Run a Local LLM with Ollama from C# and ASP.NET Core Run a local LLM with Ollama and...

Shopify’s Shop MCP gives AI agents a new way to search product data, build carts and complete Shop...

It was late at night. I was staring at a glowing terminal in Termux on my $150 Android phone. I had...

A physiotherapy clinic with four therapists and two treatment rooms discovered the problem at 10:04...

A few months ago, BOOTH was just a small idea I wanted to explore. I wasn't sure whether it would...

Building intelligent applications around sensitive information creates a fundamental engineering...

A document is not a passive object once a language model reads it. Anything printed, hidden or...

A failing test first, the smallest diff, and each project's AI policy respected: the workflow behind my merged open-source PRs.

I don't read most of the pull requests my AI writes anymore. I read the title, the description,...

Most "AI fixes your issues" demos are a session: you run a CLI, it edits files, you look at the diff....

A complete engineering blueprint for running autonomous agent evaluation in CI/CD: tiered test runners, statistical regression gates, token budgets, and GitHub Actions orchestration.

This paper reviews control architectures for building heating, ventilation and air-conditioning (HVAC) systems, addressing the tension among energy demand, occupant comfort and equipment operability, and situating proportional-integral-der…

The problem: 30 minutes per application, 400 times a day On paper, broker back-office work...

Battery degradation remains a central challenge in the development and broad application of sustainable energy technologies. Accurate degradation prediction is challenging, as battery aging emerges from complex and heterogeneous interactio…

Part 4 of a series on a self-modifying multi-agent LLM system. Report and data:...

An inspectable technical breakdown of 10 open-source robotics and physical AI GitHub repositories solving training-free 3D occupancy, targetless calibration, 50Hz VLA latency, and humanoid memory.

LLM post-training via reinforcement learning has shown consistent improvements in accuracy at the cost of reducing behavioral coverage - a phenomenon known as sharpening that can stall progress on difficult tasks. Repeated sampling objecti…

Procedural modeling offers compact, editable, and reusable representations for architectural content, but building such models still depends heavily on manually authored grammars. We study image-based procedural building reconstruction fro…

Scaling depth is a key route to stronger large language models, but Pre-LN architectures often suffer from depth-wise information dilution, limiting the effective use of deep layers. While cross-layer connectivity has proven effective at m…

This weekend I had the opportunity to work with v0, Claude Projects, Claude Code, agent skills,...

Discord is expanding the web visibility of its Discoverable Servers through public Server Web Pages...

On-policy distillation (OPD) mitigates the student's exposure bias by optimizing on student-generated trajectories. However, student-generated prefixes may contain reasoning errors or follow patterns unfamiliar to the teacher, undermining …

Despite recent advances in CUAs, their development remains constrained by the limited diversity, controllability, and reliability of interaction data. Moreover, conventional optimization pipelines lack iterative feedback, while existing re…

Assessing regulatory compliance for high-risk AI systems requires systematic identification of technical gaps such as missing controls, in- adequate processes, or shallow evaluation of practices. Compliance officers typically admin- ister …

The Log That Told Everyone the Password: Redacting Secrets in n8n Execution Logs I found...

Unit tests and eval sets don't catch the failures that end up in front of a regulator. Here's a 30-scenario red-team harness you can run against your live bot tonight.

Active-learning Kriging often replaces candidate pools by continuous metaheuristic search. A pre-specified comparison sharing surrogate, population and stopping rule isolated this inner optimizer: five budget-matched continuous optimizers,…

Large language models (LLMs) are driving autonomous agents toward real-world environments, with the Web emerging as one of the most representative interaction scenarios. However, training Web agents with naive exploration remains challengi…

Large language models (LLMs) have introduced a generative approach to recommendation, producing item lists from textual representations of user histories and item information. However, this generative setting raises challenges concerning o…

If you grew up in Nigeria, there is one sentence that can stop your heart in the middle of...

Accurate preoperative prediction of lung adenocarcinoma invasiveness is important for surgical planning and individualized treatment. However, overlapping CT appearances make it challenging to distinguish invasive adenocarcinoma (IAD) from…

Hey everyone 👋, This post is a little different from everything else I have written on this blog....

I've been building a small tool that turns one technical post into an X thread, a LinkedIn post, a...

We classify real and complex state-space models (SSMs) with linear transitions, distinguishing fixed-basis diagonal equivalence from input-output equivalence and tracking coefficient-conditioning windows under coordinate changes. We charac…

An experimental agent can succeed for the wrong reasons. Evaluations, however, often focus on the outcome, not the experiments, evidence, and inferences that produced it. We introduce LUCA, a configurable synthetic world for evaluating thi…