AI Intelligence Archive

Remember your first week at a tech company? You didn’t lack raw intelligence—you lacked context. You...

Why "just add more context" isn't a strategy — and what these four building blocks are...

Read on: the acceptance check that proved 1 = 1 · 繁體中文版 I assumed my content wasn't good enough....

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange How this was...

Coding agents write, refactor, and open pull requests at a pace humans can't match. The instinct is...

This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real...

I spent three weeks trying to fix a latency problem that didn't exist. Our multi-agent customer...

A model being intelligent does not make the agent trustworthy. Reasoning, planning, memory, tools,...

Originally published at AI Frontier Post. Every production LLM feature eventually hits the same...

Flash 0.5.5 turns a local-first terminal agent into something you can use from any screen in your house, without sending a single line of code to someone else's server.

https://github.com/567-labs/instructor/discussions/2706

Originally published on Medium. I maintain bcb-br-mcp, an open-source MCP server that gives AI...

By Andrew Pyle The first time I tried to run two coding agents at once on the same project, it went...

Astra killed Claude. Claude killed Gemini. Gemini killed Google. Google committed suicide, and...

An agent needs a boundary between proposing an action and taking it. I would put that boundary in...

An on-call agent that answers "no prior incidents" might be telling you the archive is empty. It...

Table of Contents The problem The architecture The Implementation Creating an...

Two checks in my build were green for months while testing nothing. One was switched off by a guard clause, the other by a missing space in a regex.

Coding agents such as Claude Code and Codex run with your shell and your credentials. Between October...

Learning transferable representations for dynamic text-attributed graphs (DyTAGs) requires models to capture underlying interaction dynamics that persist across domains. However, existing methods tend to overfit to domain-specific structur…

We propose sliced Orlicz-Wasserstein (SOW) distance which is a generalization of sliced Wasserstein (SW) distance. SOW replaces the $L^p$ norm in SW with a Luxemburg norm cost induced by an Orlicz function $φ$. First, we prove that SOW dis…

Multimodal contrastive learning is a dominant paradigm for learning transferable representations from unlabeled data, but standard objectives primarily capture information that is redundant between modalities. Partial Information Decomposi…

Accurate assessment of Schistosoma japonicum-associated liver fibrosis is essential for disease management and long-term follow-up in endemic regions. Ultrasound provides non-invasive imaging, but complex local echogenic patterns and anato…

Recommender systems rely heavily on heterogeneous behavioral feedback to infer user preference. Although abundant, these signals are imperfect measurements: the same observed behavior can arise from different underlying states, such as gen…

Predicting smooth dynamics and collisions requires modeling continuous evolution and abrupt state changes. We introduce HamiFormer, a dual-expert diffusion field combining whole-window denoising with residual-corrected Hamiltonian propagat…

Ultrasound (US) acquisition depends on the operator's ability to interpret anatomy and anticipate how the view will change with probe motion. Many robotic US navigation methods select actions without explicitly predicting these anatomical …

Radiomap blind prediction aims to infer radiomaps from observable representations of the propagation environment and base station configuration without field measurements. In practice, the observable representations are inherently incomple…

As AI agents are becoming widely adopted in the financial services industry, careful measurement is essential to understand where they can be reliably deployed and where oversight and professional review remain necessary. Such measurement,…

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...

A trained neural network can be represented by a parameter vector in high dimensions. Learning distributions over these vectors enables the generation of new models across various tasks and architectures. A central challenge is permutation…

Over-the-air computation has emerged as a scalable and efficient solution for deploying federated learning algorithms in wireless networks by exploiting waveform superposition for simultaneous model aggregation. Most existing work struggle…

Unified multimodal models combine understanding, generation, and editing within a single network, offering a promising foundation for versatile multimodal applications. However, growing multimodal contexts make KV cache storage and access …

Flow critics learn return distributions by transporting Gaussian noise to Bellman endpoints via continuous velocity fields. While velocity bootstrapping stabilizes training by querying a successor teacher, existing methods face a structura…

Several works have explored multi-agent reinforcement learning (MARL) in LLM collaboration. However, constructing reliable rewards is difficult in practice, as complete and accurate metrics are often unavailable and hard to aggregate. Pref…

A four-stage LLM pipeline gives up as much as 40.5 accuracy points at its own interfaces (gemma-3-12B on MATH-500, Holm-corrected p = 1.66e-19; the largest tax in the primary family). We hold model, problem, stages, stage prompts and compl…

Model merging efficiently combines specialized large language models (LLMs) without joint retraining, but can substantially alter expert routing in Mixture-of-Experts (MoE) models. Such \emph{routing drift} is often interpreted as routing …

This paper studies learning of shuffle ideals with membership queries as well as with contrastive queries---a form of membership query that reveals not only whether a selected word $w$ is in the target language or not, but also provides a …

Raising the update-to-data (UTD) ratio breaks off-policy critics in two ways grouped as "plasticity loss": collapsing representations and growing value magnitude $|Q|$. We separate them in Soft Actor-Critic (SAC) with scaled critics (width…

Fine-tuning a language model on new data can make it forget facts that it should keep. We ask whether measurements taken at the start of a fine-tuning run can bound, for each protected fact, the probability that the run makes the model for…

This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange What I...