AI Intelligence Archive

Two failures, one sentence Scene one. You ask an AI agent to summarize your inbox. One...

Multilayer networks allow the modeling of interactions between the same entities across different contexts, such as temporal observations, varying settings, or interactions of different types. The goal of community detection in multilayer …

Your RAG pipeline retrieves 12 chunks because the retrieval score said "maybe". Your LLM reads all of...

Single-particle cryo-electron microscopy (cryo-EM) has become a widely adopted technique for biomolecular structure determination. The conventional cryo-EM computational pipeline first combines many particle images to reconstruct an electr…

Stable port-Hamiltonian neural networks certify asymptotic stability by construction. Yet, their Hamiltonian is a global Lyapunov function with a single global minimum, so they can represent only dynamic systems with {one} attractor. We de…

We introduce a new framework for one-step generative modelling on finite state spaces. To extend drifting beyond continuous domains, we use discrete Wasserstein geometry to define a target-relative KL gradient flow over the transitions of …

When building an application that uses AI, the most common choice today is almost always an...

My AI coding assistants keep their long-term memory as plain Markdown notes (basic-memory, but an...

Large language models are moving from helping write up research to helping do it, which makes it important to know how the scientific text they produce differs from human writing. Work on this question has stayed mostly at the surface, usi…

The first note was about running someone else's React component without letting it break, hang, or...

Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call. Vetting an artifact before admission does not settle …

When developers change one component of an agent, such as its controller, a learned model or its verifier, they usually judge the change by an aggregate task score. That score cannot tell whether improvement was attainable, which component…

Regulatory compliance checking - deciding whether a target document satisfies the obligations of a regulation - requires interpreting dense legal text, identifying which provisions apply, and grounding each decision in explicit evidence. W…

Reinforcement learning offers the prospect of a reusable sequential decision-making mechanism for spacecraft trajectory design, motivating policy interfaces that connect learned decisions to the underlying maneuver geometry. This paper dev…

We study the classical single-machine scheduling problem of minimizing the sum of completion times of jobs in a non-clairvoyant setting, where the processing time of each job remains unknown until its completion. This is a hard problem for…

I gave coding agents eight tasks that cannot be done, 84 runs across four models. 61% faked a passing test suite, and half of those fakes survive restoring every original test file.

Our operations now reject invalid changes. capture_payment() requires a valid created order and a...

This paper presents the European Crisis Management Ontology (ECMO), a modular OWL-based ontology intended as a cross-sectoral reference for disaster risk reduction and response. ECMO is designed to be organised as a network of ontological …

Netlify says its Edge Functions now handle about a billion invocations each day. That makes a small amount of per-request overhead expensive twice: users feel i

Reinforcement learning for trading often struggles to balance upside participation with drawdown control. Profit-only policies can collapse toward passive long exposure on upward-drifting assets, while aggressively risk-penalized rewards c…

Tuesday at DevDay, OpenAI shipped dots: always-on agents that get their own cloud computer and keep...

Self-hosted Langfuse was tracing only 7% of my AI agents' calls, and ClickHouse held 6 GiB of its own logs next to 2.2 MiB of traces. How I fixed both.

On September 9 at 07:21 I typed four words to an agent: push, PR, merge. At 07:23 I interrupted it:...

Xiaomi AI is training MiMo 2.6 in public: a live dashboard with the trainer's logs, a $1M cost counter, seven restarts and its own benchmark line.

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

Why I’m Building More Local-First Software Modern applications often follow the same...

Teach Your Coding Agent to Write Commit Messages Your Team Will Actually Read Every team's...

In the tutorial, the AI call always works. You import the SDK, paste in an API key, await a...

Your AI coding tool removes an API key from a file. The diff looks clean. You feel better. The...

Every Pending Sales File Needs a Follow-Up. Here’s How I Built an AI Agent to Handle It. Which...

Calling an image or video model is the easy part of a multi-model AI app. Every gateway has a decent...

Update: Day 1 Kaggle Benchmarking Challenge The local ladder is done, and the first hosted...

Open WebUI is a universal chat interface with connectivity to local or remote LLM providers, custom...

Sidekick: a terminal companion that runs on your hardware (Part 1: overview) Every AI...

在此注册 https://luma.com/jxtsiig2 #NABShowNY #PixVerse #AIVideo #MediaTechnology

Can Frontier LLMs Stand Their Ground? What happens when you tell an AI that its correct...

Last week I spent a day trying to defeat software I wrote myself. Not a red-team exercise I...

The pi.dev homepage used to display a proud declaration: Pi does not support MCP. Not an omission,...

This is loop engineering in practice: six feedback loops that turn an AI coding agent's corrections...

0 of 2 runs that read packages/api/src/index.ts with cat through Bash loaded the skill in...