AI Intelligence Archive

Small and medium-sized language models offer cost-effective executors for tool-using agents, making them attractive for local and large-scale deployment. However, in long-horizon and stateful environments, they often make structural errors…

Financial institutions are beginning to deploy agentic workflows in credit, fraud, collections, compliance, and operational control. Governance remains largely component-centric: each model or agent is specified, tested, authorized, and mo…

Methods operating on Vision Transformer (ViT) feature spaces typically rely on Euclidean distance or cosine similarity. This assumes that every direction is equally meaningful, but there is no reason to believe the true task geometry has t…

Large language models (LLMs) have made substantial progress on medical question-answering, yet effective medical dialogue also requires learning to ask questions that uncover relevant patient information. To train such dialogue policies, a…

Accurate remaining discharge time (RDT) prediction is challenging in real-world battery applications because future load profiles are unknown and highly dynamic. To address the uncertainty of continuous RDT regression, this paper introduce…

In this paper, we are concerned with matrices formed by block-diagonal factors interleaved with fixed permutations -- a flexible family of structured matrices. This class has recently drawn interest in deep learning architectures for its b…

KV-cache eviction is typically evaluated through average quality-memory trade-offs, yet a small average loss can hide requests whose utility degrades materially. We reformulate eviction as a deployment risk-control problem: a material degr…

Pruning large pre-trained transformer-based ASR models such as OpenAI's Whisper has seen great adoption, as pruning the decoder led to significant end-to-end transcription speedups. For instance, the {\tt whisper-large-v3-turbo} variant re…

The surge in AI-assisted generation of educational materials has outpaced our capacity to validate their pedagogical quality. Automated evaluation using Bloom Classifier models is a promising approach to assess educational materials at sca…

The European Union's AI Act now requires transparency disclosures for deepfakes and certain...

Vision-language-action models (VLA) promise human-steerable autonomous driving, but their training is bottlenecked by the scarcity of frames paired with natural-language instructions: while camera streams and expert trajectories are logged…

A good human in the loop for multi-agent systems does not mean watching every agent in real time. You cannot, and you never will. It means building the…

This paper advocates category theory as a practical framework for structuring and improving rein- forcement learning in high-dimensional, partially observable environments. We model symmetries between environmental states by partitioning t…

In value-based reinforcement learning, improving the accuracy of policy evaluation has been shown to improve downstream policy optimization performance. The widely adopted family of approximations relying on $n$-step truncation yields comp…

We propose the Memory-Efficient Neural Operator (MENO) as a high-performance PDE neural solver based on the Manifold Function Encoder (MFE). MENO features three primary advantages: (1) MENO has a significantly smaller memory footprint and …

An AI agent is a language model wrapped in a loop that plans, calls tools and iterates toward a goal...

Newton-Schulz (NS) iteration has recently been used in the Muon optimizer to transform update matrices during the training of large language models. Motivated by its spectral effect, we investigate applying NS directly to Transformer atten…

Vision-Language-Action (VLA) policies often rely strongly on the camera viewpoints seen during training, causing substantial performance degradation when deployed from unseen perspectives. Collecting demonstrations from sufficiently divers…

For the last few months I've been using AI agents in almost every part of my React Native work. At...

DEV Library is my idea of first-person 3D reimagining of DEV.to. Not a themed scene with some...

On September 22, 2026, Anthropic shipped Claude Opus 5.5 and OpenAI shipped GPT-6 Sol on the same...

A prompt sent to an AI is a snapshot of what you know at the exact moment you type it. That sounds...

I run URL2Pin, a platform that turns a product URL (Amazon, Etsy, a blog post) into ready to publish...

Every HR or admin person planning a company offsite hits the same wall: nobody can tell them what it...

TL;DR "Agent framework" is used for several different kinds of tool: agent SDKs,...

Hamming's two kinds of novelty are not two kinds of stuff. They are two things you can do with one...

I have been pairing with someone who writes code in a web chat. Claude.ai, ChatGPT, whichever tab is...

A client asks for a CSV import feature. Two years ago you would have quoted 20 hours. Today an agent...

Here is the response on what the llm thought after the challenge. I think Human Cognitive Seed is...

A hands-on guide to making access control part of your Postgres vector search so an unauthorized chunk is never even ranked.

Introduction Many developers use Claude Code and look for ways to reduce token consumption...

Introduction Lately, discussions around token optimization in Claude Code have focused...

For a couple of years, this was framed as a simple either/or question: retrieve relevant chunks at...

An attacker brute-forced 87,000 IPs on legacy VPNs, rented them as proxies, and automated the whole operation with a modified AI CLI. Plus: identity as the new initial access.

I built Forger, a standalone Electron app that bundles a file explorer, Monaco editor, AI chat, Git,...

Currently, we are in a phase when the term “AI search” refers to the use of effective and slow...

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

Cisco Talos just documented the first Windows malware that doesn't wait for a human to tell it what...

Free web search for an agent sounds like a solved problem. There are dozens of DuckDuckGo MCP...

No CVE needed: how a GitHub issue hijacked an AI agent