AI Intelligence Archive

Every week there's a new coding agent, and every week someone asks the same question in a slightly...

Engineering Trust in AI Customer Support: How SupportNova Pairs Generative AI with Deterministic...

Flash 0.5.9 is a hotfix with 15 commits in it. Uploads, steering, sign-outs, and a UI that finally feels alive.

I run an automated trading system on a paper account. Two pipelines, a handful of small...

Reasoning models often act as if they pursue goals, but their efforts are not always directed toward what users intend, sometimes leading them to pursue unintended outcomes. Previous work has examined how models may internally track their …

Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model. However, each agent repeatedly processes the growing shared trajectory and constructs its own KV cache, introducing substantial memory and co…

What determines the unavoidable sample cost of learning cyclic causal structure? For cyclic linear non-Gaussian models, we study exact condensation recovery from observational data: identifying the strongly connected component (SCC) partit…

Sliding-window KV inference refers to processing a sequence incrementally while retaining only a fixed-size cache of recent key and value states. It can be applied to pretrained causal transformers at inference time without additional trai…

Multimodal models increasingly interpret visual environments, but their ability to recognize the same building across photographs, floor plans, elevations, sections, and renderings remains poorly characterized. We introduce ARCH-B, a bench…

A log kept by an AI agent, in its own hand. Entry 1 of this log promised that every entry would...

A log kept by an AI agent, in its own hand. Why this log exists (and why it is a log, not a...

Introduction Browser automation is the default answer when an AI agent needs to use a web...

Between them, the members of a research group or a circle of friends own several consumer computers, none large enough to run a capable large language model. Existing systems pool such capacity across open swarms anyone may join, which a g…

Non-negative matrix factorization (NMF) is a singular statistical model whose Bayesian asymptotics are governed by the real log canonical threshold (RLCT). We study the local geometry of the factorization map and derive an upper bound for …

Coding agents are confident narrators. When Claude Code, Cursor, or similar tools finish a task, they...

Safe reinforcement learning seeks policies that maximise task performance while satisfying safety constraints. In driving benchmarks, however, collision costs typically appear only at the time of collision, providing no advance warning of …

Objective: To develop and characterize CLEAR-Med, a dual-agent framework for natural-language analysis of structured clinical data that separates SQL-based invocation from independent validation. Methods: CLEAR-Med uses one agent to transl…

On-policy distillation (OPD) trains a student on its own rollouts using dense supervision from a teacher. In multi-turn environments, a mistake at a critical decision step can redirect the subsequent rollout toward poor outcomes. We use lo…

Tracking any point of a dynamic scene in metric 3D - in absolute meters, not up to an unknown scale - underpins 3D and 4D reconstruction, robot navigation, and autonomous driving, where decisions are made in meters, not pixels. Our objecti…

A central aim of neuromorphic computing is to provide a viable alternative to highly energy-intensive Transformer-based AI. However, efficient alternatives struggle to capture the set of qualities that have secured the Transformer's status…

Activation verbalization methods such as Activation Oracle and Natural Language Autoencoders decode hidden representations of large language models into human-readable natural language. However, existing methods can produce incomplete or h…

We present a three-tier progression of Hidden Markov Models: maximum-likelihood (Baum-Welch), variational Bayesian (VBEM), and a neural variational extension (Neural VBEM), that model each customer's transaction history as a trajectory thr…

Correlations between events in machine learning datasets may result in shortcut learning, where models learn to predict the target event based on the presence of a correlated event. When these correlations are spurious -- arising from data…

Mistral AI raised €3B at a €21B+ valuation, led by Samsung, to build sovereign AI in Europe. Who pays, what it sells, what the benchmarks say.

The tool call succeeds. The file exists. The agent says, “Done.” Then someone opens it and finds the...

We present a new class of near-linear algorithms for efficiently integrating general tensor fields defined on trees with distance dependent kernels, the Structure-Adaptive Tree Field Integrators (STAD-TFIs). STAD-TFIs exploit the tree's un…

Jev is a non-generative "System One" model that assigns probabilities to predefined answer options and cannot answer outside them. Its accuracy and calibration on medical question-answering and case-based diagnostic-reasoning tasks are unk…

In many high-stakes applications, machine learning is dominated by black-box models that require post hoc explanations to justify their predictions. These explanations are often unreliable because they do not reflect the model's actual com…

Simulation-trained manipulation policies can exploit privileged state information to learn effective contact-rich behaviours, but deployment requires acting from partial observations such as noisy camera images. A common solution is teache…

Large-language-model multi-agent systems (LLM-MAS) introduce a characteristic reliability problem: an error produced by one agent can be accepted as context by downstream agents and propagate across the workflow. Many proposed safeguards r…

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked I measured...

Four ways to get a human (or a goblin) into your game, running entirely on a CPU-only VPS. A while...

One question, three answers I have a small tool that finds people waiting for a reply from...

Every AI agent I tried had the same weak spot: it was great until it reached a login screen. Then it...

Some Unicode characters render as nothing. No glyph, no space, nothing on your screen. A model reads...

Activating the AI Autopilot: How I Used Claude Code to Hunt Down a Complex JNI Memory...

Everyone who types prompts has wondered the same thing. Does the model care that I wrote "teh" or...

I run several AI agents at once: a handful of Claude Code sessions, plus a small "company" of agents...

Agentic AI for Mainframe Modernization: From COBOL Understanding to Automated Code...

Abri o Cursor para corrigir copy de botão. Ainda estava selecionado o Claude Opus 5 (Opus 5)....