AI Intelligence Archive

Weak supervisors are usually judged by their own errors, but what matters is what a student learns from them. For squared loss and any linear learner shared by all supervisors, we show that a supervisor's value is determined by its errors …

Most agent demos stop at "it answers in a notebook". A customer asked me for the other half: how do...

Translating parallel scientific codes between HPC programming frameworks is a critical but labor-intensive task. Existing LLM-based approaches rely on fixed sequential pipelines with undifferentiated repair strategies and correctness crite…

Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only on its model but also on its harness: the prompts, tools, memory, and control loop through which the model acts. When an agent is…

The growing reliance on high-fidelity, state-of-the-art machine learning based models for engineering decision-making necessitates robust and systematic approaches for model selection. While high predictive accuracy at untrained points is …

Proximal Policy Optimization (PPO) stabilizes policy updates by clipping the importance ratio between the new policy and the data-collecting policy. The standard rule uses one fixed clipping range for all samples. While this choice offers …

Can frontier general-purpose agents understand client intent, explore creative directions, execute revisions, and prepare production deliverables? We introduce DRAFT-Bench (Design Reliability Across Feedback and Tasks), a lifecycle-oriente…

Probabilistic load forecasts for AI data centers need to represent both uncertainty under changing workloads and temporal dependence to support grid operations. This paper develops an open, grid-oriented benchmark using measured GPU power …

Quantization-aware training (QAT) is the most reliable way to obtain accurate low-bit large language models (LLMs), but training with AdamW keeps two dense FP32 states for every weight matrix. We find that low-rank memory-efficient optimiz…

Automated scientific discovery has the potential to advance understanding of disease mechanisms and accelerate identification of early disease markers. Manual data annotation is infeasible at population scale, motivating methods that autom…

Many professional reports reuse the structure of prior editions while updating the content. We formalize this setting as form-restricted report generation: given a sample report and new grounding documents, generate a report that preserves…

Real-world multivariate time series rarely come with verified ground-truth causal structure, so research on time-series causal discovery and treatment-effect estimation depends on synthetic data. Existing tools are either fixed datasets th…

We study the problem of causal effect identification from an arbitrary set of observational and/or interventional distributions, which we call Universal Identifiability (uID). The uID problem generalizes existing classical identifiability …

Recently, Claude Code just... stopped. Not a bug in my code, not an outage. I had burned through my...

Recent progress in embodied robotics is bringing robots closer to deployment in homes, as vision-language models (VLMs) are demonstrating significant advances in reasoning, making VLM-driven robots promising home assistant agents. These ag…

Machine learning methods for solving partial differential equations (PDEs) significantly improve computational efficiency over traditional numerical solvers such as finite element method (FEM). However, PDE dynamics inherently span both lo…

Five ways a prediction-market model fooled me, and the one metric I trust now For five...

Execution Truth Validator: Defeating Exchange API State Drift and Phantom Orders ...

Coding agents like Claude Code and Codex are fast, yet a lot of wall-clock time goes to them waiting...

CVE-2026-103572: Copilot in Visual Studio blocked .mcp.json by string. The agent wrote .mcp.json. and Windows saved it as the real file.

From a multi-agent testing experiment to a broader discussion about how engineering teams should...

Agents add a whole library to use one function. Put a size-limit budget on each entry point, gate the push and CI, and hand the failure back to the agent.

When an LLM edits code, it usually works on text: it rewrites the file, or it finds a string and...

An agent once told one of our users that our MCP tools "cannot create projects" and asked them to...

Before you install a Claude Code plugin, open three things in its folder: hooks/hooks.json, .mcp.json...

A post-mortem of consolidating subscription seats behind one OpenAI-compatible gateway: the OAuth client boundary that was crossed, the cluster block that followed, and the task-dispatch architecture that replaced it.

The problem I build Roblox games on my own, and good-looking 3D models were always my...

Fala, pessoal! Recentemente, desenvolvi um trabalho para a minha pós-graduação com um tema que vem...

As AI agents become increasingly capable, I've noticed a growing number of discussions questioning...

Before you open Claude Code in a repo you cloned, look inside its .claude/skills/ folder. Read the...

My first script for checking local Claude Code token usage summed raw assistant lines in...

The word was go. A bot in the on-call room had just told me the deploy caused the outage. It quoted...

Everyone says they called it. Almost nobody can show they said it first. That is the problem...

A few weeks ago we teamed up with Kaggle to ask a deceptively simple question: how do you actually...

Codex 0.165 made memory v2 the default for fresh profiles; Claude Code's auto memory is on by default. Neither shows up in a PR. Agent rules belong in git.

You finish the engagement on a Friday. The repo is clean, the pipeline is green, the agent guides in...

When people call an AI model "open," they don't always mean the same thing. On this week's Prompt...

Map what a compromised prompt, model, or host lets an attacker sign or steal, then choose a control tier.

OpenAI reports 948 local Linux escalation findings. Variant counting, human patch review and assigned-path checks explain what the research establishes.

In my very first Quenya post (so proud of myself!), I listed QuenyaTTS among the tools worth knowing:...