AI Intelligence Archive

On-policy distillation (OPD) provides dense, per-token supervision for language model post-training, but its effectiveness is bottlenecked by teacher quality: external teachers suffer from distribution mismatch, while self-distillation wit…

Late Gadolinium Enhancement (LGE) on cardiac magnetic resonance is a key marker of myocardial scar, but its limited accessibility motivates routine ECG-based screening. We evaluated whether $β$-variational autoencoder (VAE)-derived ECG rep…

Automated reference-based evaluation methods play a critical role in assessing natural language generation systems. Existing meta-evaluation primarily measures agreement with human judgments or benchmark labels, providing limited insight i…

Over five rounds of reading other people's agent frameworks on 2026-09-04, the same defect class...

Recent years have witnessed great advances in the reasoning ability of Large Language Models (LLMs). However, the reasoning processes of LLMs often exhibit uncertainty, where LLMs often produce a proliferation of divergent branches at each…

In the same week that Claude Fable 5.1 shipped, two things happened that look like they cannot both...

Production multi-agent systems replace agents constantly, on the assumption that an agent filling a role is interchangeable with any other agent that can do the job. We test that assumption. Eight teams per setting are formed independently…

Layer dropout (a.k.a. stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout - p…

LLM agents deployed for software engineering fail expensively: they act confidently wrong, and bad actions are recognized only after costly execution and retry. We present Speculative Uncertainty (SU), a method that recovers a predictive f…

Artificial intelligence (AI) is transforming not only what information systems researchers design, but also how design research is conducted. Yet existing literature offers limited guidance for computational design science (CDS) when AI ac…

LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, individually correct security mechanisms do not necessarily compose into an end-to-end secur…

We investigate the best $L_2$ approximation of mixed Sobolev spaces by shallow neural networks with $n$ neurons and general activation functions. We first establish an activation-independent Fourier-block principle: if an activation has un…

Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two factors: the labor-intensive manual annotation of cognacy judgments required for character…

Large language model agents increasingly rely on execution traces to master complex interactive tasks. However, current paradigms are bottlenecked by shallow trajectory retrieval and flat skill summarization, fundamentally ignoring the tem…

Large language models (LLMs) are increasingly used to formulate optimization models from natural-language problem descriptions, yet realistic operations research (OR) requests are often incomplete: missing objectives, constraints, or busin…

Hey! 👋 I recently shipped ailineart.com, an AI line art generator that turns photos and text prompts...

Code: github.com/alexcpn/catalogify · uv tool install catalogify · MIT Take a monorepo with ninety...

TL;DR I consolidated six service repos into a single monorepo over three weeks, using...

Previously: 9 Bugs That All Looked Like a Working System · I Built an AI That Rewrites Its Own...

Two readers said the same thing. Under the 3x-price comparison, Vinh said the next experiment should...

As a hobby project I tested whether I could build a fully functioning game with AI. The result is a...

A practical workflow for combining AI-assisted black-box testing with human review and useful open source feedback.

On Tuesday, Google announced Gemini 3.8 Flash Cyber, a model that its own Cloud Vulnerability...

The first time an n8n workflow replaces a 300-line integration script, it feels like you got away...

The dangerous moment is not when an AI suggests a workflow. It is when it can activate one. Imagine...

OpenAI's newest model can find and chain zero-days without a human walking it through each...

TL;DR: Tried to compare AI-agent n8n workflows against plain ones. Filtering the biggest public...

Per due mesi, in un progetto vero costruito con Claude Code, ogni sessione e ogni subagente ha...

AI engineering sounds fancy. New terms are everywhere: agentic development, AI-native engineering,...

Almost every AI lab now hands out a free tier. Google, Groq, Cerebras, Mistral, Cohere, NVIDIA,...

Lend him the opening. Lure him in. Cut his support. Trap him where there is no way out. To take the...

Most AI demos you see online are either simple text chatbots or basic wrappers around an API. I...

That's at least what every tech bro is saying right now on Twitter. The next wave, apparently, is...

Intro There's a pitch behind every "AI writes your tests too" workflow: more coverage,...

There's a phrase I keep seeing everywhere in AI development: "We need an AI agent." Need to analyze...

Two instructions went into an Auditor my agent collaborators and I built to surface conflicts in...

Last week I open-sourced Foremerge, a coordination protocol for coding agents that sits above Git....

A pull request can pass the compiler, the formatter, and the linter and still leave behind a serious...

I ship Codenames AI, a web game. Each game mode keeps its own save in localStorage. Reload the tab,...