AI Intelligence Archive

Long-tailed recognition often learns a shared representation before correcting the classifier for class imbalance. Once the classifier has been rebalanced, however, final accuracy does not reveal whether further encoder adaptation remains …

Real-world image editing requires coordinating multiple visual transformations with content preservation and reference constraints, yet aggregate scores can readily obscure unmet local requirements. Effective evaluation must therefore iden…

Last week we pointed BugTraceAI — our open-source agentic security scanner — at our own...

RGB-thermal (RGB-T) object detectors combine visible and thermal imagery for robust detection, but signal corruption in either stream can substantially degrade accuracy. Restoration-based methods incur significant latency and do not consis…

Cameras and vision sensors are widely used for product and process inspection in manufacturing environments. Traditionally, this process required thousands of images of both nominal and defective products to train such models. Recent resea…

A developer's look at how AI changes the economics of coding across outsourcing, software products, and SaaS, and what that means for engineering careers.

Multimodal federated learning (MFL) trains a shared model by aggregating client updates without exchanging raw data. Under missing modalities, clients adapt active modality encoders and a shared prediction block (fusion and classifier) to …

LLM agents increasingly triage security alerts by combining the outputs of several detection tools, implicitly treating those tools as trustworthy. Unlike prior work on conflicts between a model's knowledge and its context, we study confli…

I run a small AI video web app: users upload a character photo and a short motion clip, and a hosted...

End-to-end (E2E) autonomous driving models achieve strong planning performance but remain largely opaque, limiting observability and trust. We apply mechanistic interpretability to E2E driving by training Sparse Autoencoders (SAEs) on the …

Visual Studio used to ship big releases every couple of years. Now it ships something every month,...

LLM-guided program evolution can produce mathematical constructions, but validity, generality, and reproducibility require distinct evidence. We develop a researcher-in-the-loop discovery pipeline that combines program evolution, exact eva…

A replay that re-executes real tool calls is a re-run wearing a trace's clothes. Here is a paste-and-run check that blocks egress during replay, plus the five fields your trace needs so the blocked run still reproduces the original failure.

CodeNecromancer: Resurrecting Dead Repositories with Open-Weight Gemma (Hacktoberfest Week 4 - Ghost in the Machine)

Alphabet reported its fastest year-over-year Search query growth in five years during the third...

AI-powered search has made it tempting to publish more content, faster, in pursuit of citations and...

OpenAI has publicly detailed an expanded monitoring system for frontier models after a...

Alphabet’s third-quarter 2026 results provide a financial signal that Google is continuing to build...

German courts have issued two decisions in 2026 that sharpen the legal and operational stakes around...

Short video answers to questions customers already ask can be a practical way to expand useful search...

UMGD — Under Meeting Game Development game: Redneck Wreck repo:on github I owe you a...

Anthropic has introduced self-assessment, a production safety feature that has Claude evaluate a...

Rewriting a page for AI search may be the wrong first move when the page is inaccessible to the...

Why 90% of AI coding frustration comes from the Quota vs. Prompt-Compliance Death Loop, why Rich Sutton's Bitter Lesson fails in open-world software, and how we compile mid-flight collisions into 4-Vector Synthetic Scars and a Six-Pillar C…

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...

OpenAI has updated its public Model Spec, the document that describes how it intends its AI models to...

Google has launched a preview of Connected Apps Platform, a developer framework intended to bring...

Keeping up with AI is a full-time job. Prompt Pad is here to help you keep up a little at a...

Read a dead friend's messages, emails and photos on her 1999 computer, talk to her through an open-weight model, and work out what happened.

Google has expanded Gemini with tools for creating and refining files directly from its interface....

Git worktrees give each coding agent its own checkout, so the agents stop overwriting each other's...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine. ...

Some code deserves a second life. 💚 While exploring GitHub, I sometimes come across interesting...

Gemini 4 Carbon's numbers and access, a fingerprinting script with a fake system prompt in invisible characters, AlpineBSD's AI policy and Anthropic's drug development po

Data attribution methods for Language Models (LMs) are typically evaluated using downstream tasks like fact retrieval. However, existing evaluations vary multiple dataset properties simultaneously, making it impossible to isolate exactly w…

An estimator can be accurate and stable on typical data, yet sensitive to a few possible records. Differentially private mechanisms commonly scale their noise to the worst-case influence of a single record, which lets these records dictate…

The Neural Thickets hypothesis posits that pretrained language models lie in dense neighborhoods of task-specific experts in weight space, which random Gaussian perturbations can uncover. We reproduce the reported gains, but show that they…

Pixel-space generative Transformers typically use one token per image patch, so capturing finer detail requires more tokens and makes global attention increasingly expensive. We observe that finer detail does not necessarily require more g…

Distributionally robust optimization (DRO) hedges data-driven two-stage stochastic programs against error in the distribution estimated from a finite record, and standard ambiguity sets differ in how they treat realizations absent from tha…

Luggage re-identification (ReID) is a critical task in video surveillance for forensics, security or border management (suspicious or abandoned luggage recognition), as well as luggage management (lost luggage recovery). It enables the ass…