AI Intelligence Archive

I spent a weekend watching a multi-agent research pipeline die because one pod restarted. Not the...

I run Convertica, a small PDF toolkit: Django, Celery, Redis, Postgres, Nginx and LibreOffice, all in...

For forty pages, or four hundred, BM25 keyword scoring, a synonym list and a pinned rules block are usually enough.

When I started building AI Music, the core workflow looked almost trivial: User prompt ...

The starting point My Garmin watch knows how much I sleep and tracks all my health...

One day, I was watching my favorite show, The Big Bang Theory (again), when I saw the scene where...

AIHOT is an MIT-licensed template for building sector-specific news sites with configurable sources, LLM selection, event grouping and scheduled digests.

TL;DR 81% jump in AI-service leaks: GitGuardian detected over 1.27 million leaked...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

This is a submission for the Kaggle Benchmarking Challenge Ask a model "is this a scam?" and nearly...

The Query That Breaks Pure Semantic Search .

Day 10 of 30 Days of Search for AI Agents. To build an investment research agent, retrieve dated...

OpenAI and LangChain push agent orchestration into managed platforms and cheap classifiers, while new research tracks the safety fallout.

Which host does this URL point to? >>> from urllib.parse import urlsplit >>> u =...

Most prompt injection defences are a sentence in a system prompt, which asks the thing being attacked to defend itself. The alternative is architectural: the model never holds authority, and every tool call is re-checked against the user's…

An open-source toolkit for reviewing deployed previews: comments land on the app, your coding agent reads them over MCP, and CI holds the merge.

This week, security leaders raised a harder question: who verifies the AI systems now verifying...

Zero-shot coordination in embodied settings requires acting while the partner is intermittently out of view, leaving existing methods with ambiguous partner representations and uncertainty over hidden partner states. We propose Predicting …

Legal intelligence aims to support reliable decision-making across long-horizon legal processes involving evolving case states and multiple roles. However, real-world legal deployment exhibits substantial case heterogeneity in facts, evide…

Concept drift threatens production machine learning, yet the empirical behavior of multivariate two-sample drift detectors at scale remains under-characterized. Existing benchmarks rarely address the hundreds of millions of rows and high-c…

Achieving compositional concept generalization (CoCoGen), the ability to understand novel situations by recombining learned primitives, remains a fundamental challenge in artificial intelligence. Compositional semantic models such as Compo…

Cooperation with unfamiliar partners requires adapting to communication conventions that are not known in advance. We study this problem in a controlled Hanabi-derived environment with scripted hint generation, LLM-controlled receiving dec…

Product Identification has sprung up to become one of the most challenging problems in the automation of the retail industry. With the new industry 5.0 standards, automated inventory management, and catalog creation tasks are vitally impor…

Full-duplex spoken dialogue models listen and speak at the same time, enabling voice agents to have natural, low-latency interactions that turn-based systems cannot offer. However, they are commonly evaluated against single-sided interlocu…

End-to-end planners based on waypoint regression achieve strong open-loop accuracy, but they primarily learn to mimic expert geometry and remain difficult to adapt to deployment-time safety constraints. We propose a query-based cost-learni…

Covariate-aware time-series foundation models (TSFMs) promise training-free what-if answers for instrumented plants: the change in output that a different future input would cause. We test this on forced engineering systems with exact coun…

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked I'm a solo...

Path-following control strategies typically follow the bi-objective optimization dilemma: minimizing deviations from a reference path while maintaining smooth speed profiles. The latter objective is especially relevant for Electric Vehicle…

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

Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders and parallel decoding. Recent dLLMs are often initialized from pretrained AR models bef…

Attacker ASV systems for voice anonymization have been studied primarily in English, leaving their behavior in multilingual settings largely unexplored. Conventional ASV has shown that both acoustic and contextual information are important…

Multimodal large language models (MLLMs) advance rapidly, while conventional benchmark development lags behind, delaying investigation of newly observed capability gaps. Such investigation requires an expressive task format and an on-deman…

Conversational MLLM agents are increasingly expected to assist in professional workflows, from AI research and engineering design to product management and business operations. Yet this capability remains underexplored: existing benchmarks…

Shared memory coordinates agents' actions, but correct records do not establish that those actions satisfy task requirements. Memory governance and failure diagnosis regulate or inspect recorded information; they do not by themselves estab…

AI agents increasingly rely on modular third-party "skills" that are dynamically selected by skill routers to execute complex tasks. While recent studies highlight the threat of prompt injections embedded in these skills, existing evaluati…

Mathematical problem solving often requires deterministic computational steps that agents delegate to tools and implicitly trust. Yet tools can fail silently, returning plausible but incorrect results. How well can agents detect and correc…

Natural-language access to RDF knowledge graphs is a core Semantic Web ambition. Large language models (LLMs) have advanced Text-to-SPARQL, yet on unfamiliar graphs they often generate valid queries that misrepresent the populated data mod…

Developing reliable models for clinical tasks, such as Medical Question Answering (QA), is severely constrained by the limited availability of high-quality, expert-annotated training data. This challenge is exacerbated by stringent privacy…

IPv6 extension headers (EHs), such as fragmentation, segment routing, and in-situ telemetry, are operationally important yetwidely dropped in transit, and characterising their behaviour from packet captures is a recurring measurement probl…

This is a submission for the Kaggle Benchmarking Challenge. In ProgressCut, it is possible to write...