AI Intelligence Archive

Have you ever told your AI agent something important, only to realize a few conversations later that...

By Ryan Swift Yesterday, Google finally released its Gemini 4 Argon model for public use. It’s...

A scan of the Slack channels for a recent private equity deployment of Clonal (our operational...

Google mapped the complete male fruit fly brain, and my first question to an agent was “Can this run...

We spent the past few months on a question that sounds simple: what does it actually take to move a...

Many engineers rightfully view every step in a financial workflow as a potential point of failure,...

For financial technology institutions operating at enterprise scale, the initial wave of Generative...

The biggest design shift of the AI era isn’t about who writes the code. It’s about how long the code...

Getting an LLM-powered feature to work in a demo takes an afternoon. But getting it to produce the...

Someone built a torture chamber for small AI models, and the internet wanted it gone. I went through...

Imagine spending weeks agonizing over every single paragraph, polishing every example, and pouring...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...

Intro AI Avatar is a free app where your VRoid (VRM) avatar cheers you with all its...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...

The best thing I shipped last year was a diff that deleted more than it added. I don't mean that as...

Mathematical research drives scientific discovery, and recent advances in AI for mathematics have shown that language-model agents can solve challenging problems and develop substantial mathematical proofs. Yet much of today's AI-for-mathe…

We study the optimisation landscape of the maximum mean discrepancy (MMD) over weighted atomic measures. For the one-dimensional Gaussian kernel, we show that, for any compactly supported target distribution, sufficiently many particles en…

In sectors such as energy, aquaculture and chemical processing, the effectiveness of both mechanistic and data-driven models is frequently limited by poor-quality training data, which obscures underlying physical laws and degrades predicti…

Typed decision models (TDMs) are increasingly used in applications such as request routing and model selection, making reliable decisions critical to system performance. Fallback options accommodate categories outside regular choices, enab…

As Large Language Models (LLMs) continue to scale, their energy consumption during inference has become a critical concern. While Autoregressive (AR) models are the industry standard, Diffusion Language Models (DLLMs) have emerged as a pro…

We propose DeltaStreamer, a novel agentic framework for streaming video understanding inspired by how humans observe, remember, and investigate. Streaming video understanding requires a system to retain evidence before knowing which detail…

We present OpenTWBench, an open evaluation suite for Taiwan-domain knowledge in large language models, built around two benchmarks. tw-exam-bench contains 255,854 four-option questions across 148 academic subjects, from fifteen years of Ta…

Google's Agent Development Kit (ADK) is a code-first framework: you write a Python module, declare an...

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle. ...

Memory-efficient subspace optimization has emerged as a practical approach to reducing the memory cost of LLM training while preserving optimization performance. Previous algorithms typically rely on the leading singular subspace of stocha…

Long-horizon tasks expose a weakness of monolithic tool-use loops: one agent must decompose, execute, and verify a task within a single trajectory. We introduce LAGO, which treats specialized language agents as reusable temporally extended…

Enterprise group chats record project progress, decisions, task ownership, and other organizational information valuable to enterprise agents. Reliable retrieval is challenging because evidence spans interleaved threads, channels, and time…

Frontier web agents using closed models have high inference and computational costs. Smaller open models can be an alternative, but to be performant, they require training supervision from a human or teacher model. Token-level teacher dist…

Reward model overoptimization in RLHF is usually described as reward hacking. We recast it as rent-seeking: the policy, a firm, earns reward from a regulator, the proxy reward model, that true quality does not back. The lens turns overopti…

Although multivariate time series forecasting has broad application prospects, effectively incorporating exogenous variables remains challenging. Prevailing discrete-time architectures often impose rigid temporal alignment across heterogen…

LLMs absorb vast knowledge from training data, yet their inherently probabilistic nature offers no guarantee that this knowledge will surface in their outputs. To bridge this gap, Knowledge Extraction Enhancement (KEE) techniques such as a…

LLM agents are evolving from a single model calling tools to planners that orchestrate multiple expert models whose capabilities live in distinct weights. This shift breaks a hidden assumption of today's serving systems: that the working s…

Distilling capable language-model agents into smaller models requires aligning the student's behavior with the teacher's. This raises a fundamental question: at which states and at what granularity should this alignment be performed? Offli…

Agentic AI systems combine model decisions, mutable state, tool calls, and delegation to external agents. Monitoring them requires observations from different execution boundaries, while prevention requires control before an operation prod…

Human values shape how we expect language models to behave. Dominant alignment approaches treat values as global objectives, although the appropriate value orientation is personal and contextual. Training-free alignment can steer models to…

Transformer-based tabular foundation models (TFMs) achieve state-of-the-art performance on small to medium-sized tabular prediction tasks while processing diverse inputs through a shared stack of layers. Recent layerwise analyses identify …

Spatio-temporal forecasting is fundamental to many real-world systems, yet deployment environments are inherently varying: temporal distributions may evolve, spatial domains may change, and observation availability may shift from training …

I gave an AI agent a Terraform task. It found a credentials problem. Part 1 of 3 in...

Two months of full-time work went into this. The part that nearly sank it was not the routing layer,...

Are AI models running directly in the browser finally good enough to use in production? Let's find...