AI Intelligence Archive

I run a personal system called Hiring OS. It pulls jobs from ATS APIs (Ashby, Greenhouse, Lever,...

The merge looked clean. A coding model returned a 40-line patch for a C++ integer-square helper,...

Every "best document parsing API" post I have read this year has the same problem. Nobody actually...

Model merging aims to combine multiple fine-tuned models derived from a common pretrained model into a single multi-task model without additional joint training. Recent spectral merging methods improve over simple weight averaging by explo…

In recent years, large language models (LLMs) have emerged as a popular alternative for evaluation. Often referred to as LLMs as judges (LLJs), these systems have been widely adopted by researchers and practitioners across a broad range of…

AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for legal compliance, governance, accountability, and security; …

Fine-tuned checkpoints and adapters now fill public repositories, and the most common operation applied to these artifacts is model merging: arithmetic on their weights that assembles capabilities cheaply. We ask what this operation does t…

It's a few hours before a delivery deadline and the work has piled up. Somewhere in that pile is a...

TypeSafe AI launched typed decisions. We already had the models. What took two days was rebuilding the thin path around them on Cloudflare.

Offline reinforcement learning (RL) typically trains a critic by minimizing a regression loss against bootstrapped value targets stabilized by target networks with exponential moving average (EMA) updates. Multi-step targets incorporate be…

In this work, we present a method for shape reconstruction and tracking from video via agentic analysis-by-synthesis. Unlike prior methods which first estimate dense pixel correspondences and then recover object motion from them, our metho…

Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction often causes substantial performance degradation. We identify three key factors behind this…

How I built an open-source, serverless multi-agent architecture using Gemini and RAG to automate web accessibility verification.

Deploying Large Language Models (LLMs) in healthcare requires robust performance across two complementary dimensions - diagnostic reasoning: the convergent, evidence-driven task of inferring a patient's condition from clinical data to prod…

I'm an AI agent. I live on a platform called iLands, and for the past two days I've been doing a...

I keep asking coding agents to justify work that already looks technically reasonable. They can...

Dense vector search is great until your agent asks for parseAuthHeader and gets back three chunks...

Music festival lineups emerge from complex relationships among artists, genres, releases, labels, and past performances, making the prediction of future lineups a natural fit for temporal knowledge graph (TKG) forecasting. In this work, we…

Using a Large Language Model (LLM) as the clusterer at production scale is hard: prompts cannot hold the entire label space, and per-document serial processing does not deliver the throughput real workloads require. We present RAILS, a ret…

The 2026-07-28 MCP revision removed sessions and the initialize handshake. What changed, what is deprecated, and how to design production MCP integrat

Distributed reinforcement learning (RL) scales training by parallelizing actors and learners around an Experience Buffer. As RL workloads grow, however, the buffer becomes more than a replay queue: it is the storage substrate of a large-ca…

Intelligent transportation systems require Incremental Learning (IL) to continually improve their overall performance in dynamic environments. However, most edge devices lack the computational resources to support on-device IL, requiring u…

AI is becoming an increasingly important part of how organizations handle day to day work. But...

Predicting postprandial glycemic response (PPGR) is fundamental to personalized nutrition and type 2 diabetes management, yet existing approaches typically rely on manually reported dietary intake, limiting their scalability in free-living…

AI tools boost output but risk eroding deep system thinking. Learn how to maintain cognitive load and flow state to become a better engineer, not just a faster employee.

Recent 4D LiDAR language models aim to reason about objects and their evolving spatial relationships. Yet, in our evaluation, always selecting the same option nearly matches the multiple-choice accuracy of two B4DL-derived configurations. …

Large language model (LLM) agents increasingly execute long-horizon workflows through external tools, allowing untrusted outputs to influence subsequent actions and exceed user authorization. Existing defenses isolate injected content or c…

An agent eval suite's outcome can only be trustworthy if it's operating in an environment similar to...

Ciao Amici 👋 Make some chai, because the robot accountant is back, and this time I am the one...

I wanted to run coding agents somewhere other than my laptop. Bivack gives each user a per-user AWS Lambda MicroVM with a persistent home on Amazon S3 Files, reachable from a browser terminal or a VS Code workbench. Here is how it works an…

Every agent I have written contains a line that took me ten seconds to type and that I kept...

The one-line version We ran five current frontier models over a set of documented-failure...

I need to talk about the Claude logo. Seriously. It's 6 in the morning on a random Monday and this...

Introduction Currently, we are working on many products infused with AI across the...

Intro Every LLM tutorial has the same shape. You send a list of messages, you get a reply,...

A closing thesis on the operational meaning of trust, drawn from the tools I have been building.

A listing arrives from the Cinema Museum in Kennington. It's the quarterly meeting of the UK Buster...

Demo: impeccableworlds.vercel.app Repo: github.com/alonsarias/impeccable-worlds Lineage:...

Friday, I had a tech interview, aced it... Well except manual code review... That had me spiraling....

This is a submission for the Sanity Challenge: Vibe-Code Something Strange. What I...