-
Local LLMs for Data Analysis: A Self-Correcting Agentic Loop
Not Smarter, Just Persistent: Local LLMs That Fix Their Own Work This is an account of building Lattice, our agentic data analyst. Lattice works across models (from frontier APIs to…
-
What the 2026 Stanford AI Index Report Tells Us About the State of AI
Every year, Stanford’s Institute for Human-Centered AI (HAI) publishes the AI Index Report, widely considered the most comprehensive, independent snapshot of where artificial intelligence actually stands. Now in its ninth…
-
Announcing the Open-Source Release of the Agentic Paper Review System
In January, we published From Months to Days: AI-Assisted Peer Review with Human Oversight, describing how a multi-agent AI system could assist with large-scale structured academic paper review while keeping…
-
Why CAPTCHAs Are Losing Ground to AI
You’ve done it hundreds of times. A grid of blurry photos appears on your screen: “Select all images with traffic lights.” You squint, click a few tiles, wonder whether that…
-
What if your AI could actually read a table?
Most AI tools handle text well. But ask them about a table in a research paper, and they quietly fall apart. Tablemind was built to fix that. There’s a technique…
-
Going Inference-Token Free: Local Models for Enterprise Knowledge Work
We’re building a knowledge chatbot that reads from SharePoint and uploaded files, and even in its early stages, an uncomfortable question is starting to take shape: are premium cloud models…
-
The New Presentation Stack: Why Web-First Decks Win And Where They Fall Short
The humble slide deck hasn’t changed much since the 1990s. We still treat presentation design like a digital overhead transparency, rigid rectangles with fixed dimensions. A compelling alternative is quietly…
-
Democratizing Generative Agent-Based Simulation for Sustainable Development Goals
What if you could model peace negotiations between conflicting nations, simulate labor strikes to test collective bargaining strategies, or design resource management systems that prevent the tragedy of the commons,…
-
The Missing Layer Between AI Coding Agents and Institutional Knowledge
You’ve been there. You ask Claude Code to refactor the auth middleware. It proposes server-side rendering (SSR). You explain, once again, that the PM vetoed SSR six months ago for…
-
Multi-User OpenClaw: Deploying from a Single Laptop to Organization-Wide Scale (Fork-Free)
Turning a 363,000-star single-user AI agent into a secure multi-user platform, without changing a line of its code. The Problem In March 2026, we published “The Lobster in the Machine”, documenting…
