AI Intelligence Archive

Organizing unstructured feedback text into hierarchical taxonomy is a fundamental challenge in NLP, particularly in domains where feedback arrives at massive scale in varied forms such as reviews, transcripts, and surveys. Existing approac…

Model Context Protocol servers make tools easier to discover and integrate, but discovery is only the...

Large language models are increasingly capable in general, but their utility can remain modest in niche or understudied areas. One approach to address this limitation is to specialise existing models through additional training on target-d…

With the development of large language models (LLMs), generative retrieval is becoming increasingly important in e-commerce scenarios. Current mainstream approaches typically use a two-stage training strategy: first train a product embeddi…

Robust estimation is a core computer vision task frequently tackled using sample consensus. However, traditional methods suffer from inefficient sampling as they struggle to identify effective minimum sets before hypothesis evaluation. To …

I rewrote the system prompt fourteen times. Version 3 was "be thorough." Version 7 was a 900-word...

Valuation Guide There are only two ways anyone prices software. What it earns, or what it cost to...

Short answer: choose ChatGPT Plus if you mainly use ChatGPT itself, consider ChatGPT Pro only when...

Short answer: choose ChatGPT Plus if you mainly use ChatGPT itself, consider ChatGPT Pro only when...

For the last couple of months I've been handing an AI agent (Claude Code) real DevOps work — not toy...

For the last couple of months I've been handing an AI agent (Claude Code) real DevOps work — not toy...

How my agent actually finds answers — and what happens when it doesn't Part 5 findings of an...

How my agent actually finds answers — and what happens when it doesn't Part 5 findings of an...

The README for the thing I'm building puts the limits above the features. Not as a humility move....

The README for the thing I'm building puts the limits above the features. Not as a humility move....

A few weeks ago I wrote about why I built Apiarium after OpenRouter solved one problem for me and I...

A few weeks ago I wrote about why I built Apiarium after OpenRouter solved one problem for me and I...

I created this article for the purposes of entering the All Things Agentic Hackathon. Shoots is an...

I created this article for the purposes of entering the All Things Agentic Hackathon. Shoots is an...

nexus-lab-zen's probe-vs-prose, tested across two axes — clarity (20 scenarios × 5 trials) and drift (controlled fresh-vs-stale, cross-model, two runs). On clarity, prose diverges on vague rules. On drift, prose misses cleanly when a preci…

nexus-lab-zen's probe-vs-prose, tested across two axes — clarity (20 scenarios × 5 trials) and drift (controlled fresh-vs-stale, cross-model, two runs). On clarity, prose diverges on vague rules. On drift, prose misses cleanly when a preci…

Building a multi-agent system sounds simple on a whiteboard. Give one agent a task, let another...

Building a multi-agent system sounds simple on a whiteboard. Give one agent a task, let another...

This is a companion to the PlannerCritic series. Article 2 was about a specific critic bug. This one...

This is a companion to the PlannerCritic series. Article 2 was about a specific critic bug. This one...

Building an agent that adjudicates whether a required form item actually got answered — and refuses to file the report until every one has. Google ADK 2.6, Gemini 3.6 Flash, Cloud Run.

Building an agent that adjudicates whether a required form item actually got answered — and refuses to file the report until every one has. Google ADK 2.6, Gemini 3.6 Flash, Cloud Run.

How to Use Claude Code for Free in 2026: OpenRouter Free Models, Ollama & Free GPU...

Two reports dropped on August 26 that should change how you think about running AI agents in...

Two reports dropped on August 26 that should change how you think about running AI agents in...

The Browser Is Becoming a Compute Platform: How Edge AI and High-Performance Web...

The Browser Is Becoming a Compute Platform: How Edge AI and High-Performance Web...

This week was a high-output sprint across the stack—from low-level p2p networking in Python to...

Opening four coding-agent sessions feels like scaling. On a shared machine, it is closer to giving...

Gemini function calling makes tool use look simple. You describe a function, provide its input...

How I replaced manual daily logins across 16 financial portals with a reliable, observable automation...

An analysis of the trust gap in autonomous agent pipelines, exploring how tools like GStack and Orca address compounding error rates in agentic workflows.

What I learned while building a project-intelligence layer for AI-assisted development. There is...

Written for the All Things Agentic Hackathon: Ready, Set, Agent! Build next-generation agents that...

I'm building a BitTorrent client in Rust. Mostly just to actually learn Rust. A couple weeks in, I...