LLM - Reading the Water

Reading the Water

Sign in Subscribe

LLM

Large language models: capabilities, applications, and development patterns from a builder's perspective.

Build in Public

How a ChatGPT Prompt Log Became a 43-Module AI Reasoning Framework

In 2023, I had a ChatGPT Project with a growing stack of files in the knowledgebase. Not a framework. Just files. Instructions I'd written. Patterns I'd noticed. Things I wanted the model to carry between sessions. I was running a one-person shop, no team to

Open pocket watch revealing intricate mechanical movement — representing the engine built over six years of AI development

Solo AI Builder: 6 Years, 4 Frameworks, No Partners

From Google Ads scripts to 450 commits a month — and what ten years of going solo actually taught me about building alone in the AI era.

Three identical analog pressure gauges in a row on a matte navy surface, bright green needles all at the same reading. Three benchmark arms, identical result. -->

Benchmarking KnowledgeForge on GAIA: the Good, the Bad, and the Ugly

I'm building KnowledgeForge (KF) — a reasoning framework that sits on top of a base model and routes work to specialized modes: a Critic for finding gaps, a Debugger for diagnosing failures, a Strategist for trade-off decisions, a Builder for producing artifacts. The promise is easy to state

Surreal scene: glowing AGI brain emits art, music, code; cracked gavel on broken IP law book. Text: Authorship Void, Inventorship Fiction, Incentive Collapse, Training Data Ratchet.

Who Owns What AGI Creates? Nobody. That's the Problem.

Creatorship of AGI David Pedersen / NW AGI Group April 2026 Abstract Roman Yampolskiy's 2022 paper "Unownability of AGI" identified multiple structural barriers to AGI ownership — principally unpredictability, unexplainability, and uncontrollability, alongside self-modification, ease of theft, and contested AI rights — concluding that AGI, as a class