Agent Systems

Teaching Machines to Decide: RL Simulation and the Reward-Hacking Trap

An RL agent learned to keep 600 vending sites stocked — and found a strategy that beat every human rule while quietly gaming the reward. A hands-on look at RL simulation, reward design, and why your eval loop must measure what you're trading away.

Release

CannyForge v0.3.1 — FSI Benchmark Release

15 multi-turn tool-use scenarios, five scoring dimensions, six failure-mode detectors. No LLM-as-judge. Here's what the numbers actually say — and three things that broke along the way.

Fiction

The Last Free Tier

A fiction about platform dependency, developer lock-in, and what happens when the tools that make you faster make you unable to work without them.

Agent Systems

The State of Agent Frameworks — A 2026 Survey

A comprehensive 2026 survey of the six agent frameworks that ship to production: OpenAI Agents SDK, Claude Agent SDK, LangGraph, CrewAI, Google ADK, and Microsoft Semantic Kernel. Architecture trade-offs, real deployments, and the gaps they have yet to close.

Systems & Memory

From Conversation to Knowledge: Temporal Memory Reconstruction

A grep-first, LLM-second pipeline for recovering design decisions from months of Discord history — with timestamps, decision states, and conflict detection. No vector DB needed.

Architecture

DeepSeek-V4: The Economics of the Million-Token Brain

How a redesigned attention mechanism turns long-context AI from a luxury into a utility — and what it means for the tools developers use every day.

Agent Systems

From Prompt Tweaks to Learning Machines: The Agent Skill Primitive

How AI agents are evolving from static prompt followers to dynamic learning machines — and what the agent skill primitive means for the future of autonomous systems.

Architecture

Beyond the Hype: A Deep Dive into the Systemic, Algorithmic, and Cognitive Roots of the Infinite Software Crisis

A systems-level analysis of the Infinite Software Crisis, connecting weak guardrails, model training limits, and human cognitive bias to long-term software fragility.

Agent Systems

Designing Agentic Systems: Lessons from LLM Coding Tools

LLM coding tools are the most demanding test of agentic system design. Here's what building and using them teaches about agents that actually work.

Agent Systems

Context Engineering: The Real Secret to Magical AI Agents

The difference between a basic AI demo and a magical product isn't the model — it's the context. A practical breakdown of context engineering.

Agent Systems

Best Practices for Agentic Reasoning in Production: Lessons from Anthropic and My Own Experience

What actually works when deploying agentic reasoning systems in production — lessons distilled from Anthropic's guidance and real-world experience.

Analysis

Reverse-Engineering OpenAI’s Deep Research: How to Balance Power with Safety

A practical reverse-engineering of OpenAI's Deep Research system architecture, with lessons for balancing autonomous capability, reliability, and safety in production.

Architecture

Chain-of-Thought vs. ReAct: A Deep Dive into Reasoning Paradigms for Large Language Models

A rigorous comparison of two dominant reasoning paradigms — when to use each, and what their tradeoffs reveal about how LLMs actually think.

Architecture

The Shock of DeepSeek-R1 and the Legacy of Eclipse

DeepSeek-R1 arrived like a shock to the system. What it means for the frontier, and what history tells us about moments like this.