mattwood.fyi

I'm Matt Wood, and this is For Your Information. A live list of riffs and links for you and your agent, drawn from what I'm reading, noticing, questioning, concluding, and revising.

Links indicate relevance, not agreement. How to use this site →

Most connected

Understanding is the new bottleneck 31
8 Myths of Software Development with AI 31
Bridging Intent and Execution in Agentic Systems 31
Ways to think about token pricing 28
Taste Is All That's Left 27
Building an Advanced Agentic Harness 27
Comparing 11 Different AI Models 25
AI is removing the middle class of software engineering 24
SWE-bench Science: Coding Agents for Engineering Tasks 22
Introducing Dogwood: runtime verification for AI agents 22
Intelligence is not the main bottleneck 22
AMD acquires AI chip startup Taalas to boost inference performance by etching models into silicon 20
Why some people mow a lawn better than others 20
Trismik: Evidence-Based Model Switching 19
Grok 4.6 Benchmarks and Cost Efficiency Analysis 19
Leiden Declaration on Artificial Intelligence and Mathematics 19
Agentic Coding: LLM Agents, Testing, and Hallucination Risks 18
The Dynamo and the Computer: An Historical Perspective on the Modern Productivity Paradox 18
AI-Driven Development Life Cycle: Reimagining Software Engineering 17
LLMs can't jump 17
LLMs reward expertise 17
Agent Swarms and the New Model Economics 17
Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks 16
The Anti-Mac Interface 16
Formal Methods at Jane Street: Agentic Coding Changes the Calculus 16
Code Execution with MCP: Building Efficient AI Agents 15
AI Coding and the Bug Selection Problem 15
Managing Agent Skills with Dr. Skill 15
The Shape of Things to Come, Part 1: The Continuous Thunderdome 15
The Zero-Cost Fallacy: Open Source in the Agentic Era (Thoughtworks) 15
Schema: Frontier Models with the Right Harness Achieve ~99% on ARC-AGI-3 Public 15
Together AI: Research-Driven Inference and Training Platform 15
Unreal Agent: Cost-Efficient AI Agent Harness 14
Muse Connector Platform 14
Strands Harness: Frontier Performance with 28% Lower Token Cost 14
Ornith-1.5: Self-Scaffolding to Self-Improvement 14
Qwen 3.8 2.4T Mixture of Experts Model 14
DeepSeek V4 Pro 0813 API Pricing & Benchmarks 14
11–16× Faster LLM Inference with llama.cpp 14
Most tech revolutions made work worse for employees. AI could be the exception: this+that 14
TerminalWidget for Mac, iPhone, and iPad 14
Ten Advances In Mathematics 14
Fireworks AI: Specialized Intelligence Infrastructure 14
WikiSkill: Agent Experience into Persistent Knowledge 13
DiffusionGemma Technical Report 13
Nova3D: Code-Native Generation of Programmable 3D Assets 13
Controlled Agentic Commerce with AgentCore Payments 13
How This Was Made 13
Open Athena 13
How AgentCore Gateway Supports the MCP 2026-07-28 Spec 13