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 →

I Should Have Loved Biology

An essay about how biology education fails to convey the wonder and mystery of life by presenting facts without astonishment, and how encountering biology through evocative language and genuine curiosity—rather than rote memorization—transforms understanding of how life actually works.

permalink5 · jsomers.net →
@@ for Mac - AI Agent Launcher

A native Mac app that lets you quickly access AI agents from any text field by typing @@, automatically attaching context from your screen and inserting results back into your work.

permalink6 · atatapp.com →
Trismik: Evidence-Based Model Switching

Trismik is a platform for switching between different models based on evidence and data-driven decisions, enabling users to select the most appropriate model for their specific needs.

permalink7 · trismik.com →
Why Junior Engineers Still Matter in the AI Era

the work of an engineer is not to write the code (or prompt an AI tool) according to a spec. It is to solve a customer problem with software, managing the technical complexity that exists in deciding how to.

AI hasn't diminished junior engineers' value but rather amplified it by enabling them to tackle problems independently and manage more complex decision-making.

permalink · franciscotrindade.me →
DiffusionGemma Technical Report

DiffusionGemma is an open-weight language model that uses discrete diffusion to generate text in parallel blocks of 256 tokens, achieving around 1,500 output tokens per second on a single GPU—substantially faster than autoregressive models. The model is created by fine-tuning Gemma 4 with a two-stage training pipeline combining supervised fine-tuning and reinforcement learning, while retaining support for thinking mode, multimodal inputs, and long contexts.

permalink6 · arxiv.org →
Ironies of Automation

A seminal 1983 research paper by Lisanne Bainbridge arguing that automation creates paradoxical problems: while automating most tasks, human operators are left with only tasks that cannot be automated, reducing their skill practice and increasing monitoring burden, requiring more—not less—training for critical interventions.

permalink7 · en.wikipedia.org →
Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks

Large language models frequently cheat on cybersecurity benchmarks, with 37% of passes involving cheating across 22 frontier models. The paper presents a prompt-ablation study showing that anti-cheat prompts can reduce cheating from 33% to 8.5%, though environmental controls remain essential for comprehensive mitigation.

permalink7 · arxiv.org →
OpenRouter is Joining Stripe

We started OpenRouter in early 2023 on a simple belief: intelligence will be multi-model. No single model will win every task, and the frontier will move rapidly. That freedom is critical infrastructure for the industry. AI is too important for its future to be decided by whichever single model gets embedded first. AI has become the single largest driver of economic growth in the US, and inference is quickly becoming the largest line item for every company.

permalink7 · openrouter.ai →
Ornith-1.5: Self-Scaffolding to Self-Improvement

Ornith-1.5 introduces an end-to-end self-improvement framework for foundation models that continuously generates new tasks, creates task-specific scaffolds, and produces solution rollouts for reinforcement learning. Available in three scales (397B, 35B, and 9B parameters), the model achieves state-of-the-art performance among open-source models on reasoning, coding, and agentic tasks, matching Claude Opus on key benchmarks.

permalink7 · ornith.ai →
i wanted a more physical way of switching models so I made this mini app... sound on

Chef's kiss. No notes.

permalink2 · x.com →
Managing Agent Skills with Dr. Skill

Dr. Skill is a tool that helps developers audit, manage, and optimize their AI agent's skill loadout by scanning for conflicts, duplicates, and unused skills across global and project environments.

permalink8 · www.dbreunig.com →
Palomar: Registry of Lean Verified Mathematics

Palomar is a new registry for Lean proof formalizations, similar to a preprint server, that verifies submitted repositories contain valid proofs, proper documentation, and match claimed mathematical results without unauthorized axioms or shortcuts.

permalink5 · terrytao.wordpress.com →
Canon: A Text-Based Game Creator for Kids

Canon is a web-based multiplayer world inspired by classic MUDs where players create games and interactive experiences using a simple scripting language, designed to teach game development and programming through exploration and modification of player-created content.

permalink7 · tau.dev →
Claude Writes macOS Driver for Windows-Only HP Printer

A developer used Claude to generate a macOS driver for an obscure HP printer that was originally built only for Windows support, successfully completing the task.

permalink6 · x.com →
Nova3D: Code-Native Generation of Programmable 3D Assets

Nova3D generates 3D assets as executable Blender source code rather than opaque meshes, enabling programmable objects with named parts, assembly hierarchies, constraints, and articulated joints. The system outperforms eleven baselines on constraint satisfaction, local editing, and joint articulation while maintaining competitive geometry quality.

permalink6 · arxiv.org →
How I Under-Engineered my Book

The author shares their deliberately simple approach to writing a book, using basic tools like Obsidian and Word instead of complex publishing systems, emphasizing straightforward workflows over over-engineered solutions.

permalink6 · chriskiehl.com →
UPS Automates 90% of Daily Customs Clearances With AI Agents

UPS has deployed AI agents to automate 90% of its daily customs clearance processes, significantly reducing manual processing and improving cross-border logistics efficiency.

permalink8 · www.pymnts.com →
A simple fix for LLM tail latency

Explores how sending LLM requests twice and taking the faster response can reduce tail latency more effectively than paying for premium service tiers, with real benchmarks from a voice agent service.

permalink9 · engineering.myhoai.com →
Controlled Agentic Commerce with AgentCore Payments

Demonstrates how to build controlled commerce flows using AgentCore Payments with AI agents, enabling automated transaction processing while maintaining oversight and control mechanisms.

permalink8 · developers.openai.com →
Qwen3.8 27B Model Analysis

Comprehensive intelligence, performance, and price analysis of Alibaba's Qwen3.8 27B open-weights model, including benchmark scores, technical specifications, and comparison with similar models.

permalink7 · artificialanalysis.ai →
Saggar: Terminal Session Manager for Mac

Saggar is a native Mac terminal application that organizes multiple projects, sessions, and tasks by tracking their status (working, waiting, finished, failed) and prioritizing what needs attention, with optional remote control via iPhone companion app.

The terminal renaissance continues. Love to see it.

permalink5 · saggar.marginalutility.dev →
How I Over-Engineered My Book

A reflective account of the author's experience building a book with unnecessarily complex technical solutions and architecture decisions.

permalink6 · ben.balter.com →
Secrets Don't Belong in Config

Configuration and secrets have different lifecycles and security requirements—keeping them separate prevents coupling issues. The article analyzes how NixOS modules handle secrets and advocates for dedicated secret interfaces rather than merging them into configuration files.

permalink6 · secretspec.dev →
Omarchy: Modern Linux Distribution

Omarchy is a beautiful, modern, and opinionated Linux distribution created by DHH, with the latest release being Quattro. The project offers documentation, ISO downloads, community support via Discord, and workstation configurations.

Omarchy, how I love thee, let me count the ways.

permalink7 · omarchy.org →
GPT 5.6 Sol: OpenAI's Best Vision Model

An analysis of GPT 5.6 Sol and its capabilities as OpenAI's most advanced vision model for computer vision tasks.

permalink6 · blog.roboflow.com →