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.

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.

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.

A minimal, dependency-free implementation of GPT training and inference written entirely in C, offering an atomic approach to building language models without external libraries.

Wondering what the technical floor might be performance per watt in some of these optimizations. Impressive.

Today’s result is a reminder of what can emerge from pioneering: asking questions others have not yet asked, following the science where it leads, and persevering through uncertainty.

Chef's kiss. No notes.

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.

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.

Cerebras CS-4 is a rack-scale AI accelerator system featuring three WSE-3 Turbo wafers that delivers up to 30x faster inference than GPUs, with improved performance per wafer and integrated power, cooling, and I/O capabilities for hyperscale datacenter deployment.

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.

Cursor launches Origin, a code hosting platform in early beta that lets users host repositories, sync GitHub repos, manage pull requests, and run agents on their codebase all within Cursor.

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.

A tool that optimizes language model quantization to fit precisely within your available hardware memory, maximizing quality by using 99.99% of your memory budget through per-tensor mixed-precision assignment.

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.

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.

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

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.

A zero-overhead GPU compilation framework integrated into the Rust compiler that enables safe, multi-vendor GPU programming by leveraging Rust's type and ownership systems without requiring unsafe code or vendor-specific DSLs. The paper presents a two-pass compilation pipeline that handles cross-vendor ABI mismatches and demonstrates competitive performance against hand-optimized CUDA and HIP implementations.

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

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.

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.

An interactive playground for testing and comparing over 30 pre-trained computer vision models side-by-side. Users can experiment with different models and evaluate their performance on various tasks.

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

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.

SecretSpec released dotenv-ng 1.0, a modern Rust implementation for loading .env files, after discovering that dotenvy's parser was incorrectly substituting bcrypt fragments and experiencing long maintenance gaps in the original project.

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.