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.

Loop engineering is replacing yourself as the person who prompts the agent. You design the system that does it instead. A loop here can be thought of a recursive goal where you define a purpose and the AI iterates until complete. It's roughly five building blocks and Claude Code and Codex both have all five now.

"There are three phases to AI coding. The first is autocomplete. The second is AI-assisted chat panels in IDEs. We are now entering the Agent-First era." — Zach Lloyd

Issue 1: Pod stuck in Pending state - Agent correctly identified missing Fargate profile for the test namespace.

Key details from coverage (NYT article paywalled; sourced from aggregated reporting):

AI Doomerism = a Secular Apocalypse Narrative. Practically, the "AI doom gospel" translates traditional religious forms into technical language. In the rationalist/effective altruist discourse, God becomes a superintelligence, prophecy becomes timelines and probability estimates, and hell becomes human extinction from AI.

I've been spending a lot of time thinking about the shape of the capabilities of coding agents. What they're good at now, what they're going to be good at. What they're bad at now, how much of that is inherent and how much is transient.

Problem: Adapting foundation models to a morphologically rich language (Azerbaijani) with limited training data, no existing blueprint for efficient LLM training in that language.

"Learning can only take place through the attempt to solve a problem and therefore only takes place during activity."

The 1997 analogy: We are in an era of radical uncertainty where the technology is transformative but most high-value use cases haven't been built yet and the "winners" are not yet clear. Just as it was impossible in 1997 to predict that a search engine with a quirky logo would reshape the world, we cannot yet see the final shape of the AI-driven ec

Authors: Tianyi Zhou, Dongrui Liu, Leitao Yuan, Jing Shao, Xia Hu

Mollick's post (May 30, 2026): "It does seem like meaningfully better AI releases are accelerating, especially from OpenAI & Anthropic. To illustrate, I caused this timeline to be created. It only lists new models that scored 3 points or higher over previous models in the Artificial Analysis index."

The problem: At Meta, significant lines of code per human-landed diff grew by 105.9% year over year and per-developer diff volume rose 51%, with agentic AI responsible for over 80% of that growth. Meanwhile, the share of diffs receiving timely review has declined, exposing a widening gap between code supply and reviewer bandwidth.

Thinking Display: See how the agent works through a problem as it happens. Thinking display streams the model's reasoning in real time, so you can follow its logic, catch a wrong turn early, and understand why it chose an approach. Enabled by default; toggle from /settings > Display > Show thinking.

Architecture: Built with Electron, TypeScript, and AWS SDK. Uses Kiro CLI's Agent Client Protocol for conversational AI. Three agents collaborate to build features and improve code/UX quality.

Architecture: - Multi-agent pipeline with orchestrator, workers, and reviewers operating in a DAG workflow - MCP tool servers: filesystem, git, bash, Lean REPL/LSP, mathlib - Supports multi-node execution via SLURM - Configurable LLM backends (Claude Opus 4.6, GPT, Gemini)

Key quotes from Levie (via X/LinkedIn, reported across multiple outlets):

Scale (May 2026): - 26 books - 630,999 total lines of code (483,917 lines of Lean, excluding comments/blanks) - 46,203 declarations, 42,837 proved (92.7%) - 2,855 / 4,007 statements formalized (71.3%) - 183,157M tokens consumed

(LinkedIn source blocked; synthesized from Columbia Business School event, Fortune reporting, and Forbes coverage of Chatterji's research)

Key features: - Live presence for agents and humans in the same document - Comments, suggestions, and provenance tracking - Integrates via MCP/skill install with Claude Code, Codex, OpenClaw - Designed for pre-implementation work: scoping, planning, spec review - Free, no login required - Uses X-Agent-Id headers for agent identity in presence

Core idea: Recursive Reasoning Models (RRMs) use repeated computation to refine a persistent latent state rather than append new elements to an output sequence. This decouples reasoning depth from both parameter scale and output length: a compact model can perform many steps of internal computation by repeatedly applying shared transition functions

Key highlights from the podcast discussion: - "AI makes experts more valuable. When everyone can produce a decent first draft, the floor rises, but so does the amount of comparable content." - "The goalposts will keep moving. Models improve exponentially on benchmarks precisely because benchmarks are fixed frames. Humans remain indispensable becaus

Core argument: "AI commoditizes the residue of human expertise. Whatever can be made explicit enough to train on. That collapses the value of default model output and creates demand for what's different. Demand for what's different is demand for human experts, even as we approach artificial general intelligence."

The problem AI-assisted engineering amplifies: "The prompt you give to the agent is the de-facto requirement now. Every vague prompt produces a vague spec or plan, and the AI agent implementing that spec produces code full of undisclosed decisions made on your behalf, without your awareness or agreement."