🔥 TOP SIGNAL

Simon Willison dropped a high-leverage pattern for agent-heavy codebases: have the coding agent generate interactive/animated explanations of how code works to pay down “cognitive debt” (the “black box” feeling you get when agent-written internals stop being intuitively understandable) simonwillison. His concrete loop: generate a linear walkthrough, then reuse that walkthrough as context to ask for an animation—ending in a playable demo you can inspect and tweak simonwillison.

🛠️ TOOLS & MODELS

• Claude Code — Remote Control now for Pro: /remote-control is now available to all Pro users@_catwu. The intent: start sessions locally in terminal and continue from your phone without breaking flow @noahzweben.

• Model routing in a real tmux setup (DHH)

  • Layout: OpenCode + Kimi K2.5 (via Fireworks AI) on top, Claude Code (danger mode) on bottom @dhh +1.
  • Personal router: start “almost all agent tasks” with Kimi for speed, then ask Claude for second opinion / harder work @dhh.
  • Omarchy 3.4 launcher: tdl c cx (Tmux Developer Layout + OpenCode + Claude Code) @dhh.

• Codex vs Claude (early practitioner signal)

  • Uncle Bob Martin: “Codex is definitely faster and probably smarter than Claude” (initial use) @unclebobmartin.
  • Tibo Sottiaux: “Codex is now starting to be associated to speed” @thsottiaux.

• Verification-first framing (Addy Osmani): argues the “unsolved problem isn’t generation but verification,” making engineering judgment the highest-leverage skill @addyosmani. Also frames the next step as moving from writing code to orchestrating systems that write code (“building the factory”) @addyosmani.

💡 WORKFLOWS & TRICKS

• Turn walkthroughs into animations (Willison’s loop)

  1. Have the agent produce a linear walkthrough of an unfamiliar codebase simonwillison.
  2. Paste that walkthrough into a new agent session and request an animated explanation of the hard-to-intuit part simonwillison.
  3. Use the result as an explorable artifact (his example shows spiral placement + collision checks for each word) simonwillison.

• Prompt formatting that reliably improves agent output: use checklists (ThePrimeagen)

  • “Hey review every file and tell me …” → “always sucks” @ThePrimeagen.
  • Rewrite as a checklist (e.g., “review every file and gather context” then “tell me about …”) because “llms LOVE checklists” @ThePrimeagen.

• Put stable intent above fast-changing implementation (swyx + replies)

  • swyx: prompt engineering is evolving toward “Specification Engineering”—encoding intents/goals/principles as agents get more autonomous @swyx.
  • Reply synthesis: separate what you want (task) from how (models/tools/strategies that keep changing) @dbreunig +1.

• Write-code-is-cheap ⇒ testing/QA becomes the choke point (Theo)

  • Theo’s claim: “Lines of code effectively are free now… Tests matter” Theo - t3․gg.
  • He describes a feature pipeline where you can now skip from “user problem” straight to code via an agent (e.g., screenshot → Claude Code → fix), destroying the old funnel—but leaving review, testing, and release as the real constraints Theo - t3․gg.

• Agent-run “company OS” pattern (Pulsia)

  • Product claim: Pulsia is “an AI that builds and runs companies autonomously,” covering product coding, marketing, emails, Meta ads, and competitive research Latent Space.
  • Nightly loop: a “CEO” instance decides which task to do, executes, and emails a morning summary + next plan; users steer via email/dashboard Latent Space.
  • Scale signals: “91k human messages” and users averaging “15 messages per day” Latent Space.
  • Infra note: founder uses Neon because it’s pay-as-you-go and “very agent friendly” for spinning up and killing databases Latent Space.

👤 PEOPLE TO WATCH

• Simon Willison — keeps turning agent usage into durable patterns, now with “interactive explanations” as an antidote to cognitive debt simonwillison.
• DHH — valuable for operator-grade setups (tmux + two-agent stack + model routing + exact launcher command) @dhh +1.
• Addy Osmani — consistently sharp about where the work is shifting: verification/judgment and “factory model” orchestration @addyosmani.
• Theo (t3.gg) — one of the clearest (and most polarizing) narrators of the “code is cheap; shipping isn’t” transition Theo - t3․gg.
• Miguel Grinberg — governance/attribution reality check: CPython has commits co-authored by the claude GitHub user, implying LLM usage is allowed (explicitly or via lack of prohibition) miguelgrinberg.

🎬 WATCH & LISTEN

1) Theo (t3.gg) — “lines of code are free; tests matter; the pipeline is destroyed” (≈21:20–25:31)

A crisp articulation of why agent coding compresses everything before code-writing—and why review/QA becomes the bottleneck.

📊 PROJECTS & REPOS

• Interactive explanations (guide chapter) — Willison’s write-up + example-driven pattern simonwillison: https://simonwillison.net/guides/agentic-engineering-patterns/interactive-explanations/@simonw
• Rust wordcloud research repo + artifacts (Willison)
  • Code/report: https://github.com/simonw/research/tree/main/rust-wordcloudsimonwillison
  • Walkthrough artifact: https://github.com/simonw/research/blob/main/rust-wordcloud/walkthrough.mdsimonwillison
  • Interactive demo result: https://tools.simonwillison.net/animated-word-cloudsimonwillison
• Factory model (long-form) — Osmani’s write-up @addyosmani: https://addyosmani.com/blog/factory-model/@addyosmani

Editorial take: Today’s through-line: generation is abundant—the winning workflows convert that into shipped value by upgrading specs, explanation artifacts, and verification loops@addyosmani +2.