Resources I Love

A coding agent is six functions in a trenchcoat

Hadley Wickham demystifies coding agents (Claude Code, Cursor, Codex) by building a minimal one in R with ellmer. The core is just six tools — read file, write file, edit file, list files, search, run command — plus a system prompt. Also covers path safety and why a targeted edit tool beats full file rewrites.

How to Give Your Exhausted Prefrontal Cortex a Break

On "frontal fatigue" — how modern life (digital tech, decision overload, the loss of tradition as a guide) is stressing the prefrontal cortex in historically new ways, and what primary sensory experiences can do to restore it.

First time hearing about PFC dysfunction as a framing. The three red flags are useful — attention span collapsing, tip-of-the-tongue word loss, and surprising irritability — all signs the PFC is overtaxed, not just tiredness.

Agent coordination has a real cost that scales with task sequentiality

via Many Agents, Many Problems — Linear Digressions

Hadley Wickham's honest framework for holding AI's benefits and harms together

via Returning to life! — Hadley Wickham

The ideal ratio is 20% consuming, 80% thinking — most of us have it backwards

via The AirPods Effect

Temperament matters more than talent in AI research

via Zen and the Art of Machine Learning Research — Jack Morris

Digital tech is stressing the prefrontal cortex in ways new to humanity

via How to Give Your Exhausted Prefrontal Cortex a Break — Markham Heid

"They screwed us": Personality clashes sent Anthropic's models offline

Simon Willison's commentary on an Axios piece — the best behind-the-scenes account of the US government export control story that took Fable and Mythos offline.

Your LLM can't math (and that's ok)

Hadley Wickham refines the agent definition by clarifying that tools run in the harness, not the model — and uses math as the concrete example. LLMs are confidently wrong at arithmetic, but harnesses can supply a calculator tool. Also covers how web chat harnesses quietly provide web search, page fetch, memory, and image generation.

Many Agents, Many Problems (The Agents Season, Ep. 7)

Why scaling up multi-agent AI systems doesn't deliver proportional benefits — collaboration turns out to be a distinct capability, and adding agents to sequential tasks often makes things worse.

Loved the exploration of coordination cost — the idea that agents communicating and handing off work isn't free, and that overhead often swamps any gains from parallelism.

What is an agent?

Hadley Wickham builds up the definition of an agent from first principles — conversations, turns, tools, harnesses — landing on "an LLM in a harness that calls tools repeatedly in a loop." A clear technical explainer for a term that's everywhere but rarely unpacked.

Great bottom-up explainer. Hadley's definition ("LLM in a harness, calling tools in a loop") is more detailed than Simon Willison's earlier "runs tools in a loop to achieve a goal" (https://simonwillison.net/2025/Sep/18/agents/) — interesting to see how the concept has accumulated vocabulary as the field matures.

Returning to life!

Hadley Wickham relaunches his Substack to write about AI — a genuinely conflicted take that acknowledges both the excitement (programming accessibility, wide and shallow expertise) and the harms (copyright theft, wealth concentration, intellectual laziness) without collapsing into a take.

The excited/harm framing is what makes this worth reading — programming accessibility, voice input, and wide/shallow expertise as genuine wins, alongside copyright and wealth concentration as real costs. Rare to see someone acknowledge both sides without collapsing into a take.

The AirPods Effect

How constant personal audio is quietly reshaping our social lives — earbuds reinforce insecurities, narrow our information diets, and pull us further apart in public spaces.

Zen and the Art of Machine Learning Research

Temperament matters more than talent in AI research — a meditation on the daily practice of reading and building, and why equanimity is the real prerequisite.

The Zen framing isn't just a metaphor — he quotes Suzuki directly, structures the piece like numbered koans, and the equanimity point is genuinely it: sit with failure the same way you sit with success, neither attached to the outcome.