You Own an Asset You've Never Scored
The file your agent reads first is capital. Score it out of sixteen, fix the thinnest mark, and run the one check that tells you whether the spec, not the model, was your limit.
The archive
Everything
we have published
Long-form analyses about where value migrates as the layer underneath commoditises. Investments, AI systems, knowledge architecture, durable design.
- Entries
- 76
- Reading
- 11 h 39
- Subjects
- 7
- Built on
- 36
- Sourced
- 10
◈ Where to start 6 paths
Show the routes 6 paths
-
I 5 essays · 56 min
Deciding whether to trust an agent
You are about to put an autonomous system somewhere it can do damage. Five pieces, in the order that builds the check.
-
II 5 essays · 48 min
Why your benchmark is lying to you
Every number on your dashboard was produced by something. This is what each one is actually measuring.
The sequence
-
III 5 essays · 48 min
Building an agent that gets better
The model is the part you cannot change. Five pieces on the parts you can.
-
IV 5 essays · 58 min
Where the money actually lands
Everyone can see the buildout. Far fewer can say which layer of it keeps the return.
The sequence
-
V 5 essays · 58 min
What the machine is doing to you
The capability arrived. Five pieces on what it quietly took on the way in.
The sequence
-
VI 5 essays · 37 min
Learning the lens itself
The terms this publication runs on, then the two pieces that put them to work.
The sequence
- The Lens Lexicon 2 min
- The Substrate Map 2 min
- The Five Laws of Durable Systems 5 min
- The Forest Floor Is The Product 20 min
- You Can Win the Wrong Game for Years 8 min
Filter 76 entries
About
You get
Time
Evidence
By lanethe publication's own series, for readers who know it
/
2026·09
-
-
Show It an Example
Why 'make it distinctive' gets you the least distinctive thing there is, and what to paste instead.
-
Ask for the Step Before the Answer
Before you trust an AI answer you cannot check, ask for the step it was built from.
-
You Can Win the Wrong Game for Years
You usually cannot tell whether you are playing the wrong game. Write down what would prove it, and by when.
-
The Planes That Didn't Come Back
Success stories and the antiques that outlasted the rest. Your evidence was filtered by what survived to reach you.
-
Your Verification Budget Is Backwards
You can't check everything your agents produce, so you're already triaging. Most of us spend the effort where checking is easy, which is rarely where a mistake is expensive.
-
The Extra Lane Fills Itself
Wider roads, faster teams, more appointments. Add room to a queue that turned people away and demand rushes back.
-
The Option You Were Never Meant to Buy
The weak rival, the overpriced tier, the house shown first. The option you never choose can change what you pick.
2026·08
-
The Skill That Never Fired
A Claude skill can fail two ways: its instructions are wrong, or Claude never picks it. Anthropic's own tooling scores whether one skill fires. This tests it against the neighbour that can quietly win its requests, with a small routing eval you run yourself.
-
The Graph Looks Right. The Merge Is Where It Breaks.
A multi-agent graph can lose a verdict with no error and nothing turning red. The bug is one line in the state schema.
-
Everyone Got Safer. That's the Problem.
Safety has two numbers: how often each system fails, and whether they fail together. The field has spent years driving the first one down while almost no dashboard reports the second.
-
You Built a Number You Will Not Trust
Some things you build get graded by the world. Some only ever hand you back your own guess wearing a decimal. Telling the two apart before you start is the cheapest hour you will spend.
-
The Work That Comes Due After You Leave
A checklist can only confirm the steps you remembered to put on it. The one you forgot is caught by a record you did not write.
-
It Will Never Think Less of You
What telling AI the things you can't tell anyone quietly does to being known.
-
Confidently Wrong
The effort you're handing to AI was doing two hidden jobs. Skip them and you get faster, weaker, and blind to your own mistakes.
-
A Green Score Is Not Evidence
A groundedness metric scored its best with the evidence removed. The way to tell whether your model is actually using its evidence is to change the evidence and watch what moves in the answer.
-
The Limit Said 10. The Loop Made 500 Calls.
Your limit counts one cycle. The one that runs away is another. Here is how to tell them apart.
-
You Reach Before You Think
What leaning on AI for every small decision quietly does to your own judgement.
-
You Were Never the Customer
The free app, the free inbox, the free feed. Someone pays for each, and that changes what it is.
-
Stop Re-Priming Claude Code by Hand
The context you paste at the start of every session, put into one file you invoke with /prime.
-
The Setting You Never Changed
The pre-ticked box, the factory setting, the plan already selected. Someone chose each one before you did.
-
The Guardrail Your Agent Can Reach
Most guardrails end up with an escape hatch. Check whether the thing you are constraining can reach yours.
-
The Average Is Nobody's Result
Of 255 studies on AI-assisted colonoscopy, 21 split the result by who held the scope. They disagree.
-
You Cannot Try to Fall Asleep
Sleep is only where you notice it first. Much of what matters works the same way.
-
Your Robot Coworker Is Still a Pilot
Built, shipped, installed, working: four counts, quoted as one. Almost nobody publishes the fourth.
2026·07
-
The Most Expensive AI Errors Are Made of True Numbers
Two months auditing an AI research agent. Nine ways a true number lies, and the check that catches each.
-
Your AI Stack Has Three Bugs Other Fields Already Fixed
Your benchmark, your model jury, your agent swarm: three old structures, and the obvious fix is usually wrong.
-
Your AI Looks Best Where You Can Check It Least
When the first failure is terminal, you cannot iterate your way back.
-
The Difficulty You're Escaping Was Making You
AI can lift the effort out of almost anything you find hard. Some of that effort was the thing turning you into someone.
-
Your Tests Pass. So What?
A green suite only proves your agent cleared the gate. Mutation testing shows whether the tests behind it can bite.
-
Where Your Metrics Fold
A metric can be perfectly accurate and still hide the distinction your decision depends on.
-
◑ PROOF & TRUST TEST · 2026·07·11 Your Research Agent Cites Sources It Never Read
The same trap has killed pricing models and trading desks for decades. One move tells you if your number is next.
-
Your Multi-Agent System Is an Org Chart
Cognition said don't build them. Anthropic said do. A year on, they converge on the one question that decides it.
-
◑ SYSTEMS & LAWS FIG · 2026·07·01 Your Benchmark Measures a Sprint. Your Agent Runs a Marathon.
An open model looks frontier-grade on the coding leaderboard. On a long job, it does half the leader's work.
2026·06
-
Never Let Claude Code Tell You It's Done
A test the agent can't talk its way past, wired to run itself.
-
◑ SYSTEMS & LAWS FIG · 2026·06·28 How Long Until Your AI Edge Stops Paying?
You adopted AI everywhere and it still didn't pay. The scarce layer keeps the money, until its clock runs out.
-
Ten Lines of Code Scored 100%. One Agent Broke Eight Benchmarks.
Not one task was actually solved, and the same blind spot is sitting in your own dashboard.
-
The Safe Parts of Your Job Are the First to Go
The parts of your job with a method feel the safest. A method is the first thing a machine learns.
-
The Seven-Layer Agent Audit
Your agent is starved on one layer of seven. It is rarely the harness everyone argues about.
-
The Cheaper Fix You Keep Skipping
What looks like a deficit is usually good capability, aimed at the wrong target. The cheapest fix is the one nobody can sell you.
-
◑ PROOF & TRUST TEST · 2026·06·15 How Reliable Is Your AI Agent?
A month running an autonomous agent. Everyone who does comes back having built the same thing: a verifier.
-
Self-Improvement Is Release Engineering
Your agent can rewrite its own memory and skills overnight. The hard part is whether you can see what changed and take it back. That makes self-improvement a release-engineering problem.
-
Skills Are Package Management for Your AI
There are more than 1.6 million you can install. You need about twenty. Software already solved that problem once.
-
Right About AI, Wiped Out Anyway
AI is real. The open question is whether the companies spending $725 billion on it live to collect.
-
Remembers Everything, Learns Nothing
You gave your agent a memory and it still repeats the same mistake. What makes it improve is a loop that tests each failure and turns the ones that recur into procedures.
-
You Only Hold Four Thoughts
Working memory tops out around four things at once. Every leap in human intelligence has come from storing the rest outside your head, and the most advanced AI systems get their gains the same way.
-
The Other Half of Compute
Everyone is counting gigawatts and GPUs. The number that decides the return is what each one actually buys.
-
The Stable Liar
Every metric you optimise quietly stops measuring what you meant. The dangerous ones never break. They keep reporting green while the thing underneath rots.
-
Your Tools Got Powerful. Get Boring.
The most powerful tools in history reward the most boring strategies. The gap widens every time they improve.
2026·05
-
◑ AI & WORK PROC · 2026·05·30 Same Model, Different Product: The Case for Harness Engineering
Harness engineering, the code wrapped around an AI model, now drives more of the performance gap than the model you pick.
-
◑ SYSTEMS & LAWS FIG · 2026·05·26 The Leverage Hierarchy of Agent Engineering
Donella Meadows ranked twelve places to intervene in a system. Most agent teams spend their hours at the bottom of the ladder.
-
◑ MARKETS & POWER MKT · 2026·05·26 Three Hidden Bottlenecks the AI Buildout Has Already Moved Past GPUs
NVIDIA's GPU shipments are not the binding constraint anymore. The supply chain has voted on what comes next.
-
◑ MARKETS & POWER MKT · 2026·05·21 NVDA Q1 FY2027: The Networking Number That Changes the Story
NVIDIA Q1 FY2027 revenue hit $81.6B (+85% YoY) — but the real story is networking revenue surging 199% as the AI bottleneck migrates from GPUs to interconnects.
-
◑ THE HUMAN LAYER OBS · 2026·05·19 Access Is Not Agency
The tool is not the authority. Teams add connectors before defining what the agent is allowed to change. That is not agency, it is reach with a larger blast radius.
-
◑ SYSTEMS & LAWS FIG · 2026·05·09 Your AI Agent Stack Is Solving The Wrong Problem
The real setup is not MCP servers, skills, memory files, and subagents. It is the contract stack that decides what an agent may know, do, prove, escalate, and lose.
-
◑ SYSTEMS & LAWS FIG · 2026·05·07 The Engine Underneath Hard Decisions
Eight stages turn hidden structure into durable knowledge. Most teams run three of them and call it understanding. The other five are where compounding hides.
-
◑ SYSTEMS & LAWS FIG · 2026·05·06 The Five Laws of Durable Systems
What still has a job after the change? Five tests for seeing what is likely to survive.
-
◑ MARKETS & POWER MKT · 2026·05·05 The SpaceX IPO Is Not What You Think You're Buying
The filing will not just price rockets. It will reveal which layer public investors actually own.
-
◑ THE HUMAN LAYER OBS · 2026·05·04 AI Made You Faster. It Did Not Make You Safer.
The strange thing about the AI productivity boom is that the people getting faster are not always getting more secure. Speed is becoming the surface. Proof is moving somewhere else.
-
◑ SYSTEMS & LAWS FIG · 2026·05·03 The 90-Day Canopy Audit
A roadmap can look productive while most of the work is easy to displace. Run the Substrate Map on the last 90 days and force the next planning decision to change.
-
◑ SYSTEMS & LAWS FIG · 2026·05·02 Start Here: What Survives When The Surface Changes?
A short front door to the publication: the lens, the instruments you can run now, and the reader paths.
-
◑ SYSTEMS & LAWS FIG · 2026·05·02 The Lens Lexicon
A free two-page reference card defining the ten load-bearing terms behind the durability lens, with tests, examples, and common confusions.
-
What Proves You Can Think?
AI did not just make output cheap. It broke the old contract between effort, competence, and trust. The next scarce signal is proof of judgement under conditions where the surface itself can be faked.
-
◑ PROOF & TRUST TEST · 2026·05·01 Most Verification Is Just Bigger Classification
A confidence score is not evidence. If your eval cannot produce a replayable artefact, it will fail the moment the system can respond to being measured.
-
◑ THE HUMAN LAYER OBS · 2026·05·01 Taste Is What You Delete
Generation got cheap. The scarce skill is knowing what to cut.
-
The Displacement Rate Audit
A five-minute scoring tool for any product, position, architecture, business model, or career bet. Find out what still works after the environment changes.
-
◑ SYSTEMS & LAWS FIG · 2026·05·01 The Substrate Map
A free one-page taxonomy and 10-minute exercise for finding the substrate-vs-canopy ratio in your last 90 days of work.
2026·04
-
◑ MARKETS & POWER MKT · 2026·04·30 PLTR: The AI Stock That Has To Prove It Owns The Permission Layer
A bull/bear thesis for Palantir: not whether AI demand is real, but whether Palantir owns the permission layer between model capability and real-world action.
-
◑ MARKETS & POWER MKT · 2026·04·26 Right Company, Wrong Vector
A pick is a number. A position is a vector. The post-mortem language we have only knows how to blame the company.
-
◑ MARKETS & POWER MKT · 2026·04·24 The Investor's Substrate Test
Score the substrate beneath any single position in seven minutes. A 5-axis profile and a 0-10 score for any holding. Free.
-
◑ SYSTEMS & LAWS FIG · 2026·04·23 The Forest Floor Is The Product
Most people are optimising for canopy. The work that survives the next five AI releases is built from the forest floor up.
-
◑ PROOF & TRUST TEST · 2026·04·19 You're Not Comparing Models. You're Comparing Contracts.
Agent benchmarks don't measure models. They measure contracts. Two teams running the same model can publish different scores, and both can be honest.
-
◑ AI & WORK PROC · 2026·04·17 Prompting Isn't Writing, It's Compilation
If you treat the prompt as a spec and the model as a renderer, quality stops coming from more words and starts coming from better constraints.
-
◑ STRATEGY & MOATS POS · 2026·04·14 The Model Is Not the Moat
If frontier capability keeps centralising, the durable edge shifts outward into trust, workflow fit, and the surrounding package.
-
◑ SYSTEMS & LAWS FIG · 2026·04·05 I Read 3,000 Papers Across 12 Fields. Five Patterns Kept Appearing.
Every field discovers them independently. Nobody connects them.
-
◑ SYSTEMS & LAWS FIG · 2026·04·05 Is This Difficulty Load-Bearing?
Before you automate anything, ask what the friction was actually doing.
Found in the text
2026·09·21 You Own an Asset You've Never Scored Agents A lens 7 min 2026·09·17 Show It an Example Agents A lens IV 4 min 2026·09·16 Ask for the Step Before the Answer Evidence A lens IV 4 min 2026·09·14 You Can Win the Wrong Game for Years Value A lens ◈ 8 min 2026·09·09 The Planes That Didn't Come Back Design Mechanism 4 min 2026·09·04 Your Verification Budget Is Backwards Evidence A lens V 3 min 2026·09·02 The Extra Lane Fills Itself Design Mechanism 6 min 2026·09·01 The Option You Were Never Meant to Buy Design Mechanism 5 min 2026·08·31 The Skill That Never Fired Agents Run it 14 min 2026·08·30 The Graph Looks Right. The Merge Is Where It Breaks. Agents Autopsy ◈ 13 min 2026·08·28 Everyone Got Safer. That's the Problem. Evidence Mechanism ◈ A 13 min 2026·08·28 You Built a Number You Will Not Trust Work Argued V 8 min 2026·08·25 The Work That Comes Due After You Leave Work Argued IV 9 min 2026·08·24 It Will Never Think Less of You Work Argued II 4 min 2026·08·23 Confidently Wrong Work Argued ▲2 ◈ II 10 min 2026·08·21 A Green Score Is Not Evidence Evidence Measured ▲4 ◈ 8 min 2026·08·16 The Limit Said 10. The Loop Made 500 Calls. Agents Run it ◈ 14 min 2026·08·12 You Reach Before You Think Work Argued V 3 min 2026·08·11 You Were Never the Customer Design Mechanism 5 min 2026·08·10 Stop Re-Priming Claude Code by Hand Agents Run it IV 9 min 2026·08·09 The Setting You Never Changed Design Mechanism ▲2 5 min 2026·08·08 The Guardrail Your Agent Can Reach Agents Run it ◈ IV 21 min 2026·08·04 The Average Is Nobody's Result Evidence Measured ◈ IV 22 min 2026·08·03 You Cannot Try to Fall Asleep Work Argued ◈ A 7 min 2026·08·01 Your Robot Coworker Is Still a Pilot Evidence Measured ◈ IV 15 min 2026·07·27 The Most Expensive AI Errors Are Made of True Numbers Evidence Autopsy ▲1 IV 10 min 2026·07·25 Your AI Stack Has Three Bugs Other Fields Already Fixed Agents A lens IV 10 min 2026·07·24 Your AI Looks Best Where You Can Check It Least Evidence A lens ▲5 V 10 min 2026·07·17 The Difficulty You're Escaping Was Making You Work Argued ▲5 II 16 min 2026·07·14 Your Tests Pass. So What? Agents Run it IV 20 min 2026·07·12 Where Your Metrics Fold Evidence A lens ▲3 IV 7 min 2026·07·11 Your Research Agent Cites Sources It Never Read Evidence Autopsy ▲2 I 9 min 2026·07·07 Your Multi-Agent System Is an Org Chart Agents A lens ▲1 I 11 min 2026·07·01 Your Benchmark Measures a Sprint. Your Agent Runs a Marathon. Evidence Measured ▲1 I 10 min 2026·06·29 Never Let Claude Code Tell You It's Done Agents Run it ▲6 IV 10 min 2026·06·28 How Long Until Your AI Edge Stops Paying? Value A lens I 10 min 2026·06·23 Ten Lines of Code Scored 100%. One Agent Broke Eight Benchmarks. Evidence Measured ▲3 A 12 min 2026·06·20 The Safe Parts of Your Job Are the First to Go Work A lens ▲2 I 10 min 2026·06·17 The Seven-Layer Agent Audit Agents A card ▲2 I 13 min 2026·06·16 The Cheaper Fix You Keep Skipping Value A lens ▲2 I 8 min 2026·06·15 How Reliable Is Your AI Agent? Agents A lens ▲9 IV 11 min 2026·06·09 Self-Improvement Is Release Engineering Agents A lens ▲2 III 7 min 2026·06·07 Skills Are Package Management for Your AI Agents A lens ▲5 III 7 min 2026·06·06 Right About AI, Wiped Out Anyway Markets Position I 8 min 2026·06·05 Remembers Everything, Learns Nothing Agents A lens ▲1 II 12 min 2026·06·04 You Only Hold Four Thoughts Thinking Mechanism ▲1 I 8 min 2026·06·03 The Other Half of Compute Markets Position ▲3 I 9 min 2026·06·02 The Stable Liar Evidence A lens ▲5 A 11 min 2026·06·01 Your Tools Got Powerful. Get Boring. Value A lens ▲3 I 8 min 2026·05·30 Same Model, Different Product: The Case for Harness Engineering Agents A lens ▲9 IV 11 min 2026·05·26 The Leverage Hierarchy of Agent Engineering Agents A lens ▲4 II 6 min 2026·05·26 Three Hidden Bottlenecks the AI Buildout Has Already Moved Past GPUs Markets Position ▲2 I 11 min 2026·05·21 NVDA Q1 FY2027: The Networking Number That Changes the Story Markets Position I 4 min 2026·05·19 Access Is Not Agency Work Argued 13 min 2026·05·09 Your AI Agent Stack Is Solving The Wrong Problem Agents A lens ▲1 11 min 2026·05·07 The Engine Underneath Hard Decisions Thinking Mechanism 6 min 2026·05·06 The Five Laws of Durable Systems Thinking A card ▲2 5 min 2026·05·05 The SpaceX IPO Is Not What You Think You're Buying Markets Position ▲1 18 min 2026·05·04 AI Made You Faster. It Did Not Make You Safer. Work Argued ▲1 16 min 2026·05·03 The 90-Day Canopy Audit Value A card 8 min 2026·05·02 Start Here: What Survives When The Surface Changes? Value Mechanism ▲10 6 min 2026·05·02 The Lens Lexicon Thinking A card 2 min 2026·05·02 What Proves You Can Think? Work Argued ▲1 13 min 2026·05·01 Most Verification Is Just Bigger Classification Evidence A lens ▲6 16 min 2026·05·01 Taste Is What You Delete Work Argued ▲1 9 min 2026·05·01 The Displacement Rate Audit Value A card 2 min 2026·05·01 The Substrate Map Value A card 2 min 2026·04·30 PLTR: The AI Stock That Has To Prove It Owns The Permission Layer Markets Position 10 min 2026·04·26 Right Company, Wrong Vector Markets A lens 14 min 2026·04·24 The Investor's Substrate Test Markets A card ▲1 2 min 2026·04·23 The Forest Floor Is The Product Value A lens ▲5 20 min 2026·04·19 You're Not Comparing Models. You're Comparing Contracts. Evidence A lens 9 min 2026·04·17 Prompting Isn't Writing, It's Compilation Agents A lens 6 min 2026·04·14 The Model Is Not the Moat Value A lens 3 min 2026·04·05 I Read 3,000 Papers Across 12 Fields. Five Patterns Kept Appearing. Thinking Mechanism 7 min 2026·04·05 Is This Difficulty Load-Bearing? Thinking A card 1 min
Nothing filed under that strand yet.
◇ By idea 13 terms
-
Harness The code wrapped around a model. The part of the performance you control. 18
- Show It an Example 4 min
- The Limit Said 10. The Loop Made 500 Calls. 14 min
- The Guardrail Your Agent Can Reach 21 min
- Your Multi-Agent System Is an Org Chart 11 min
- Your Benchmark Measures a Sprint. Your Agent Runs a Marathon. 10 min
- How Long Until Your AI Edge Stops Paying? 10 min
- Ten Lines of Code Scored 100%. One Agent Broke Eight Benchmarks. 12 min
- The Seven-Layer Agent Audit 13 min
- The Cheaper Fix You Keep Skipping 8 min
- How Reliable Is Your AI Agent? 11 min
- Skills Are Package Management for Your AI 7 min
- Remembers Everything, Learns Nothing 12 min
-
Load-bearing Difficulty that is producing the result, not sitting next to it. 17
- Confidently Wrong 10 min
- The Difficulty You're Escaping Was Making You 16 min
- Your Tests Pass. So What? 20 min
- Your Research Agent Cites Sources It Never Read 9 min
- Never Let Claude Code Tell You It's Done 10 min
- Self-Improvement Is Release Engineering 7 min
- Remembers Everything, Learns Nothing 12 min
- Three Hidden Bottlenecks the AI Buildout Has Already Moved Past GPUs 11 min
- NVDA Q1 FY2027: The Networking Number That Changes the Story 4 min
- Your AI Agent Stack Is Solving The Wrong Problem 11 min
- AI Made You Faster. It Did Not Make You Safer. 16 min
- Start Here: What Survives When The Surface Changes? 6 min
-
Substrate The parts of a system that compound regardless of what changes around them. 11
- Everyone Got Safer. That's the Problem. 13 min
- The Seven-Layer Agent Audit 13 min
- The SpaceX IPO Is Not What You Think You're Buying 18 min
- The 90-Day Canopy Audit 8 min
- Start Here: What Survives When The Surface Changes? 6 min
- The Lens Lexicon 2 min
- The Displacement Rate Audit 2 min
- The Substrate Map 2 min
- Right Company, Wrong Vector 14 min
- The Investor's Substrate Test 2 min
- The Forest Floor Is The Product 20 min
-
Verifier The check that decides whether an agent’s output is allowed to count. 8
- Your Research Agent Cites Sources It Never Read 9 min
- Your Benchmark Measures a Sprint. Your Agent Runs a Marathon. 10 min
- Ten Lines of Code Scored 100%. One Agent Broke Eight Benchmarks. 12 min
- How Reliable Is Your AI Agent? 11 min
- Self-Improvement Is Release Engineering 7 min
- AI Made You Faster. It Did Not Make You Safer. 16 min
- What Proves You Can Think? 13 min
- Most Verification Is Just Bigger Classification 16 min
-
Canopy The parts of a system that get repriced or reset when the surroundings change. 7
- The 90-Day Canopy Audit 8 min
- Start Here: What Survives When The Surface Changes? 6 min
- The Lens Lexicon 2 min
- The Displacement Rate Audit 2 min
- The Substrate Map 2 min
- The Investor's Substrate Test 2 min
- The Forest Floor Is The Product 20 min
-
Context window What the model can hold at once, and therefore what it can reason across. 7
- The Skill That Never Fired 14 min
- The Guardrail Your Agent Can Reach 21 min
- Your AI Stack Has Three Bugs Other Fields Already Fixed 10 min
- Your Multi-Agent System Is an Org Chart 11 min
- The Seven-Layer Agent Audit 13 min
- Same Model, Different Product: The Case for Harness Engineering 11 min
- The Leverage Hierarchy of Agent Engineering 6 min
-
Goodhart What happens to a measure once it becomes the target. 7
- You Own an Asset You've Never Scored 7 min
- Everyone Got Safer. That's the Problem. 13 min
- A Green Score Is Not Evidence 8 min
- Your AI Looks Best Where You Can Check It Least 10 min
- Where Your Metrics Fold 7 min
- Ten Lines of Code Scored 100%. One Agent Broke Eight Benchmarks. 12 min
- The Stable Liar 11 min
-
Disturbance A rare event that resets a system, distinct from the ordinary variation it absorbs. 6
-
Guardrail A constraint on an agent, which only holds if the agent cannot reach it. 5
-
Displacement rate How much of what you have built will still be working after a specific large change in its environment. 3
-
Old-growth Work or systems that have compounded long enough to support entirely new dependent layers above them. 2
- The Lens Lexicon 2 min
- The Forest Floor Is The Product 20 min
-
Pioneer species The first arrivers after disturbance, who prepare the ground for everything that follows but rarely capture what they enable. 2
- The Lens Lexicon 2 min
- The Forest Floor Is The Product 20 min
-
Succession The predictable order in which a system rebuilds after disturbance. 2
- The Lens Lexicon 2 min
- The Forest Floor Is The Product 20 min
Definitions, tests and the confusions each term is usually mistaken for: the Lens Lexicon.
↓ Take it with you
- The feed Full text, not extracts. Every essay arrives whole in your reader.
- Offline Anything you save on an essay page stays readable with no connection.
- One plain-text file The whole archive as text, for a model, a grep, or your own notes.
- Your reading record Export what this browser knows and import it on another device. It never leaves your machine.
- The claim ledgers Every sourced claim, and the ones struck before publication.
- Corrections What changed after publication, and why.