Scott Clark

Figures

Diagrams and images from the essays, in one place. Open any figure to zoom and pan, follow the link to read it in context, or download it. House diagrams download as SVGs with a copyright line and the link back to their source essay bottom-right; other images download as the original files.

Figures are the work of Scott Clark and are copyright Scott Clark. Each SVG download carries its attribution and the link to its source essay. Reuse terms: below. Machine-readable index: figures.json. Markdown: figures.md.

Reuse

House diagrams (the SVG downloads) are licensed CC BY-ND 4.0: reproduce them unmodified, anywhere, with the attribution footer intact. The download already carries the credit, the source link, and the license. No modified versions: no cropping, re-labeling, or re-branding, and nothing that implies endorsement.

Talk slides and other raster images on these pages are not under that license; they carry third-party marks. Ask before reusing them.

License: CC BY-ND 4.0.

Accelerating Science with AI: Surfing the Frontier Between the Bitter Lesson and No Free Lunch (talk recap)

October 19, 2026 · 44 figures

Title slide: Accelerating Science with AI: Surfing the Frontier Between the Bitter Lesson and No Free Lunch. Scott Clark, Founder and CEO, with the Distributional and Talaria Scientific logos.
Title slide: Accelerating Science with AI: Surfing the Frontier Between the Bitter Lesson and No Free Lunch. Scott Clark, Founder and CEO, with the Distributional and Talaria Scientific logos.In the essayDownload© 2026 Scott Clark
Slide: three takeaways. 1. AI x Science can lead to abundance. 2. Researchers will always have a role. 3. Better tools can accelerate this.
Slide: three takeaways. 1. AI x Science can lead to abundance. 2. Researchers will always have a role. 3. Better tools can accelerate this.In the essayDownload© 2026 Scott Clark
Slide: what abundance with AI actually means, a four-step build: new scientific discoveries, new materials and more efficient energy, advances in medicine, aerospace and more, living in a sci-fi future.
Slide: what abundance with AI actually means, a four-step build: new scientific discoveries, new materials and more efficient energy, advances in medicine, aerospace and more, living in a sci-fi future.In the essayDownload© 2026 Scott Clark
Slide: improving quality of life, not just replacing repetitive work.
Slide: improving quality of life, not just replacing repetitive work.In the essayDownload© 2026 Scott Clark
Slide: we can now meaningfully accelerate science with AI.
Slide: we can now meaningfully accelerate science with AI.In the essayDownload© 2026 Scott Clark
Slide: scale beats cleverness, but specificity beats generality. Rich Sutton, The Bitter Lesson, 2019; Wolpert and Macready, No Free Lunch Theorems for Optimization, 1997.
Slide: scale beats cleverness, but specificity beats generality. Rich Sutton, The Bitter Lesson, 2019; Wolpert and Macready, No Free Lunch Theorems for Optimization, 1997.In the essayDownload© 2026 Scott Clark
Figure: the bitter lesson drawn as a rising wave. Problems arranged left to right by how much evidence exists for ones like them, performance on the vertical axis. Three waterlines, t1 to t3, each generation raising the water and washing further right; specialized methods drawn as narrow peaks, the left ones under water since t2, one held out until t3; past the dashed out-of-distribution line a specialized solver still stands above the waterline.
Figure: the bitter lesson drawn as a rising wave. Problems arranged left to right by how much evidence exists for ones like them, performance on the vertical axis. Three waterlines, t1 to t3, each generation raising the water and washing further right; specialized methods drawn as narrow peaks, the left ones under water since t2, one held out until t3; past the dashed out-of-distribution line a specialized solver still stands above the waterline.In the essayDownload© 2026 Scott Clark
Slide: there will always be a frontier. Surf the wave. Don't climb a static mountain that is about to be washed over.
Slide: there will always be a frontier. Surf the wave. Don't climb a static mountain that is about to be washed over.In the essayDownload© 2026 Scott Clark
Figure: the same wave with two annotations, a gray peak labeled "a static mountain" that the water has already covered, and an amber arrow labeled "surf here" pointing at the edge where the newest waterline meets the out-of-distribution region.
Figure: the same wave with two annotations, a gray peak labeled "a static mountain" that the water has already covered, and an amber arrow labeled "surf here" pointing at the edge where the newest waterline meets the out-of-distribution region.In the essayDownload© 2026 Scott Clark
Slide: we are still a long way from /goal solve stable fusion containment.
Slide: we are still a long way from /goal solve stable fusion containment.In the essayDownload© 2026 Scott Clark
Slide: things that were previously impractical are now achievable.
Slide: things that were previously impractical are now achievable.In the essayDownload© 2026 Scott Clark
Figure: the cost, quality, speed triangle, with the feasible region at its center grown outward past the old edges.
Figure: the cost, quality, speed triangle, with the feasible region at its center grown outward past the old edges.In the essayDownload© 2026 Scott Clark
Figure: the rising wave again, with a callout reading "Use the best of both worlds to push right" and arrows from the top waterline and from the specialized solver toward the right edge.
Figure: the rising wave again, with a callout reading "Use the best of both worlds to push right" and arrows from the top waterline and from the specialized solver toward the right edge.In the essayDownload© 2026 Scott Clark
Slide: I have been trying to solve this problem for the last 20 years of my career, with varying degrees of success.
Slide: I have been trying to solve this problem for the last 20 years of my career, with varying degrees of success.In the essayDownload© 2026 Scott Clark
Slide: whatever the field, the final step was always parameter tuning. A timeline strip: Oregon State, finite elements, 2004 to 2008; UC Davis, protein folding, 2006; Max Planck, quantum, 2007; Cornell PhD, applied math, 2008 to 2012; Los Alamos, metagenomics, 2009; Berkeley Lab and JGI, genome assembly, 2010. Methods for efficient optimization given an objective.
Slide: whatever the field, the final step was always parameter tuning. A timeline strip: Oregon State, finite elements, 2004 to 2008; UC Davis, protein folding, 2006; Max Planck, quantum, 2007; Cornell PhD, applied math, 2008 to 2012; Los Alamos, metagenomics, 2009; Berkeley Lab and JGI, genome assembly, 2010. Methods for efficient optimization given an objective.In the essayDownload© 2026 Scott Clark
Figure: a one-dimensional knob on the horizontal axis, the quantity you care about on the vertical, and a handful of expensive evaluations drawn as dots.
Figure: a one-dimensional knob on the horizontal axis, the quantity you care about on the vertical, and a handful of expensive evaluations drawn as dots.In the essayDownload© 2026 Scott Clark
Figure: the same dots with a Gaussian process fit through them: a mean curve and an uncertainty band that pinches to nothing at the measured points and opens up between them.
Figure: the same dots with a Gaussian process fit through them: a mean curve and an uncertainty band that pinches to nothing at the measured points and opens up between them.In the essayDownload© 2026 Scott Clark
Figure: below the belief, an acquisition curve (expected improvement) scores every point on the knob; its peak marks the next evaluation.
Figure: below the belief, an acquisition curve (expected improvement) scores every point on the knob; its peak marks the next evaluation.In the essayDownload© 2026 Scott Clark
Figure: the new point added, the band collapsed where it was measured, the mean moved, and the acquisition function pointing to the next evaluation.
Figure: the new point added, the band collapsed where it was measured, the mean moved, and the acquisition function pointing to the next evaluation.In the essayDownload© 2026 Scott Clark
Slide: SigOpt, Bayesian optimization as a service. A timeline strip: founding, 2014, with the Y Combinator and Andreessen Horowitz logos; building, 2015 to 2020, with the American Express, Netflix, and OpenAI logos; scaling, 2020 to 2023, with the Intel logo. Optimization at scale for problems that mattered.
Slide: SigOpt, Bayesian optimization as a service. A timeline strip: founding, 2014, with the Y Combinator and Andreessen Horowitz logos; building, 2015 to 2020, with the American Express, Netflix, and OpenAI logos; scaling, 2020 to 2023, with the Intel logo. Optimization at scale for problems that mattered.In the essayDownload© 2026 Scott Clark
Slide: the optimizer worked, except when it didn't. It overfit, or optimized the "wrong" thing.
Slide: the optimizer worked, except when it didn't. It overfit, or optimized the "wrong" thing.In the essayDownload© 2026 Scott Clark
Slide: the best thing about a black box optimizer is that it will optimize anything you tell it to. The worst part about a black box optimizer is that it will optimize exactly what you tell it to.
Slide: the best thing about a black box optimizer is that it will optimize anything you tell it to. The worst part about a black box optimizer is that it will optimize exactly what you tell it to.In the essayDownload© 2026 Scott Clark
Slide: you need to be able to trust the numbers.
Slide: you need to be able to trust the numbers.In the essayDownload© 2026 Scott Clark
Slide: pre-production AI testing, 2023 to 2025. High dimensional Bayesian statistical tests for chaotic and non-stationary AI systems and agents. Stamped: It failed. 1. People didn't know what to test (or have the data before deployment). 2. They couldn't understand tests well enough to act. 3. They shipped to prod anyway.
Slide: pre-production AI testing, 2023 to 2025. High dimensional Bayesian statistical tests for chaotic and non-stationary AI systems and agents. Stamped: It failed. 1. People didn't know what to test (or have the data before deployment). 2. They couldn't understand tests well enough to act. 3. They shipped to prod anyway.In the essayDownload© 2026 Scott Clark
Slide: a second column, post-production agent analytics, 2025 to 2026. Post-production analytics on agent traces to find the evals that you aren't monitoring for. Stamped: It failed. A feature, not a product (let alone a business or a startup).
Slide: a second column, post-production agent analytics, 2025 to 2026. Post-production analytics on agent traces to find the evals that you aren't monitoring for. Stamped: It failed. A feature, not a product (let alone a business or a startup).In the essayDownload© 2026 Scott Clark
Slide: knowing what to measure matters. Trusting what you measure matters.
Slide: knowing what to measure matters. Trusting what you measure matters.In the essayDownload© 2026 Scott Clark
Slide: a third column, computational science harness, 2026 and on. A multi-agent, multi-FM harness for computational science research acceleration, using domain specific guardrails rooted in physics and simulation to ensure trustworthiness.
Slide: a third column, computational science harness, 2026 and on. A multi-agent, multi-FM harness for computational science research acceleration, using domain specific guardrails rooted in physics and simulation to ensure trustworthiness.In the essayDownload© 2026 Scott Clark
Slide: ideas move science forward, but testing them is expensive in researcher time.
Slide: ideas move science forward, but testing them is expensive in researcher time.In the essayDownload© 2026 Scott Clark
Figure: from idea to trusted result, where the week goes. Panel 1, today: the scientist walks the whole span by hand, with the science (ideas, taste, judgment) getting the scraps above a gray band labeled the validation schlep: data wrangling, environments, baselines, sweeps, checking. Caption on the slide: AI is now good at the mechanical middle of research.
Figure: from idea to trusted result, where the week goes. Panel 1, today: the scientist walks the whole span by hand, with the science (ideas, taste, judgment) getting the scraps above a gray band labeled the validation schlep: data wrangling, environments, baselines, sweeps, checking. Caption on the slide: AI is now good at the mechanical middle of research.In the essayDownload© 2026 Scott Clark
Figure: the second panel of the same figure, in the suit: the scientist holds ideas, taste, and judgment end to end, with no schlep between idea and trusted result; below a dashed boundary labeled "judgment is proposed, never assumed", the harness carries the same five mechanical steps plus the full search recorded, adversarial review, and provenance on every run.
Figure: the second panel of the same figure, in the suit: the scientist holds ideas, taste, and judgment end to end, with no schlep between idea and trusted result; below a dashed boundary labeled "judgment is proposed, never assumed", the harness carries the same five mechanical steps plus the full search recorded, adversarial review, and provenance on every run.In the essayDownload© 2026 Scott Clark
Slide: a computational science what-if machine. Start new research from scratch. Respond to reviewers. Convert old academic software. Extend current papers.
Slide: a computational science what-if machine. Start new research from scratch. Respond to reviewers. Convert old academic software. Extend current papers.In the essayDownload© 2026 Scott Clark
Figure: the Talaria architecture. A research loop of five actions, idea, plan, implement, run, synthesize, with supporting actions and gates between them, all depositing into a system of record (references, concepts, hypotheses, results, findings, an append-only event journal) kept as markdown and JSONL in a git repository; record inspection, extra rigor, maintenance, and meta-usage actions hang off the record.
Figure: the Talaria architecture. A research loop of five actions, idea, plan, implement, run, synthesize, with supporting actions and gates between them, all depositing into a system of record (references, concepts, hypotheses, results, findings, an append-only event journal) kept as markdown and JSONL in a git repository; record inspection, extra rigor, maintenance, and meta-usage actions hang off the record.In the essayDownload© 2026 Scott Clark
Slide: receipts. Hypotheses, what you asked, frozen; results, what ran, immutable; findings, what you now believe. Every run pinned to exact code, configuration, and environment, so a rerun is a reproduction. A result with no hypothesis is not allowed to exist, because orphan numbers are how spurious findings start. Kept whether or not it worked. The lab notebook, inverted: a record the work keeps of itself.
Slide: receipts. Hypotheses, what you asked, frozen; results, what ran, immutable; findings, what you now believe. Every run pinned to exact code, configuration, and environment, so a rerun is a reproduction. A result with no hypothesis is not allowed to exist, because orphan numbers are how spurious findings start. Kept whether or not it worked. The lab notebook, inverted: a record the work keeps of itself.In the essayDownload© 2026 Scott Clark
Slide: a mech suit instead of a replacement. The scientist pushes out of distribution, and the model fills in behind. So what can we do with it?
Slide: a mech suit instead of a replacement. The scientist pushes out of distribution, and the model fills in behind. So what can we do with it?In the essayDownload© 2026 Scott Clark
Slide: every field that simulates the physical world keeps a portfolio of models, from the full-fidelity solvers it trusts to the cheap surrogates it can afford. Surrogate: any cheap model standing in for an expensive one. Fidelity: how faithfully it reproduces the metric you care about, in the regime you care about.
Slide: every field that simulates the physical world keeps a portfolio of models, from the full-fidelity solvers it trusts to the cheap surrogates it can afford. Surrogate: any cheap model standing in for an expensive one. Fidelity: how faithfully it reproduces the metric you care about, in the regime you care about.In the essayDownload© 2026 Scott Clark
Figure: a plane with cost per answer on a log scale across and fidelity up. A handful of points: empirical fits and crude heuristics at the cheap end, a few reduced-order models and response surfaces in the middle, full-order solvers at the expensive end; open circles mark hand-built historical one-offs.
Figure: a plane with cost per answer on a log scale across and fidelity up. A handful of points: empirical fits and crude heuristics at the cheap end, a few reduced-order models and response surfaces in the middle, full-order solvers at the expensive end; open circles mark hand-built historical one-offs.In the essayDownload© 2026 Scott Clark
Figure: the same plane with a new row of blue points, neural operators and learned surrogates, filling the cheap-but-decent region the classical stack left empty; cheap per answer once trained, valid where validated.
Figure: the same plane with a new row of blue points, neural operators and learned surrogates, filling the cheap-but-decent region the classical stack left empty; cheap per answer once trained, valid where validated.In the essayDownload© 2026 Scott Clark
Figure: the multi-fidelity loop. Explore with cheap surrogates, exploit what they learn to call the next, costlier rung, verify the answers that matter with the reference solver or the lab; every run lands in the record, cheap or dear, with its provenance, in a model ledger and a run ledger, and the record feeds the next pass.
Figure: the multi-fidelity loop. Explore with cheap surrogates, exploit what they learn to call the next, costlier rung, verify the answers that matter with the reference solver or the lab; every run lands in the record, cheap or dear, with its provenance, in a model ledger and a run ledger, and the record feeds the next pass.In the essayDownload© 2026 Scott Clark
Figure: the same cost-fidelity plane with the frontier drawn as a curve through today's models and a dashed amber curve above it marking where a harness pushes it, with amber circles for the points a harness would add.
Figure: the same cost-fidelity plane with the frontier drawn as a curve through today's models and a dashed amber curve above it marking where a harness pushes it, with amber circles for the points a harness would add.In the essayDownload© 2026 Scott Clark
Slide: the models, validated surrogates on a dense frontier, and the optimizer, the right model per job via multi-fidelity Bayesian optimization. A denser frontier makes a sharper search; the search buys the runs that train and validate the next models; the policy itself can be learned, over surrogates, acquisition functions, and fidelities.
Slide: the models, validated surrogates on a dense frontier, and the optimizer, the right model per job via multi-fidelity Bayesian optimization. A denser frontier makes a sharper search; the search buys the runs that train and validate the next models; the policy itself can be learned, over surrogates, acquisition functions, and fidelities.In the essayDownload© 2026 Scott Clark
Figure: the strategy in four parts. 1, Talaria manufactures validated physics surrogate models; a dense Pareto frontier of accuracy versus cost per job; 2, TauOpt picks the right model per job and optimizes and searches over them; 3, the harness keeps the research reproducible and self-improves the process; 4, the outputs: fluids, materials, and energy search and design, and just-in-time physics models for robotics and world models.
Figure: the strategy in four parts. 1, Talaria manufactures validated physics surrogate models; a dense Pareto frontier of accuracy versus cost per job; 2, TauOpt picks the right model per job and optimizes and searches over them; 3, the harness keeps the research reproducible and self-improves the process; 4, the outputs: fluids, materials, and energy search and design, and just-in-time physics models for robotics and world models.In the essayDownload© 2026 Scott Clark
Slide: search over surrogates toward what you build next. Materials discovery, energy, physical AI: the classic multi-fidelity design search, with a dense set of validated models to search over parameter and model space.
Slide: search over surrogates toward what you build next. Materials discovery, energy, physical AI: the classic multi-fidelity design search, with a dense set of validated models to search over parameter and model space.In the essayDownload© 2026 Scott Clark
Slide: built in the open, free for open science. Private beta today. Public, open source, and always free for open scientific work. Public launch at NeurIPS, December 2026.
Slide: built in the open, free for open science. Private beta today. Public, open source, and always free for open scientific work. Public launch at NeurIPS, December 2026.In the essayDownload© 2026 Scott Clark
Slide: thank you, with QR codes for talariasci.com and scottclark.io. Researching computational physics or applied math? Running physics simulations? Private beta signups, open source launch at NeurIPS 2026, always free for open science.
Slide: thank you, with QR codes for talariasci.com and scottclark.io. Researching computational physics or applied math? Running physics simulations? Private beta signups, open source launch at NeurIPS 2026, always free for open science.In the essayDownload© 2026 Scott Clark

How Better Evals Can Bring Abundance through Accelerated Scientific Discovery (talk recap)

August 31, 2026 · 17 figures

Title slide: How Better Evals Can Bring Abundance through Accelerated Scientific Discovery. Scott Clark, Founder and CEO, with the Distributional and Talaria Scientific logos.
Title slide: How Better Evals Can Bring Abundance through Accelerated Scientific Discovery. Scott Clark, Founder and CEO, with the Distributional and Talaria Scientific logos.In the essayDownload© 2026 Scott Clark
Slide: what abundance with AI means, a four-step build from new scientific discoveries to living in a scifi future.
Slide: what abundance with AI means, a four-step build from new scientific discoveries to living in a scifi future.In the essayDownload© 2026 Scott Clark
Slide: improving quality of life, not just replacing repetitive work.
Slide: improving quality of life, not just replacing repetitive work.In the essayDownload© 2026 Scott Clark
Slide: we can now meaningfully accelerate science with AI.
Slide: we can now meaningfully accelerate science with AI.In the essayDownload© 2026 Scott Clark
Slide: I have been trying to solve this problem for the last 20 years of my career, with varying degrees of success.
Slide: I have been trying to solve this problem for the last 20 years of my career, with varying degrees of success.In the essayDownload© 2026 Scott Clark
Slide: grad school timeline across Oregon State, UC Davis, Max Planck, Cornell, Los Alamos, and Berkeley Lab. Whatever the field, the final step was always parameter tuning.
Slide: grad school timeline across Oregon State, UC Davis, Max Planck, Cornell, Los Alamos, and Berkeley Lab. Whatever the field, the final step was always parameter tuning.In the essayDownload© 2026 Scott Clark
Slide: SigOpt, Bayesian optimization as a service, with the founding, building, and scaling timeline.
Slide: SigOpt, Bayesian optimization as a service, with the founding, building, and scaling timeline.In the essayDownload© 2026 Scott Clark
Slide: the optimizer worked, except when it didn't. It overfit, or optimized the wrong thing.
Slide: the optimizer worked, except when it didn't. It overfit, or optimized the wrong thing.In the essayDownload© 2026 Scott Clark
Slide: the best thing about a black box optimizer is that it will optimize any eval you tell it to. The worst part is that it will optimize exactly the eval you tell it to.
Slide: the best thing about a black box optimizer is that it will optimize any eval you tell it to. The worst part is that it will optimize exactly the eval you tell it to.In the essayDownload© 2026 Scott Clark
Slide: we are still a long way from typing goal solve stable fusion containment.
Slide: we are still a long way from typing goal solve stable fusion containment.In the essayDownload© 2026 Scott Clark
Slide: Distributional attempt one, pre-production AI testing, 2023 to 2025: high dimensional Bayesian statistical tests for chaotic and non-stationary AI systems and agents.
Slide: Distributional attempt one, pre-production AI testing, 2023 to 2025: high dimensional Bayesian statistical tests for chaotic and non-stationary AI systems and agents.In the essayDownload© 2026 Scott Clark
Slide: the same testing slide grayed out with It failed stamped over it, and the three reasons: people didn't know what to test or have the data before deployment, they couldn't understand tests well enough to act, and they shipped to prod anyway.
Slide: the same testing slide grayed out with It failed stamped over it, and the three reasons: people didn't know what to test or have the data before deployment, they couldn't understand tests well enough to act, and they shipped to prod anyway.In the essayDownload© 2026 Scott Clark
Slide: Distributional attempt two on the timeline strip, post-production agent analytics, 2025 to 2026: analytics on agent traces to find the evals you aren't monitoring for.
Slide: Distributional attempt two on the timeline strip, post-production agent analytics, 2025 to 2026: analytics on agent traces to find the evals you aren't monitoring for.In the essayDownload© 2026 Scott Clark
Slide: the pivot slide grayed out with It failed stamped over it. A feature, not a product, let alone a business or a startup.
Slide: the pivot slide grayed out with It failed stamped over it. A feature, not a product, let alone a business or a startup.In the essayDownload© 2026 Scott Clark
Slide: the timeline strip gains its third column, Computational Science Harness, 2026 and beyond: a multi-agent, multi-FM harness for computational science research acceleration, using domain-specific evals and guardrails rooted in physics and math.
Slide: the timeline strip gains its third column, Computational Science Harness, 2026 and beyond: a multi-agent, multi-FM harness for computational science research acceleration, using domain-specific evals and guardrails rooted in physics and math.In the essayDownload© 2026 Scott Clark
Slide: from idea to trusted result, where the week goes. Two rows compare a computational scientist's week today, dominated by the validation schlep done by hand, with the same week in the harness, where data wrangling, environments, baselines, sweeps, and checking run with provenance on every run.
Slide: from idea to trusted result, where the week goes. Two rows compare a computational scientist's week today, dominated by the validation schlep done by hand, with the same week in the harness, where data wrangling, environments, baselines, sweeps, and checking run with provenance on every run.In the essayDownload© 2026 Scott Clark
Slide: thank you, with QR codes for talariasci.com and scottclark.io. Researching computational physics or applied math? Building world models? Private beta signups, open source launch at NeurIPS 2026, always free for open science.
Slide: thank you, with QR codes for talariasci.com and scottclark.io. Researching computational physics or applied math? Building world models? Private beta signups, open source launch at NeurIPS 2026, always free for open science.In the essayDownload© 2026 Scott Clark

Making New Mistakes Faster as a Second-Time Founder

July 28, 2026 · 1 figure

The map I was actually on, drawn with axes I could only name later. Vision-market fit is the top-left quadrant: resonance keeps climbing, the pull line never gets crossed, and the quadrant keeps you alive exactly long enough to matter. Rooms lean in, rounds come together, pilots start, and none of it compounds on its own.
The map I was actually on, drawn with axes I could only name later. Vision-market fit is the top-left quadrant: resonance keeps climbing, the pull line never gets crossed, and the quadrant keeps you alive exactly long enough to matter. Rooms lean in, rounds come together, pilots start, and none of it compounds on its own.In the essayDownload SVG© 2026 Scott Clark · CC BY-ND 4.0

Building this blog: Part II

July 28, 2026 · 1 figure

A site written for two readers. The dossier repo holds verified public facts, the resume repo holds bio truth, and the site composes both into two surfaces: HTML for the person, and a machine-readable stack (markdown twins, an entity graph, llms.txt, a full-content feed) for the agent they sent. The connective tissue between repos is markdown contracts. Facts flow one direction.
A site written for two readers. The dossier repo holds verified public facts, the resume repo holds bio truth, and the site composes both into two surfaces: HTML for the person, and a machine-readable stack (markdown twins, an entity graph, llms.txt, a full-content feed) for the agent they sent. The connective tissue between repos is markdown contracts. Facts flow one direction.In the essayDownload SVG© 2026 Scott Clark · CC BY-ND 4.0
100%Download SVG