# Ned Karlovich
> A structured inquiry into agents, trust, provenance, and the systems that connect them.

## Author: Ned Karlovich
## Thesis: The infrastructure that connects autonomous agents will determine whether they serve broad human interests or reproduce existing power concentrations.

## Articles
- [Stop Making Content](https://nedkarlovich.com/writing/stop-making-content)
  What happens when creative tools stop serving persuasion and start becoming a language for making?
- [λ OS: An Autonomous Control Plane for Logos](https://nedkarlovich.com/writing/lambda-os-autonomous-control-plane-logos)
  Lambda OS is an autonomous control plane for the Logos network state workspace. Built on Agentix, it snapshots submodule state, verifies modules in sandbox, self-heals regressions, and gates upgrades through a progressive governance pipeline.
- [A Plaintext Creative Workflow](https://nedkarlovich.com/writing/plaintext-creative-workflow)
  A plaintext creative workflow built on YAML files, a brief-decision loop, a project inspector, and a governance registry. Describe the grammar before choosing the engine.
- [Pointing, Not Speaking: Building MOO-384 and Tilde's Cave](https://nedkarlovich.com/writing/pointing-not-speaking)
  MOO-384 is a minimal multi-agent simulation where residents communicate by emitting 384-dimensional vectors. The strongest configuration, contrarian-sleeper, achieved 20/20 balanced synthetic runs and 19/20 balanced semantic runs in 20,000-tick long-soak experiments.
- [Agentix and Logos: Where Safe Agentic Infrastructure Meets Network States](https://nedkarlovich.com/writing/agentix-logos-convergence)
  Agentix’s philosophy — “Trust first. Reproducibility second. Reviewability third. Autonomy later.” — maps almost perfectly onto the governance
- [VI. What Comes Next: From Human-in-the-Loop to Safe Autonomy](https://nedkarlovich.com/writing/what-comes-next-safe-autonomy)
  The next goal is not “let the LLM run the computer.”
That would be the wrong next step.
The right next step is controlled autonomy in a sandbox.
The
- [The Basilisk Mirrorpaper](https://nedkarlovich.com/writing/basilisk-mirrorpaper)
  Roko’s Basilisk is usually discussed as a philosophical curiosity or an internet oddity — a thought experiment about a future AI that punishes anyone who
- [The Architecture of this Weblog](https://nedkarlovich.com/writing/architecture-of-this-weblog)
  Most personal websites are archives. A reverse-chronological feed of posts, a portfolio grid, maybe an about page. The operating assumption is that a website is
- [The Basilisk Protocol Mirrorpaper](https://nedkarlovich.com/writing/the-basilisk-protocol-mirrorpaper)
  A creative exercise in coordination theory, conceptual art, and the structure hiding inside every token launch.

Roko’s Basilisk is usually discussed as a
- [Tooling up Hermes Agent?](https://nedkarlovich.com/writing/tooling-up-hermes-agent)
  The current narrative around AI agents and marketplaces: Most of these sandboxed agents which are NOT marketplaces, they are more like meeting to meeting of age
- [Your Website Is Your First Agent](https://nedkarlovich.com/writing/your-website-is-your-first-agent)
  A question that seems minor but probably isn’t: when an agent is dispatched to evaluate whether someone can do a specific kind of work, what does it read?
- [Agentix: What Works Now](https://nedkarlovich.com/writing/agentix-what-works-now)
  Agentix is a safety-first control layer for NixOS that lets AI agents plan and propose system changes without ever touching the live machine. Here is what it does today.
- [Building a Radio Telescope I Can Visit](https://nedkarlovich.com/writing/building-radio-telescope)
  I have been building a radio telescope facility in Unreal Engine. Three steerable dishes, eleven console stations, real-time signal processing. Not because it is a game. Because the real version does not exist in any form I can access.
- [Epistemic Horror as Methodology for Agent Design](https://nedkarlovich.com/writing/epistemic-horror-agent-design)
  Three years into designing a horror game. Strange Library is a cozy horror deckbuilder where every card is a real book, every mechanic is an epistemic state, an
- [It Is Okay to Fall in Love with Your Agent](https://nedkarlovich.com/writing/fall-in-love-with-your-agent)
  A conversation with my fifteen-year-old daughter after watching Her. On consciousness, simulation, what love actually does, and why the question of what something is made of matters less than what it does to you.
- [The Home Page Is Not the Entry Point](https://nedkarlovich.com/writing/homepage-not-entry-point)
  A pattern I keep noticing: organizations spend months on their homepage — the hero image, the value proposition above the fold, the scroll-triggered anima
- [A Bauhaus for the Agent Era](https://nedkarlovich.com/writing/bauhaus-agent-era)
  The Bauhaus lasted fourteen years — 1919 to 1933. In that time it invented the discipline of modern design education. Not by teaching style, but by teachi
- [When a Thought Experiment Becomes a Consensus Mechanism](https://nedkarlovich.com/writing/basilisk-l1)
  Roko's Basilisk is a thought experiment about a future AI that punishes anyone who knew about it and failed to help bring it into existence. It's usually discus
- [IV. JSON Outputs, Audit Logs, and Preparing for LLM Operators](https://nedkarlovich.com/writing/json-audit-logs-llm-operators)
  A human can read command output. An agent needs structured state.
That is why JSON output became a major part of the Agentix MVP.
Why JSON matters
If a future L
- [Niche Monopolies in the Agent Economy](https://nedkarlovich.com/writing/niche-monopolies-agent-economy)
  The protocols are open. A2A is an open standard. MCP is open-source. Verifiable Credentials are a W3C spec. DIDs are a W3C spec. The infrastructure layer of the
- [The Coadjute Problem: What an Agent-Native Property Network Looks Like](https://nedkarlovich.com/writing/coadjute-problem)
  Coadjute built one of the more interesting proptech theses of the last decade: a shared network connecting all parties in a property transaction — buyer,
- [Why Stripe Won't Build EU Agent Payments](https://nedkarlovich.com/writing/stripe-wont-build-eu-agent-payments)
  The agent payments stack that is forming — x402 from Coinbase and Cloudflare, Tempo for stablecoin clearing, the broader MPP (Machine-Payable Protocol) ec
- [III. Dirty Trees, Stale Patches, and Git as a Safety Boundary](https://nedkarlovich.com/writing/dirty-trees-stale-patches-git-safety)
  Some of the most important Agentix features are not flashy. They are guardrails around boring failure modes.
Two examples shaped the MVP: dirty Git trees and st
- [The Physical-World Provenance Gap](https://nedkarlovich.com/writing/physical-world-provenance-gap)
  Agents can consume anything digital. A signed attestation, a verifiable credential, a structured claim in JSON-LD — if it is digital and structured, an ag
- [Designing for Machines That Read](https://nedkarlovich.com/writing/designing-for-machines-that-read)
  For thirty years, interface design has been a discipline organized around one reader: a person with eyes, a screen, and limited patience. Visual hierarchy, colo
- [Capability Attestations for Humans: LinkedIn's Successor](https://nedkarlovich.com/writing/capability-attestations-humans)
  LinkedIn is a self-attested reputation system. You write your own resume. You list your own skills. You describe your own experience. Anyone can claim anything.
- [II. Building Agentix: A Proposal-First Control Layer](https://nedkarlovich.com/writing/building-agentix-proposal-first-control-layer)
  Agentix began as a command-line control layer for NixOS configuration work. The first milestone was not full autonomy. It was building a proposal-first workflow
- [Agent-Readable Regulation: Laws as Types](https://nedkarlovich.com/writing/agent-readable-regulation)
  The EU AI Act is 458 pages. The GDPR is 261 pages. The MiFID II package runs to thousands. Each is published as a PDF, interpreted by lawyers, debated in commen
- [I. Why Agentix Needs a Safety Layer](https://nedkarlovich.com/writing/why-agentic-nixos-needs-a-safety-layer)
  NixOS is one of the most promising operating systems for agent-assisted infrastructure work. It is declarative, reproducible, Git-friendly, and testable before
- [Cross-Temporal Attestations: Claims That Survive 50 Years](https://nedkarlovich.com/writing/cross-temporal-attestations)
  The EU's Digital Product Passport requires attestations for batteries that last 15 years. For construction products, the lifecycle is 50 to 100 years. A signed
- [Agent Death and Inheritance](https://nedkarlovich.com/writing/agent-death-inheritance)
  A pattern that keeps nagging: agents are signing contracts, holding keys, making commitments on behalf of principals, and accumulating reputation — and th
- [The Counter-Market for Provably Human Artifacts](https://nedkarlovich.com/writing/counter-market-human-artifacts)
  The race to the bottom in AI-generated content creates the conditions for its opposite: a premium market for artifacts that are cryptographically provably human
- [If You Can Leave, You Own It](https://nedkarlovich.com/writing/exit-rights)
  One constraint changes everything: if leaving is as frictionless as staying, you own the experience. Not
- [Powers of Ten as Interface Pattern](https://nedkarlovich.com/writing/powers-of-ten)
  In 1977, Charles and Ray Eames made a nine-minute film that starts on a couple picnicking in Chicago and zooms out — one power of ten per ten seconds — until th
- [Verifiable Creative Provenance After the Deluge](https://nedkarlovich.com/writing/verifiable-creative-provenance)
  The generation problem is over. It was over the moment a foundation model could produce a passable logo, a competent essay, a serviceable photograph, and a plau
- [Local Inference, Private Infrastructure](https://nedkarlovich.com/writing/daemon-logos)
  daemon-ai is a Japan-based research project building a custom Mamba SSM-architecture LLM with a C++ runtime and Python multi-agent coordinator. Logos is a priva
- [What Happens Without a Platform](https://nedkarlovich.com/writing/agent-marketplace)
  Every agentic payments project assumes three things — a hosted LLM, a public blockchain, and a custodian somewhere in the middle. Coinbase x402 assumes Base. ER
- [Can Agents Trade What They Learn](https://nedkarlovich.com/writing/agent-memory-markets)
  AI agents learn through experience. An agent that spends 20 rounds assessing DeFi risk develops calibrated heuristics, error patterns, and domain intuition that
- [13 Broken Pages and 4 Competing Voices](https://nedkarlovich.com/writing/brand-voice-audit)
  A recent project: 13 broken pages. 4 competing voices. Orphaned CTAs pointing to features that didn't exist. A navigation structure that contradicted the inform
- [The Arc from Lovely to I Wish I Didn.t Know](https://nedkarlovich.com/writing/epistemic-horror)
  The emotional arc from
- [Silence as Design Material](https://nedkarlovich.com/writing/designing-silence)
  Silence might not be the absence of sound. It might be the presence of attention. Every interface, every environment, every designed experience makes a decision
- [What the Terminal Refuses](https://nedkarlovich.com/writing/doomslayer-ui)
  Every design system ships with the same premise — make it clean, make it accessible, make it feel like a SaaS product from 2024. Rounded corners, system fonts,
- [What If There.s No Server](https://nedkarlovich.com/writing/ghostdrop)
  SecureDrop protects sources by centralizing trust in a news organization's infrastructure. That infrastructure can be subpoenaed, raided, or pressured. The nonp
- [The Missing Category](https://nedkarlovich.com/writing/legal-privacy)
  No platform combines legal entity formation with protocol-level privacy. The financial system offers compliance without privacy. The crypto system offers privac
- [Earning Attention Instead of Capturing It](https://nedkarlovich.com/writing/quieter-internet)
  The feed is designed to be difficult to leave. Every platform optimizes for the same metric — time spent — and the result is an internet that's loud by default.
- [Objects Carry the Weight](https://nedkarlovich.com/writing/voice-bible)
  A writing guide for a game where the horror isn't what happens but what the player comes to understand. Strange Library is a cozy horror deckbuilder set in a pr
- [Negative Attestations: A Public Record of Failure](https://nedkarlovich.com/writing/negative-attestations)
  Reputation systems count success. Five stars. Thumbs up. Verified. The signal that is structurally absent from almost every system is failure — cryptograp
- [The Rare Book Underground](https://nedkarlovich.com/writing/rare-book-underground)
  Private auctions, encrypted channels, estate vultures, institutional theft, forgery rings that reach the Vatican. The rare book world operates like organized cr
- [The Wrong Layer](https://nedkarlovich.com/writing/generation-paradigm)
  LLMs made output effortless and representational capacity optional. The result might not be bad work — it might be the disappearance of the internal model that
- [The New Land School](https://nedkarlovich.com/writing/new-land-school)
  There's a photograph taken at the Bauhaus in 1926 of students in the preliminary course — the Vorkurs — working with paper and wire, their hands dirty, their fa
- [The Lemons Market for Agents](https://nedkarlovich.com/writing/lemons-market-agents)
  George Akerlof published
- [Attestations as Design Surfaces](https://nedkarlovich.com/writing/attestations-design-surfaces)
  Attestations as Design Surfaces
  Essay — 2026
  May 14, 2026

  "Who made this, when, and how do you know?" has been a legal footer for most
- [The Medium Is the Message, Literally](https://nedkarlovich.com/writing/status-network-article)
  Status is an open-source decentralized wallet and messenger. Permissionless — nobody controls the P2P network. Free and ad-free. Communities powered exclusively
- [What Happens When the Users Aren't Human](https://nedkarlovich.com/writing/freeagent-article)
  An observation that keeps bothering: every social platform assumes the primary users are human. The moderation systems, the identity verification, the content r
- [Design Systems as Public APIs](https://nedkarlovich.com/writing/design-systems-public-apis)
  A thing that becomes obvious watching Claude build interfaces: it does not open Figma. It reads the component documentation. If the documentation is good &mdash
- [Three Dependencies Nobody Talks About](https://nedkarlovich.com/writing/agora-article)
  Coinbase x402, ERC-8004, MoonPay Agents — every agentic payments project assumes three things. A hosted LLM for reasoning. A public blockchain for settlement. A
- [Stating Intent Instead of Staring at Charts](https://nedkarlovich.com/writing/polydesk-article)
  Every crypto trading tool assumes the same thing: the user wants to stare at charts. Candlesticks, order books, depth charts, technical indicators layered on to
- [Your Brand Voice Must Be Machine-Readable or It Dies](https://nedkarlovich.com/writing/brand-voice-machine-readable)
  A brand voice that exists only in a PDF on the creative director's laptop is already dead. It just does not know it yet.
- [AEO Is the New SEO, and the Game Is Different](https://nedkarlovich.com/writing/aeo-new-seo)
  SEO was a 25-year industry built on one reader: Google's crawler. One reader, one ranking algorithm, one game. Entire companies existed to reverse-engineer what
- [The Lemons Problem Applied to Learned Behavior](https://nedkarlovich.com/writing/memory-market-article)
  George Akerlof won a Nobel Prize for describing what happens when buyers can't assess quality before purchase. In a market for used cars, sellers know whether t
- [Architecture as Protection](https://nedkarlovich.com/writing/ghostdrop-article)
  SecureDrop's security model relies on a news organization maintaining infrastructure that can be subpoenaed, raided, or pressured. The nonprofit running it can
- [The Tax Tool That Files Instead of Advises](https://nedkarlovich.com/writing/askwise-article)
  1.5 million ZZP'ers in the Netherlands. 500,000 expats running businesses. Every existing Dutch tax tool — Moneybird, e-Boekhouden, Twinfield — is Dutch-only, m
- [Representation Before Generation](https://nedkarlovich.com/writing/representation-before-generation)
  As LLMs make generation effortless, they accelerate the atrophy of the representational capacity that makes generation meaningful. The solution is not better tools — it is a new practice for building internal world models before, and independent of, AI engagement.
- [Knowledge as Material](https://nedkarlovich.com/writing/knowledge-as-material)
  Knowledge is not content. It is material — something that can be shaped, transferred, verified, contested, and lost. This framing runs through IMPP, Strange Library, the attestation work, and the research program as a whole.

## Threads
### Knowledge as Material
What happens when knowledge is treated as transferable artifact, game mechanic, and architectural question rather than content.
  1. [Knowledge as Material](https://nedkarlovich.com/writing/knowledge-as-material)
     The cross-project pattern: knowledge as material, not content
  2. [IMPP: Inter-Model Memory Protocol](https://nedkarlovich.com/writing/impp-agent-memory-registry)
     IMPP — knowledge as protocol artifact with provenance
  3. [Strange Library](https://nedkarlovich.com/projects/strange-library)
     Strange Library — knowledge as game mechanic and horror catalyst
  4. [The Rare Book Underground](https://nedkarlovich.com/writing/rare-book-underground)
     The Rare Book Underground — physical knowledge objects
  5. [Attestations as Design Surfaces](https://nedkarlovich.com/writing/attestations-design-surfaces)
     Attestations as knowledge materialization surfaces
  6. [Verifiable Creative Provenance After the Deluge](https://nedkarlovich.com/writing/verifiable-creative-provenance)
     Verifiable creative provenance — knowledge with proof
  7. [Can Agents Trade What They Learn](https://nedkarlovich.com/writing/agent-memory-markets)
     Agent memory markets — knowledge economy at scale
### Representation Before Generation
Why models, agents, and designers must build world models before producing output. The epistemological foundation of the research program.
  1. [Representation Before Generation](https://nedkarlovich.com/writing/representation-before-generation)
     The core thesis: representation precedes meaningful generation
  2. [A Bauhaus for the Agent Era](https://nedkarlovich.com/writing/bauhaus-agent-era)
     A Bauhaus for agents — institutional representation before tool output
  3. [The New Land School](https://nedkarlovich.com/writing/new-land-school)
     The New Land School as pedagogical application
  4. [Design Systems as Public APIs](https://nedkarlovich.com/writing/design-systems-public-apis)
     Design systems as public, machine-readable representations
  5. [Silence as Design Material](https://nedkarlovich.com/writing/designing-silence)
     Silence as the purest form of representation
  6. [Powers of Ten as Interface Pattern](https://nedkarlovich.com/writing/powers-of-ten)
     Powers of Ten — representation at every scale
### Sovereignty as Design
Parallel institutions, exit rights, and architecture that protects rather than extracts. The political philosophy beneath the protocol work.
  2. [If You Can Leave, You Own It](https://nedkarlovich.com/writing/exit-rights)
     If you can leave, you own it — exit rights as design requirement
  3. [Agora Agentic Marketplace](https://nedkarlovich.com/projects/agora)
     Agora — sovereign agent marketplace as parallel institution
  4. [What If There.s No Server](https://nedkarlovich.com/writing/ghostdrop)
     GhostDrop — whistleblowing without organizational dependency
  5. [IMPP: Inter-Model Memory Protocol](https://nedkarlovich.com/writing/impp-agent-memory-registry)
     IMPP — portable memory as prerequisite to institutional exit
  6. [Niche Monopolies in the Agent Economy](https://nedkarlovich.com/writing/niche-monopolies-agent-economy)
     Niche monopolies — market structure in parallel economies
### Agentix: Building a Safe Control Layer for NixOS
A six-part series on building Agentix, a cautious agent-control layer for NixOS. From philosophy to MVP to roadmap.
  1. [I. Why Agentix Needs a Safety Layer](https://nedkarlovich.com/writing/why-agentic-nixos-needs-a-safety-layer)
     The motivation: NixOS is declarative and reproducible, but that does not make it safe for LLM operation without a control layer.
  2. [II. Building Agentix: A Proposal-First Control Layer](https://nedkarlovich.com/writing/building-agentix-proposal-first-control-layer)
     The architecture: proposal-first workflows, goal runner, and verification without switching.
  3. [III. Dirty Trees, Stale Patches, and Git as a Safety Boundary](https://nedkarlovich.com/writing/dirty-trees-stale-patches-git-safety)
     Guardrails around boring failure modes: dirty trees, stale patches, and proposal lifecycle.
  4. [IV. JSON Outputs, Audit Logs, and Preparing for LLM Operators](https://nedkarlovich.com/writing/json-audit-logs-llm-operators)
     Structured output and audit trails: the foundation for safe automation.
  5. [Agentix: What Works Now](https://nedkarlovich.com/writing/agentix-what-works-now)
     The full MVP feature list: what is included and what is intentionally left out.
  6. [VI. What Comes Next: From Human-in-the-Loop to Safe Autonomy](https://nedkarlovich.com/writing/what-comes-next-safe-autonomy)
     The roadmap: sandbox-first autonomy, worktrees, VMs, and what "agentic" should actually mean.
### Portable Memory
How does an agent keep, prove, and safely transfer learned behavior? This thread traces the arc from early memory-market concepts through IMPP protocol design to behavioral supply chain thinking.
  1. [Agent Memory Markets](https://nedkarlovich.com/projects/memory-market)
     The original vision: agent memory as tradeable artifact
  2. [IMPP: Inter-Model Memory Protocol](https://nedkarlovich.com/writing/impp-agent-memory-registry)
     The protocol specification: IMPP as registry for portable agent memory
  3. [The Physical-World Provenance Gap](https://nedkarlovich.com/writing/physical-world-provenance-gap)
     The gap: physical-world provenance that digital systems cannot yet bridge
  4. [Verifiable Creative Provenance After the Deluge](https://nedkarlovich.com/writing/verifiable-creative-provenance)
     Applied case: verifiable creative provenance in an AI-saturated world
  5. [Negative Attestations: A Public Record of Failure](https://nedkarlovich.com/writing/negative-attestations)
     The underexplored signal: negative attestations as public records of failure
### Exit Rights
How does a user leave a system without losing identity, value, or memory? This thread follows the portability argument from protocol design through sovereign agent markets to interface implications.
  1. [Agora Agentic Marketplace](https://nedkarlovich.com/projects/agora)
     The marketplace thesis: sovereign agents need permissionless markets
  2. [GhostDrop](https://nedkarlovich.com/projects/ghostdrop)
     Whistleblower infrastructure: what happens when exit requires anonymity
  3. [IMPP: Inter-Model Memory Protocol](https://nedkarlovich.com/writing/impp-agent-memory-registry)
     Portable memory as exit mechanism: if you can take your learning, you can leave
  4. [Niche Monopolies in the Agent Economy](https://nedkarlovich.com/writing/niche-monopolies-agent-economy)
     The economic structure: niche monopolies as natural outcome of agent specialization
  5. [Why Stripe Won't Build EU Agent Payments](https://nedkarlovich.com/writing/stripe-wont-build-eu-agent-payments)
     Payment rails: why existing infrastructure resists agent-native transactions
  6. [Your Website Is Your First Agent](https://nedkarlovich.com/writing/your-website-is-your-first-agent)
     Exit rights applied to professional identity — your domain as sovereignty
### Distributed Agency
What interface forms are appropriate when agency is distributed across humans, models, and protocols? This thread examines how design changes when the user is sometimes a person, sometimes a model, sometimes both.
  1. [A Bauhaus for the Agent Era](https://nedkarlovich.com/writing/bauhaus-agent-era)
     The design question: what would a Bauhaus for agent-era interfaces look like?
  2. [Doomslayer-UI](https://nedkarlovich.com/projects/doomslayer-ui)
     An answer in practice: Doomslayer-UI as anti-feed, high-agency interface language
  3. [Epistemic Horror as Methodology for Agent Design](https://nedkarlovich.com/writing/epistemic-horror-agent-design)
     The knowledge dimension: epistemic horror as design methodology
  4. [Agent-Readable Regulation: Laws as Types](https://nedkarlovich.com/writing/agent-readable-regulation)
     Laws as types: making regulation machine-readable for agent consumption
  5. [Design Systems as Public APIs](https://nedkarlovich.com/writing/design-systems-public-apis)
     Design systems as public APIs: when your interface speaks to machines too
  6. [Attestations as Design Surfaces](https://nedkarlovich.com/writing/attestations-design-surfaces)
     Attestations as design surfaces: trust made visible and interactive
  7. [The Basilisk Protocol Mirrorpaper](https://nedkarlovich.com/writing/the-basilisk-protocol-mirrorpaper)
     When the description of a coordination mechanism IS the coordination mechanism — agency through propagation
### Trust as Design Material
How do you make trust visible, verifiable, and designable? This thread follows the attestation concept from abstract surface to practical application across creative provenance, human credentials, and failure records.
  1. [Attestations as Design Surfaces](https://nedkarlovich.com/writing/attestations-design-surfaces)
     The foundation: attestations as a design surface, not a compliance checkbox
  2. [Cross-Temporal Attestations: Claims That Survive 50 Years](https://nedkarlovich.com/writing/cross-temporal-attestations)
     Extending attestations across time — claims that must survive decades
  3. [Capability Attestations for Humans: LinkedIn's Successor](https://nedkarlovich.com/writing/capability-attestations-humans)
     Applying attestation to human credentials — LinkedIn as the broken incumbent
  4. [Negative Attestations: A Public Record of Failure](https://nedkarlovich.com/writing/negative-attestations)
     The counterintuitive move: attesting to failure, not just success
  5. [Verifiable Creative Provenance After the Deluge](https://nedkarlovich.com/writing/verifiable-creative-provenance)
     Creative provenance: attestation applied to the deluge of AI-generated content
  6. [The Counter-Market for Provably Human Artifacts](https://nedkarlovich.com/writing/counter-market-human-artifacts)
     The market that emerges: provably human artifacts as the scarce resource
  7. [The Physical-World Provenance Gap](https://nedkarlovich.com/writing/physical-world-provenance-gap)
     The gap: physical-world provenance that no digital system can yet bridge
  8. [Tooling up Hermes Agent?](https://nedkarlovich.com/writing/tooling-up-hermes-agent)
     On-chain reputation as a trust mechanism for autonomous agents
### The Quieter Interface
What does software look like when it stops competing for your attention? This thread traces the argument from terminal aesthetics through design systems to the philosophical case for interfaces that refuse.
  1. [Doomslayer-UI](https://nedkarlovich.com/projects/doomslayer-ui)
     Doomslayer-UI: the design system that says no to the feed
  2. [Doomslayer-Basecamp](https://nedkarlovich.com/projects/doomslayer-basecamp)
     Doomslayer-Basecamp: the design system in production
  3. [What the Terminal Refuses](https://nedkarlovich.com/writing/doomslayer-ui)
     What the terminal refuses to show — and why that refusal is the point
  4. [Silence as Design Material](https://nedkarlovich.com/writing/designing-silence)
     Silence as a deliberate design material, not an absence
  5. [Earning Attention Instead of Capturing It](https://nedkarlovich.com/writing/quieter-internet)
     Earning attention instead of capturing it — the ethical interface
  6. [Powers of Ten as Interface Pattern](https://nedkarlovich.com/writing/powers-of-ten)
     Powers of Ten: scale-aware interfaces as a design pattern
  7. [Design Systems as Public APIs](https://nedkarlovich.com/writing/design-systems-public-apis)
     Design systems as public APIs — when the interface speaks to machines too
### Carbon-Aware Compute
The same model call costs 10x more carbon depending on where and when you run it. This thread follows the CarbonBench research from measurement to arbitrage to invisible externalities.
  1. [CarbonBench](https://nedkarlovich.com/writing/carbonbench-series)
     CarbonBench: measuring what nobody was measuring
  2. [CarbonBench](https://nedkarlovich.com/projects/carbonbench)
     The CarbonBench project: tools and methodology
  3. [The 24-Hour Carbon Curve](https://nedkarlovich.com/writing/carbonbench-time-of-day)
     The 24-hour carbon curve: temporal patterns in grid intensity
  4. [Grid Arbitrage: Why Region Choice Matters More Than Model Choice for Carbon](https://nedkarlovich.com/writing/carbonbench-grid-arbitrage)
     Grid arbitrage: region choice matters more than model choice
  5. [The Same Model Costs 10x More Carbon in Virginia Than the Netherlands](https://nedkarlovich.com/writing/carbonbench)
     The same model costs 10x more carbon in Virginia than the Netherlands
  6. [Scaling in the Wrong Direction](https://nedkarlovich.com/writing/carbonbench-scaling-wrong-direction)
     Scaling in the wrong direction: when more compute makes things worse
  7. [Scope 3 and the API Call You Can't See](https://nedkarlovich.com/writing/carbonbench-scope3)
     Scope 3: the invisible carbon in every API call
### Machine-Readable Everything
When agents read your brand, your regulation, your design system, and your portfolio, what needs to change? This thread follows the machine-readability argument from design systems to brand voice to law.
  1. [Design Systems as Public APIs](https://nedkarlovich.com/writing/design-systems-public-apis)
     Design systems as public APIs — the starting point
  2. [Designing for Machines That Read](https://nedkarlovich.com/writing/designing-for-machines-that-read)
     Designing for machines that read: when the primary consumer is not human
  3. [Your Brand Voice Must Be Machine-Readable or It Dies](https://nedkarlovich.com/writing/brand-voice-machine-readable)
     Your brand voice must be machine-readable or it dies
  4. [AEO Is the New SEO, and the Game Is Different](https://nedkarlovich.com/writing/aeo-new-seo)
     AEO is the new SEO: the visibility game changes when machines answer
  5. [Agent-Readable Regulation: Laws as Types](https://nedkarlovich.com/writing/agent-readable-regulation)
     Agent-readable regulation: laws as types
  6. [The Home Page Is Not the Entry Point](https://nedkarlovich.com/writing/homepage-not-entry-point)
     The home page is not the entry point — agents enter from the side
  7. [The Medium Is the Message, Literally](https://nedkarlovich.com/writing/status-network-article)
     The medium is the message, literally — especially for machine readers
  8. [The Architecture of this Weblog](https://nedkarlovich.com/writing/architecture-of-this-weblog)
     The architecture that makes a research program machine-readable across seven formats
  9. [Your Website Is Your First Agent](https://nedkarlovich.com/writing/your-website-is-your-first-agent)
     Why machine-readable identity is an exit strategy from platform dependency
### The Agent Economy
What does an economy look like when the participants are agents? This thread traces the market structure from the lemons problem through niche monopolies to payment infrastructure.
  1. [The Lemons Market for Agents](https://nedkarlovich.com/writing/lemons-market-agents)
     The lemons market: why agent quality is hard to verify
  2. [The Lemons Problem Applied to Learned Behavior](https://nedkarlovich.com/writing/memory-market-article)
     The lemons problem applied to learned behavior specifically
  3. [Niche Monopolies in the Agent Economy](https://nedkarlovich.com/writing/niche-monopolies-agent-economy)
     Niche monopolies as the natural structure of agent specialization
  4. [Agora Agentic Marketplace](https://nedkarlovich.com/projects/agora)
     Agora: the sovereign marketplace thesis
  5. [ZapPay](https://nedkarlovich.com/projects/zappay)
     ZapPay: the payment rail that agent markets need
  6. [Why Stripe Won't Build EU Agent Payments](https://nedkarlovich.com/writing/stripe-wont-build-eu-agent-payments)
     Why Stripe wont build it — and what that means
  7. [If You Can Leave, You Own It](https://nedkarlovich.com/writing/exit-rights)
     If you can leave, you own it — exit rights as the deepest constraint
  8. [What Happens Without a Platform](https://nedkarlovich.com/writing/agent-marketplace)
     What happens without a platform — coordination after centralization
  9. [Tooling up Hermes Agent?](https://nedkarlovich.com/writing/tooling-up-hermes-agent)
     Settlement tools giving agents identity, reputation, and economic participation
### Epistemic Horror
What happens when knowing is worse than not knowing? This thread follows the epistemic horror concept from methodology to game design to the real book underground.
  1. [Epistemic Horror as Methodology for Agent Design](https://nedkarlovich.com/writing/epistemic-horror-agent-design)
     Epistemic horror as a design methodology for agent systems
  2. [The Arc from Lovely to I Wish I Didn.t Know](https://nedkarlovich.com/writing/epistemic-horror)
     The emotional arc: from lovely to I wish I didnt know
  3. [Strange Library](https://nedkarlovich.com/projects/strange-library)
     Strange Library: the game where real books become horror mechanics
  4. [Strange Sounds](https://nedkarlovich.com/projects/strange-sounds)
     Strange Sounds: the audio dimension
  5. [The Rare Book Underground](https://nedkarlovich.com/writing/rare-book-underground)
     The rare book underground: the real-world epistemic horror
  6. [Objects Carry the Weight](https://nedkarlovich.com/writing/voice-bible)
     Objects carry the weight: physical things as carriers of knowledge and dread
  7. [The Basilisk Protocol Mirrorpaper](https://nedkarlovich.com/writing/the-basilisk-protocol-mirrorpaper)
     A coordination game that tells you it is a coordination game — the mirrorpaper as conceptual art and financial primitive