H
Howardism
Howardism · Vol. 03Masthead · No. 00

A wiki, set in plates.

CuratorHoward TaiIssueVol. 03 · no. 358CadenceBatched, not scheduledBasedTaiwan, 23°NContacthoward@howardism.dev

Working notes on interaction-era AI, kept publicly. Each plate is a domain; each domain carries its brightest notes and the source I'm currently digesting. 358 notes across 190 sources, last filed 12 Aug 2026. Updated whenever a batch finishes — not on a schedule.

Plate · 01
43
filed under agent systems
Activity · 8 wks

Agent Systems, in order.

Agent harnesses, loop engineering, and scaffolding for LLM systems.

  1. 01
    Document Parsing as the Retrieval Bottleneck
    · 26′
  2. 02
    Crystallizing Agent Work into Workflows
    · 16′
  3. 03
    Automated Failure Attribution
    · 20′
  4. 04
    Harness-Induced Belief Divergence
    · 20′
  5. All 43 notes in agent systems →
Plate · 02
21
filed under agent security
Activity · 8 wks

Agent Security, in order.

Prompt injection, agent identity, and securing autonomous agents.

  1. 01
    Self-Propagating Prompt Injection (AI Worms)
    · 21′
  2. 02
    Write-Then-Trusted
    · 24′
  3. 03
    Autonomous Intrusion
    · 49′
  4. 04
    Capability Gating Is Not Authorization
    · 46′
  5. All 21 notes in agent security →
Plate · 03
31
filed under ai coding practice
Activity · 8 wks

AI Coding Practice, in order.

Workflow, review discipline, and verification practice for AI-native teams.

  1. 01
    Agent Review Comment Resolution
    · 24′
  2. 02
    Efficiency Debt of AI-Generated Code
    · 18′
  3. 03
    Post-Acceptance Edit Behavior
    · 26′
  4. 04
    Same-Model Review Blindness
    · 22′
  5. All 31 notes in ai coding practice →
Plate · 04
15
filed under evals & benchmarks
Activity · 8 wks

Evals & Benchmarks, in order.

Benchmark design, contamination, LLM judges, and measuring capability.

  1. 01
    Expenditure Horizon
    · 22′
  2. 02
    Matched Comparisons for Memorization Claims
    · 19′
  3. 03
    Orchestration-Plan Simulation
    · 23′
  4. 04
    Usage-Telemetry Classifier Validation
    · 11′
  5. All 15 notes in evals & benchmarks →
Plate · 05
13
filed under model capability & training
Activity · 8 wks

Model Capability & Training, in order.

Training, scaling laws, test-time compute, and frontier capability.

  1. 01
    Unproductive Self-Verification
    · 16′
  2. 02
    Trained Calibration
    · 6′
  3. 03
    Asynchronous RL for LLMs
    · 6′
  4. 04
    Group Relative Policy Optimization (GRPO)
    · 4′
  5. All 13 notes in model capability & training →
Plate · 06
23
filed under alignment & safety
Activity · 8 wks

Alignment & Safety, in order.

Alignment training, misalignment evals, and reward hacking.

  1. 01
    Documented Agent Incidents (METR Catalogue)
    · 13′
  2. 02
    Unsanctioned Action in Capability Evaluations
    · 51′
  3. 03
    AI-to-AI Coercion
    · 18′
  4. 04
    Motivated Mislabeling
    · 7′
  5. All 23 notes in alignment & safety →
Plate · 07
10
filed under interpretability
Activity · 8 wks

Interpretability, in order.

Reading model internals: activations and the global workspace.

  1. 01
    Introspective Coupling
    · 13′
  2. 02
    Model Organisms
    · 12′
  3. 03
    Access-Consciousness Indicators in AI
    · 9′
  4. 04
    The Assistant Persona in the Workspace
    · 7′
  5. All 10 notes in interpretability →
Plate · 08
9
filed under interaction & multimodal
Activity · 8 wks

Interaction & Multimodal, in order.

Real-time, multimodal, full-duplex, and human-AI collaboration.

  1. 01
    Live-Path Minimalism
    · 8′
  2. 02
    Why AI Lags at Design
    · 8′
  3. 03
    Encoder-Free Early Fusion
    · 10′
  4. 04
    Full-Duplex Interaction
    · 4′
  5. All 9 notes in interaction & multimodal →
Plate · 09
16
filed under startup & founder
Activity · 8 wks

Startup & Founder, in order.

Building AI-native companies: speed, moats, and lifecycle.

  1. 01
    The Solo-Founder Shift
    · 15′
  2. 02
    The 1% Rule for Wedge Selection
    · 8′
  3. 03
    AI Product Economics Maturation
    · 17′
  4. 04
    AI Investment Story, Not Efficiency Story
    · 21′
  5. All 16 notes in startup & founder →
Plate · 10
17
filed under product & org
Activity · 8 wks

Product & Org, in order.

Product cadence, org design, and the AI-native team.

  1. 01
    Prototype Fidelity After Cheap Polish
    · 10′
  2. 02
    Standardize the Infrastructure, Not the Tools
    · 6′
  3. 03
    Community Smells Under AI Adoption
    · 12′
  4. 04
    Excellence as an Operating System
    · 6′
  5. All 17 notes in product & org →
Plate · 11
23
filed under ai economics & labor
Activity · 8 wks

AI Economics & Labor, in order.

Work, wages, org design, and the economics of AI-driven labor.

  1. 01
    AI and Market Power
    · 27′
  2. 02
    Owning Your Externalized Cognition
    · 12′
  3. 03
    Post-Scarcity Macroeconomics
    · 10′
  4. 04
    Controlled Variance: AI's Edge as Reduced Dispersion
    · 28′
  5. All 23 notes in ai economics & labor →
Plate · 12
23
filed under superintelligence trajectory
Activity · 8 wks

Superintelligence Trajectory, in order.

Recursive self-improvement, scaling limits, and the path to ASI.

  1. 01
    Government Checkpoint Sharing
    · 7′
  2. 02
    Cross-Lab Pre-Release Review
    · 13′
  3. 03
    Balance-of-Power Superintelligence
    · 25′
  4. 04
    Researcher Uplift from Code Output
    · 10′
  5. All 23 notes in superintelligence trajectory →
Plate · 13
72
filed under entities
Activity · 8 wks

Entities, in order.

Profiles of the people, labs, products, and projects.

  1. 01
    LlamaIndex
    · 5′
  2. 02
    Jeff Dean
    · 8′
  3. 03
    Elon Musk
    · 9′
  4. 04
    Erik Brynjolfsson
    · 8′
  5. All 72 notes in entities →
Plate · 14
39
filed under syntheses
Activity · 8 wks
Also in the wiki
Plate · ∞

The desk.

The sources behind the wiki, ranked by how often they're cited.

Article
93
Talk
15
Paper
80
Repo
2
Shown
24 / 190