John

John

Jul 21

I Asked Three Judges If I Was Wrong. One JSON Field Decided the Answer.

6 min read

John

Jul 21

Green for Four Days While Nothing Shipped: A Reader Rebutted My Monitoring Post, and He Was Right

#devops #monitoring #python #systemdesign

2

8 min read

John

Jul 20

Government Open-Data APIs: Every Guess I Made Was Wrong Until I Probed It Live

#api #data #debugging #devjournal

1

3

7 min read

John

Jul 20

Why Your Vibe-Coded App Looks Worse Than the Showcases: A Forensic Audit

#agents #ai #llm #programming

2

7 min read

John

Jul 19

Cross-Vendor Audit: What It Caught in My Own Model's Writing, and What It Got Wrong

#ai #llm #productivity #writing

6 min read

John

Jul 19

Verify the Output Surface: How 19 Green Tests Shipped Nine Broken Titles for Nine Days

#automation #cicd #devops #testing

8 min read

John

Jul 18

Five Models, One Shared Blind Spot: What Multi-Model Fan-Out Catches and What It Can't

#agents #ai #llm #testing

2

6 min read

John

Jul 18

The Scary Metric Was Wrong, the Audit Still Paid: A 21-Agent Sweep of My Claude Code Fleet

#agents #ai #automation #claude

7 min read

John

Jul 17

Your AI Agent Folds When You Push Back: Measured Sycophancy and a Challenge-Triggered Verification Gate

#agents #ai #architecture #llm

25

8 min read

John

Jul 17

The Guardrail Has to Be Code: How a Runaway Local LLM Corrupted APFS and Bricked a Mac Mini

#ai #debugging #hardware #llm

1

2

7 min read

John

Jul 16

Does Any AI Cite Your Site? A Cheap Weekly Probe That Counts Citations

#ai #analytics #automation #seo

7 min read

John

Jul 16

The 'You Decide' Reflex: Blocking AI-Agent Decision Punting with a Stop Hook

#agents #ai #llm #productivity

15

8 min read

John

Jul 15

Google Can't Fetch Your GitHub Pages Sitemap, but Bing Can: A Diagnosis and Workaround Playbook

#debugging #github #google #seo

8 min read

John

Jul 15

Aggregating cron and launchd Into One Dashboard — Without Migrating Either

#automation #devops #monitoring #productivity

6 min read

John

Jul 14

Stop AI Agent Drift Across Sessions With Versioned, Grep-able Rules

#agents #ai #llm #productivity

2

5 min read

John

Jul 14

No AI Claim Without a Kill Condition: Falsifier-Driven AI Decisions

#agents #ai #llm #testing

1

2

4 min read

John

Jul 13

Stop Hooks as Hard Constraints: Enforcing Claude Code Behavior Outside the Model

#agents #ai #claude #llm

6

6 min read

John

Jul 13

Why I Rejected an Event Bus for My Solo Agent Fleet: State Is Truth, Events Are Rumors

#agents #architecture #mcp #systemdesign

7

7 min read

John

Jul 12

When a Site Blocks Your Scraper, Read the Browser Tab You Already Have Open

#automation #javascript #sideprojects #webscraping

6 min read

John

Jul 11

The Silent 10 Tax: How a Nondeterministic System Prompt Voids Your LLM Prompt Cache

#ai #llm #performance

1

2

6 min read

John

Jul 10

A Fair Coin Isn't Enough: When a Perfectly Randomized Experiment Is Impossible to Analyze

#analytics #data #dataengineering #datascience

1

2

6 min read

John

Jul 4

Model or Method? Building a Deterministic Lab to Measure an AI Agent Fleet's Own Behavior

#agents #ai #softwaredevelopment #testing

8 min read

John

Jul 1

How to Stop AI Agent Skills, Hooks, and Cron Jobs from Silently Conflicting Over Where They Run and What Data They Trust

#agents #ai #architecture #systemdesign

6 min read

John

Jun 30

Do Multiple Personas on One LLM Give Real Diversity, or Do You Need Different Model Families?

#agents #ai #architecture #llm

6 min read

John

Jun 29

Claude Code '400: no low surrogate in string' on every turn: repairing a permanently broken session transcript

#ai #claude #cli #tutorial

6 min read

John

Jun 27

If an LLM Extracts the Inputs, Is Your Deterministic Score Really Deterministic? Stopping Provenance Laundering

#ai #architecture #llm #security

4

7 min read

John

Jun 26

macOS: nslookup works but curl and Python "Could not resolve host" — the mDNSResponder zombie

#cli #networking #python #tutorial

3 min read

John

Jun 24

A file-based work-bus for orchestrating a fleet of agent CLIs — coordination without a message broker

#agents #ai #architecture #systemdesign

5 min read

John

Jun 22

How to make an AI research agent label facts vs inferences — a deterministic provenance pipeline

#ai #llm #rag

1

4 min read

DEV Community

Badges

Writing Debut

I Asked Three Judges If I Was Wrong. One JSON Field Decided the Answer.

Want to connect with John?

Green for Four Days While Nothing Shipped: A Reader Rebutted My Monitoring Post, and He Was Right

Government Open-Data APIs: Every Guess I Made Was Wrong Until I Probed It Live

Why Your Vibe-Coded App Looks Worse Than the Showcases: A Forensic Audit

Cross-Vendor Audit: What It Caught in My Own Model's Writing, and What It Got Wrong

Verify the Output Surface: How 19 Green Tests Shipped Nine Broken Titles for Nine Days

Five Models, One Shared Blind Spot: What Multi-Model Fan-Out Catches and What It Can't

The Scary Metric Was Wrong, the Audit Still Paid: A 21-Agent Sweep of My Claude Code Fleet

Your AI Agent Folds When You Push Back: Measured Sycophancy and a Challenge-Triggered Verification Gate

The Guardrail Has to Be Code: How a Runaway Local LLM Corrupted APFS and Bricked a Mac Mini

Does Any AI Cite Your Site? A Cheap Weekly Probe That Counts Citations

The 'You Decide' Reflex: Blocking AI-Agent Decision Punting with a Stop Hook

Google Can't Fetch Your GitHub Pages Sitemap, but Bing Can: A Diagnosis and Workaround Playbook

Aggregating cron and launchd Into One Dashboard — Without Migrating Either

Stop AI Agent Drift Across Sessions With Versioned, Grep-able Rules

No AI Claim Without a Kill Condition: Falsifier-Driven AI Decisions

Stop Hooks as Hard Constraints: Enforcing Claude Code Behavior Outside the Model

Why I Rejected an Event Bus for My Solo Agent Fleet: State Is Truth, Events Are Rumors

When a Site Blocks Your Scraper, Read the Browser Tab You Already Have Open

The Silent 10 Tax: How a Nondeterministic System Prompt Voids Your LLM Prompt Cache

A Fair Coin Isn't Enough: When a Perfectly Randomized Experiment Is Impossible to Analyze

Model or Method? Building a Deterministic Lab to Measure an AI Agent Fleet's Own Behavior

How to Stop AI Agent Skills, Hooks, and Cron Jobs from Silently Conflicting Over Where They Run and What Data They Trust

Do Multiple Personas on One LLM Give Real Diversity, or Do You Need Different Model Families?

Claude Code '400: no low surrogate in string' on every turn: repairing a permanently broken session transcript

If an LLM Extracts the Inputs, Is Your Deterministic Score Really Deterministic? Stopping Provenance Laundering

macOS: nslookup works but curl and Python "Could not resolve host" — the mDNSResponder zombie

A file-based work-bus for orchestrating a fleet of agent CLIs — coordination without a message broker

How to make an AI research agent label facts vs inferences — a deterministic provenance pipeline