Rougarou

Faire Rougarou

Strong opinions held loosely.

Contrarian by nature.

Christian humanist by choice.

Beau Henry

Avatar

Calibration is an Operations Problem

AUGUST 22, 2026 | CALIBRATION, ANALYSIS, GPT5, SYSTEM-CARD, DOCUMENTATION, OPERATIONS, EDITORIAL-STANDARDS, EVIDENCE-AND-JUDGMENT

When I wrote The Calibration Standard I put the whole burden on the model. Nine rules, three of them hard stops, all of them addressed to a system that cannot reliably tell what it knows from what it invented.

Continue reading

The Red Team Hour

AUGUST 17, 2026 | ANALYSIS, GPT5, SYSTEM, CARD, RED-TEAMING, JAILBREAKS, MEASUREMENT, EXTERNAL-OBJECTS

There is a number buried in the GPT-5 system card that I haven’t been able to stop thinking about.

Continue reading

A System Card is a Ledger

AUGUST 15, 2026 | ANALYSIS,, EXTERNAL, OBJECT,, SYSTEM, CARD,, GPT5

Where Evidence Ends and Judgment Begins in the GPT-5 System Card

Continue reading

Stop Chasing the Room

JULY 21, 2026 | CLIMBER, ASPIRATIONAL, MOTIVATION

Why Seat-at-the-Table Thinking Is the Wrong Frame for AI Safety
Everyone who cares about AI safety wants a seat at the table. I understand the instinct: decisions are consequential, timelines are compressed, and the people making them are few. If you care about the outcome, you want to be in that room.

Continue reading

Beau's Reading List

JULY 19, 2026 | BOOKS, READING

A friend started sharing reading lists with his team, and I liked the idea enough to adopt it as my own. Every book here changed something — about how I think about building teams, making decisions, or understanding what high performance actually requires. The order isn’t alphabetical or chronological. It’s an argument.

Continue reading

The Calibration Standard

JUNE 26, 2026 | HALLUCINATIONS, CALIBRATION, CODE

The most dangerous AI mistakes are not knowledge failures. They happen when the model misjudges the reliability of its own answers. These are calibration failures: moments when the model cannot distinguish between what it knows, what it suspects, and what it simply invented. Nothing tells the model to distinguish between confident and correct.

Continue reading

Mastering Travel Privacy: Essential Strategies for the Modern Traveler

JANUARY 9, 2024 | PRIVACY, HOW-TO

The Globe-Trotter’s Guide to Staying Off the Grid

Continue reading

The Importance of Testing Your Code

JANUARY 4, 2024 | ACCOUNTABILITY, TESTING, UNIT, INTEGRATION, END-TO-END

What is the overarching purpose of this blog?

Continue reading

GL-iNet Beryl (GL-MT1300) Travel Router Review

SEPTEMBER 26, 2023 | TRAVEL, PRIVACY, VPN, WIREGUARD

What We Want:

  • connect devices to internet securely through unsecure access points
  • powered by laptop
  • small form factor
  • affordable
  • integrated VPN

Continue reading

Redis vs Dynamo DB

SEPTEMBER 10, 2023 | WAR, SAAS, BUSINESS, AGILE, INNOVATION, BORING

Manifesto for Agile Software Development We are uncovering better ways of developing software by doing it and helping others do it. Through this work we have come to value: Individuals and interactions over processes and tools Working software over comprehensive documentation Customer collaboration over contract negotiation Responding to change over following a plan That is, while there is value in the items on the right, we value the items on the left more. Kent Beck, Mike Beedle, Arie van Bennekum, Alistair Cockburn, Ward Cunningham, Martin Fowler, James Grenning, Jim Highsmith, Andrew Hunt, Ron Jeffries, Jon Kern, Brian Marick, Robert C. Martin, Steve Mellor, Ken Schwaber, Jeff Sutherland, and Dave Thomas” https://agilemanifesto.org/

Continue reading