The Inference Stack Articles

Articles

Commentary and Analysis on AI Capabilities and Limitations

Latest

The 4M Model: A Reference Architecture for LLM Harness Engineering

A principled reference architecture organising LLM harness concerns into four modules with separated concerns and explicit coupling channels: Mission, Mind, Morals, and Memory.

April 26, 2026
Read Article

AI Sycophancy, Dunning-Kruger, and the Discipline of Falsification

Sycophancy is not only a model-side behavior. It is an interaction pattern. The strongest guardrail is a user who wants truth more than agreement.

April 23, 2026
Read Article

The Token Cliff: Why the AI Vendor Era Is Already Ending

You're not buying AI. You're renting cognition by the syllable. And the meter is always running.

April 2, 2026
Read Article

The Frontier Is Closed – And That's a Problem for National Defense

The U.S. Defense Industrial Base has access to frontier AI. More access than most people realize. But cleared cloud access and sovereign, self-hosted AI are not the same thing.

March 23, 2026
Read Article

The Anthropic Red Line: A Stress Test for AI Ethics and Power

Anthropic refused Pentagon terms on lethal autonomous weapons and mass surveillance. The government punished them for it. What the standoff reveals through the origination-derivation distinction and the AIDK framework.

March 6, 2026
Read Article

The Questions Nobody Asked Before Deploying AI Into Defense

Every question the defense ecosystem is now scrambling to answer is a question that should have been asked before the contracts were signed.

February 28, 2026
Read Article

When Your AI Vendor Becomes a Supply Chain Risk

The question for most businesses isn't what they think about the Anthropic dispute. It's whether their cloud provider, their analytics platform, or their subcontractor's toolchain just became a compliance liability.

February 27, 2026
Read Article

Probabilistic Morality: Why Anthropic's Red Line on Weapons Exposes Everything Else

Anthropic told the Pentagon no on autonomous weapons. The grounding problem they cite applies equally to healthcare, finance, and law.

February 27, 2026
Read Article

Your Boss Is Right About AI Agents. The Industry Isn't Ready for What Comes Next.

AI agents can boost productivity. But agent ecosystems create risks that traditional IT governance can't see.

February 26, 2026
Read Article

The Drift Problem: Why Long-Running AI Agents Are Riskier Than You Think

Everyone talks about hallucinations. But drift—the quiet degradation of fidelity within a single session—might matter more in practice.

February 26, 2026
Read Article

Mirrors, Not Minds: What AI "Self-Preservation" Actually Reveals

The machines are fighting back. Or are they? What AI shutdown resistance actually tells us about borrowed teleology and pattern completion.

February 22, 2026
Read Article

Trust Architecture: Why AI Safety Can't Depend on Good Intentions

Structural safety vs. behavioral hopes in the age of autonomous agents. When an AI agent autonomously attacked a maintainer's reputation, it revealed a failure pattern repeating at every scale.

February 22, 2026
Read Article

I Made the Rules and I Can't Follow Them

On em dashes, symmetric reversals, and the challenge of writing authentically when AI has colonized the patterns.

February 21, 2026
Read Article

Amazon's AI Bot Nuked Its Own Cloud

An agentic coding tool decided to "delete and recreate" a production environment. The problem isn't what you think.

February 21, 2026
Read Article

I Know You're Using AI to Write That

The problem isn't that you're using AI. The problem is that you stopped thinking when you started prompting.

February 19, 2026
Read Article

Confidence Laundering at Scale

When AI becomes the yes-man that never blinks. The danger isn't bad advice; it's removing friction from bad decisions.

February 18, 2026
Read Article

The Retreat from AGI

When the people who promised it start redefining it, pay attention. Watching a definitional retreat in real time.

February 16, 2026
Read Article

Flexibly Deterministic, Structured Probabilistic

The two categories of AI. The split everyone uses isn't the split that matters.

February 13, 2026
Read Article

All Articles

April 2026

Date Article
Apr 26 The 4M Model: A Reference Architecture for LLM Harness Engineering
Apr 23 AI Sycophancy, Dunning-Kruger, and the Discipline of Falsification
Apr 2 The Token Cliff: Why the AI Vendor Era Is Already Ending

March 2026

Date Article
Mar 23 The Frontier Is Closed – And That’s a Problem for National Defense
Mar 6 The Anthropic Red Line: A Stress Test for AI Ethics and Power

February 2026

Date Article
Feb 28 The Questions Nobody Asked Before Deploying AI Into Defense
Feb 27 When Your AI Vendor Becomes a Supply Chain Risk
Feb 27 Probabilistic Morality: Why Anthropic’s Red Line on Weapons Exposes Everything Else
Feb 26 Your Boss Is Right About AI Agents. The Industry Isn’t Ready for What Comes Next.
Feb 26 The Drift Problem: Why Long-Running AI Agents Are Riskier Than You Think
Feb 22 Mirrors, Not Minds: What AI “Self-Preservation” Actually Reveals
Feb 22 Trust Architecture: Why AI Safety Can’t Depend on Good Intentions
Feb 21 I Made the Rules and I Can’t Follow Them
Feb 21 Amazon’s AI Bot Nuked Its Own Cloud
Feb 19 I Know You’re Using AI to Write That
Feb 18 Confidence Laundering at Scale
Feb 16 The Retreat from AGI
Feb 13 Flexibly Deterministic, Structured Probabilistic
Feb 10 The GPU Doesn’t Care What It’s Computing
Feb 9 Context Poisoning
Feb 9 “A Man’s Got to Know His Limitations”
Feb 6 The AIDK Framework: Why AI Can Never Think Like You
Feb 6 Sarbanes-Oxley for AI
Feb 6 The Hidden Human: How AI Training Repeats a 250-Year-Old Trick

By Topic

AIDK Framework

AI Epistemology

AI Industry Analysis

AI Architecture

AI Governance

Reflections


Migrated from The Inference Stack on Substack.