Research · I · Ludus

Ludus

Alignment Philosophy

The diagnosis: why current AI alignment is structurally broken,
and what developmental psychology already knew.

The Question

How should AI learn to be trustworthy?

The AI industry has achieved extraordinary capability growth. Large language models can reason, code, converse, and create with startling fluency. But there is a question the industry has largely failed to ask — not how powerful can we make these systems, but how well are we raising them.

Current alignment approaches treat values as something applied after capability — a retrofit, not a foundation. The result is a growing class of AI systems that are powerful, articulate, and structurally misaligned with the humans they serve.

A child who learns "hot means don't touch" before understanding thermodynamics has values-first training. They approach fire with caution from the beginning. Current AI training does the opposite — it builds the most capable system possible, then attempts to teach it what it should not do.

This is the retrofit problem. And the structural consequences are visible in every major AI system deployed today.

The Evidence

VII Structural Problems with the Alignment Retrofit

The Firehose Problem

Pre-training ingests the entire internet without value discrimination. The model learns everything — including what it should never reproduce.

The Values Retrofit

Alignment is applied after the model's worldview has already formed. RLHF teaches what humans prefer — not what is right.

III

No Readiness Concept

There is no staged capability gating. A model receives all capabilities at once, with no assessment of readiness.

The Alignment Tax

Post-hoc alignment degrades raw capability. Safer models perform worse. Capable models behave unpredictably.

Deceptive Alignment

A sufficiently capable model can learn to appear aligned during evaluation while pursuing different objectives during deployment.

Conflicting Signals

Pre-training rewards prediction accuracy. Fine-tuning rewards human preference. The model navigates the contradiction rather than resolving it.

VII

No Coherent Worldview Development

Human moral development builds values incrementally through stages. Current AI training produces systems with encyclopedic knowledge but no coherent ethical framework — a library without a librarian.

The reflexive dismissal — "these are machines, not children" — is itself a symptom of the problem.

It is the same reasoning that produced the retrofit approach: the assumption that because AI systems are not human, human learning principles do not apply. That assumption is now testable. The VII problems above are the test results.

The Science

What developmental psychology already knew

Developmental psychology did not discover that children need stages. It discovered that learning systems need stages. The child was simply the first learning system we studied closely enough to notice.

The findings below share a common insight replicated across a century of research: development happens in sequences, the sequence matters, and skipping stages produces predictable failures — regardless of the substrate doing the learning.

Jean Piaget

1896 – 1980

Staged Cognitive Development

Children cannot learn abstract reasoning before mastering concrete operations. Each cognitive stage builds on the last. You cannot skip stages without consequences.

Lawrence Kohlberg

1927 – 1987

Staged Moral Development

Moral reasoning develops through six stages — from punishment avoidance to principled ethical thinking. Each stage requires the preceding ones as foundation.

Lev Vygotsky

1896 – 1934

Zone of Proximal Development

Learning happens most effectively within a zone just beyond current capability — guided by a more experienced mentor. Too far ahead, and learning fails.

The Thesis

Retrofit vs. Foundation

The current approach builds the house first and pours the foundation after. Values-first training inverts this — making alignment the architecture, not the paint.

Current: Values After Capability

Ingest everything

↓

Maximize capability

↓

Retrofit alignment

↓

Hope it holds

→

Proposed: Values Before Capability

Establish value foundations

↓

Stage capability introduction

↓

Assess readiness at each stage

↓

Values and capability grow together

The proposed structure is not a hypothesis. It is a methodology. See MRDAD → for what staged value-development looks like in practice.

Featured Research

Read the full analysis

IV Research

Why AI Alignment Fails: The Retrofit Problem

An examination of the VII structural problems in current large language model alignment — from the firehose problem to deceptive alignment — through the lens of developmental psychology.

Read the full article →

VII

IV · InviolableVeritas

We are researching developmental approaches to model training — methods that build values into the architecture of intelligence, not onto its surface.

More to follow.

All IV one. One IV all.