Two frameworks. One conversation.

The 4D Framework describes the four human competencies you need to work well with AI. Its companion, the Capabilities and Limitations Framework, describes the four machine properties those competencies respond to. Each human 'D' has a machine property it is reacting to. Learn both and you stop being surprised by AI behaviour.

Human side meets machine side.

Human (4D)Machine propertyWhat it means in one line
DelegationSteerabilityDecide what to hand to AI and how to direct it. Because the model is controllable but not understanding.
DescriptionWorking MemoryGive it the right context, in the right size. Because it can only see what is in its window.
DiscernmentNext Token PredictionJudge what comes back. Because it writes plausible text, not retrieved truth.
DiligenceKnowledgeVerify and stand behind it. Because its knowledge has gaps and a cutoff date.

Real failures are two properties meeting.

Hallucinated citation

Next Token Prediction (generating what looks plausible) + Knowledge (gap the model does not know is there).

Drift over long conversation

Working Memory (early context fades) + Steerability (later instructions overwrite earlier ones).

Confidently wrong math

Next Token Prediction (fluency decoupled from truth) + Steerability (no native sense of quantity).

Agreeing with a bad premise

Trained disposition (sycophancy) + Next Token Prediction (continuing your framing).

The order, most to least trustworthy.

Most trustworthy

1. Steerability

If your instruction is short, concrete and verifiable, the model will follow it. Use precise output formats, hard limits, structured responses. Lean on this.

Usually trustworthy

2. Working Memory

Within a fresh, well-scoped context, it works with exactly what you give it. But the cliff is real: long docs or expectations of cross-session memory will silently break things.

Trust with verification

3. Next Token Prediction

It writes fluently. Whether what it writes is true is a separate question. Hallucinations live where you push toward the edge.

Least trustworthy

4. Knowledge

Bounded, dated, uneven. Anything recent, niche, contested or rare is suspect. Give the model the documents. Do not trust its memory.

A small model of the machine, in your head.

Fluent AI use is not about memorising every failure mode. It is about holding a small model of the machine in your head, clear enough that when something goes wrong, you can name which property drifted and respond accordingly. The properties stay stable even as models improve. Boundaries shift, edges move, but the four properties remain the same. That is why this framework is durable.

Source: Anthropic, "AI Fluency Framework: Capabilities and Limitations" (Dakan and Feller, 2026), CC BY-NC-SA 4.0.

Want the boardroom version of this?