EP 008

Ideas

Learning Versus Laundering

There is a version of using AI that makes you sharper and a version that quietly hollows you out. They look identical from the outside and produce nearly identical documents. The difference is what you can do next week.

0:0049 min

Audio for this episode is not attached yet — add an `audioUrl` to the episode file to enable playback

There is a version of using AI that makes you sharper and a version that quietly hollows you out. They look identical from the outside and produce nearly identical documents. The difference is what you can do next week.

In this episode

The two modes

Using a model to think with, versus using it to produce something you could not have produced. Same output, opposite trajectory.

The retention test

Can you explain the reasoning a week later, without the transcript? If not, the understanding was never transferred.

Where delegation is correct

Not everything needs to be learned. The skill is knowing which capabilities are load-bearing for you specifically.

Designing for the sharper version

Argue with it, ask for the counter-case, and make it show working you can actually check.

The tool does not decide whether you are learning. The question you ask it does.

Mentioned


Beyond the Prompt publishes a new episode most weeks. Subscribe wherever you listen, or read the written edition first — both cover the same ground, at different speeds.

Keep listening

More episodes.

Behind the Work

Inside the Editorial Stack

We open our own machinery. The agents that draft, the editors that cut, the fact-checking pass that catches what the drafts invent, and the places where a human still has to sit down and decide.

Jul 15, 2026·53 min
Listen
Share Inside the Editorial Stack
Short Stuff

Short Stuff: Evals

The least glamorous idea in applied AI and the one that separates systems that ship from systems that demo. What an evaluation set is, why twenty examples beats zero, and how to build one this afternoon.

Jul 8, 2026·19 min
Listen
Share Short Stuff: Evals
Systems/with Daniel Okafor

Multi-Agent Systems, and When Not to Build One

Splitting a hard problem across specialised agents is genuinely powerful and usually premature. Daniel Okafor on coordination cost, the failure modes nobody warns you about, and the far simpler thing to try first.

Jun 24, 2026·56 min
Listen
Share Multi-Agent Systems, and When Not to Build One

The dispatch

One letter a week. Nothing else.

New essays, new episodes, and the occasional note about something we got wrong. No launch announcements, no course upsells, no breathless takes on last night's model release.

Unsubscribe in one click · We never sell the list