Markdown source

The Z/L Continuum: Should AI Engineers Still Read Code?

Conference Context

Session Description

At AI Engineer Europe, two of the best speakers gave directly opposite advice. Zechner: slow the f*** down, read every line your model writes. Lopopolo: code is a liability, you don't even open the IDE anymore. Both got applause. The room walked out confused. On the train back I sketched the Z/L Continuum on a napkin — a five-stop spectrum from "read the clanker code" to "what IDE?" — and the whole week clicked into place. In this talk I'll walk through the Continuum, introduce FOMAT (Fear of Missing Agent Time — coined backstage by Michael Richman), and make four arguments: the Continuum is real, your stop is per-task not per-person, model capability bends everything toward L, and FOMAT is a filter problem, not an agent problem. You'll leave with a vocabulary for the argument every AI engineer is having right now. Audience takeaways A shared vocabulary (Z, L, the five stops) for the debate splitting AI engineering teams FOMAT — name the fear so you can manage it A per-task framework for choosing where on the Continuum to operate Why capability drift makes "I'll never let it cook" a losing position over time Speaker: Alex Volkov · ThursdAI · @altryne

Media Evidence

The State of MCP observability: Observable.tools — Alex Volkov and Benjamin Eckel, W&B and Dylibso (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Transcript Status

Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

People

Supporting Slides

Slide Evidence

Official YouTube Recording

Synthesis

Synthesized Breakdown

two talks at a engineer Europe. One guy is saying code is free and deleted his ID and the other one is saying read every effing line of code. So should AI engineers still recode their agents output in 2026? I named this the Zopo continue and you guys probably have argued about this in Slack.

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis uses the official schedule plus cached video transcripts. Official AI Engineer World's Fair San Francisco 2026 livestreams and cut videos are primary event video sources for transcript/slide evidence; external, historical, or speaker-matched videos remain supporting context unless manually verified as exact official event recordings.