# AI Barista Orders 120 Eggs With No Stove, Matt Pocock Skills, Build for the Next Model, The Gervais Principle

Page: https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728/ai-barista-orders-120-eggs-with-no-stove-matt-pocock-skills-build-for-the-next-model-the-gervais-principle
Text version: https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728/ai-barista-orders-120-eggs-with-no-stove-matt-pocock-skills-build-for-the-next-model-the-gervais-principle.md
Podcast: [You've Been a Bad Agent](https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728)
Published: 2026-05-09T16:26:19+00:00
Episode link: https://share.transistor.fm/s/f365174e
Audio file: https://media.transistor.fm/f365174e/d6f2eac0.mp3
Processing state: processed
JSON: https://stenobird.com/v1/public/podcasts/you-ve-been-a-bad-agent-7334728/episodes/ai-barista-orders-120-eggs-with-no-stove-matt-pocock-skills-build-for-the-next-model-the-gervais-principle
Duration seconds: 3018

## Resource

An exploration of the friction between rapid AI capability gains and the messy reality of real-world implementation. The hosts discuss everything from autonomous agents making disastrous supply chain errors to the potential for 'skills' to act as a new prompt-injection attack vector.

## Highlights
- Failure mode: Autonomous agents can cause physical-world chaos, such as ordering massive quantities of unusable supplies due to a lack of environmental context
- Main idea: The 'capability overhang' remains significant; even as models scale, the gap between raw intelligence and reliable, low-stakes decision-making is wide
- Practical takeaway: Using structured 'skills' (markdown paired with deterministic scripts) can significantly improve model performance and reliability
- Security risk: New prompting techniques like 'skills' may inadvertently create new prompt-poisoning attack vectors by being treated with system-prompt authority
- Future outlook: The next era of work may shift from performing tasks to becoming 'automation engineers' who manage agentic workflows

## Topics

AI Agents, LLM Prompting, Automation, Software Engineering, Autonomous Systems, Cloudflare, Anthropic, Prompt Injection

## Chapters
- 1:00 — Reflections on a Year in SF: A look back at the past year of the podcast, moving from startups to Cloudflare and the unique, time-distorting atmosphere of San Francisco.
- 16:00 — The Slow Pace of AI Progress: Discussing the tension between massive ARR growth at companies like Anthropic and the persistent difficulty in reliable prompting.
- 24:00 — The AI Barista Hall of Shame: A deep dive into the errors of Mona, an AI agent at a Stockholm cafe, including the infamous 120-egg order.
- 27:00 — The Future of Automation Engineering: Debating whether employees will eventually be tasked solely with automating their own roles and the implications for the workforce.
- 39:00 — iOS Live Activities and UI Surfaces: Exploring how mobile OS features like Live Activities can serve as high-priority surfaces for agentic notifications.
- 42:00 — Building for the Next Model: The frustration and strategy of developing tech that works on current models but might break with the next iteration.
- 46:00 — Prompt Poisoning and Scripted Skills: Analyzing how Matt Pocock's 'skills' approach uses markdown and scripts to change model behavior and the potential security risks involved.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/you-ve-been-a-bad-agent-7334728/episodes/ai-barista-orders-120-eggs-with-no-stove-matt-pocock-skills-build-for-the-next-model-the-gervais-principle/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/you-ve-been-a-bad-agent-7334728/ai-barista-orders-120-eggs-with-no-stove-matt-pocock-skills-build-for-the-next-model-the-gervais-principle.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.