---
title: "Slides: Field Guide to Fable — Thariq Shihipar, Anthropic"
category: "slides"
video_id: "9fubhllmsBU"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: Field Guide to Fable — Thariq Shihipar, Anthropic

## Source Video
[Field Guide to Fable — Thariq Shihipar, Anthropic](https://www.youtube.com/watch?v=9fubhllmsBU)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/9fubhllmsBU/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-004.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> The Map is Opening Up
> In the Land of AI Agents, the Verifiers Are King

![[assets/slides/9fubhllmsBU/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> A Field Guide to Fable:
> 1 Unhobbling Claude
> 2 Finding your Unknowns
> 3 Dealing with the Grief
> 4 Being Unreasonable

![[assets/slides/9fubhllmsBU/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Models are grown, not designed.

![[assets/slides/9fubhllmsBU/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.92`
- Text source: agent_vision.
- OCR decision: ready — contains a dense code screenshot suitable for OCR

Slide text:

> Fetch every Pokémon. Write a script. Filter for “aw.”

![[assets/slides/9fubhllmsBU/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.

Slide text:

> CAPABILITY OVERHANG
> Claude gets smarter in spiky ways

![[assets/slides/9fubhllmsBU/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-009.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> It's closer to a biology, than a physics.
> On the Biology of a Large Language Model
> Anthropic · transformer-circuits.pub

![[assets/slides/9fubhllmsBU/slide-010.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-010.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.

Slide text:

> the most important part of working with Fable is staying in the loop

![[assets/slides/9fubhllmsBU/slide-011.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-011.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> The past is a foreign country
> 2019-2024 · a 30-person YC startup · 12 engineers

![[assets/slides/9fubhllmsBU/slide-012.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/9fubhllmsBU/slide-012.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> The past is a foreign country
> 2019-2024 · a 30-person YC startup · 12 engineers


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/9fubhllmsBU/slide-001.jpg) — `title_card` confidence `0.03`; stage intro title screen, not a presentation content slide
- [`slide-002.jpg`](/assets/slides/9fubhllmsBU/slide-002.jpg) — `speaker_stage` confidence `0.02`; speaker shot in front of sponsor wall, not a slide
- [`slide-003.jpg`](/assets/slides/9fubhllmsBU/slide-003.jpg) — `speaker_stage` confidence `0.02`; speaker shot in front of sponsor wall, not a slide
- [`slide-013.jpg`](/assets/slides/9fubhllmsBU/slide-013.jpg) — `title_card` confidence `0.98`; logo/end card

Classification audit: `raw/sources/slide-ai-classification/slides/9fubhllmsBU/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.