---
title: "Slides: What Lies Beneath the API — Benjamin Cowen, Modal"
category: "slides"
video_id: "HvZXAOZ3iv8"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: What Lies Beneath the API — Benjamin Cowen, Modal

## Source Video
[What Lies Beneath the API — Benjamin Cowen, Modal](https://www.youtube.com/watch?v=HvZXAOZ3iv8)

## 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/HvZXAOZ3iv8/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HvZXAOZ3iv8/slide-002.html)
- AI slide classifier: `title_card` confidence `0.98`
- Text source: agent_vision.

Slide text:

> What Lies Beneath the API:
> When you should fine-tune your own model
> Benjamin Cowen, PhD

![[assets/slides/HvZXAOZ3iv8/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HvZXAOZ3iv8/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.97`
- Text source: agent_vision.
- OCR decision: ready — dense multi-column slide with small labels and diagram text

Slide text:

> Modal 101

![[assets/slides/HvZXAOZ3iv8/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HvZXAOZ3iv8/slide-005.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.

Slide text:

> Use a frontier API
> Move fast. Ship something.
> Works for
> Get started fast
> No infrastructure overhead
> Very good models!
> When you might want to shift
> You need performance control at scale
> Cost, throughput, latency, custom metric
> You need model differentiation
> You're hitting rate limits

![[assets/slides/HvZXAOZ3iv8/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HvZXAOZ3iv8/slide-006.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — dense code screenshot with small text and compact layout

Slide text:

> SFT in 300 lines of code

![[assets/slides/HvZXAOZ3iv8/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/HvZXAOZ3iv8/slide-007.html)
- AI slide classifier: `content_slide` confidence `0.98`
- Text source: agent_vision.
- OCR decision: ready — dense code screenshot with small text and compact layout

Slide text:

> GRPO (RL) in 300 lines of code.


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/HvZXAOZ3iv8/slide-001.jpg) — `speaker_stage` confidence `0.99`; speaker on stage with audience; no readable slide content
- [`slide-004.jpg`](/assets/slides/HvZXAOZ3iv8/slide-004.jpg) — `speaker_stage` confidence `0.98`; speaker on stage with a blank projected screen; no readable slide content

Classification audit: `raw/sources/slide-ai-classification/slides/HvZXAOZ3iv8/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.