Markdown source

Slides: Stop Making Models Bigger, Make Them Behave — Kobie Crawford, Snorkel

Source Video

Stop Making Models Bigger, Make Them Behave — Kobie Crawford, Snorkel

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

• Recreated text/layout view: open HTML recreation
• AI slide classifier: title_card confidence 0.98
• Text source: agent_vision.

Slide text:

Stop Making Models Bigger.

Make Them Behave

Making a 4B Model Outperform 235B on Tool Use for Financial Analysis

Kobie Crawford, Developer Advocate

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.99
• Text source: agent_vision.

Slide text:

What we’ll cover

1 Research Objective

2 The Approach

3 The Result

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.91
• Text source: agent_vision.

Slide text:

Qwen3 235B

FinQA Tool Use

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.98
• Text source: advanced OCR rapidocr-live/border-trim/opencv-adaptive.
• OCR decision: ready — dense chart slide with small labels, percentages, and QR code

Slide text:

GLLM Snorke

AIE 4B + RL 59.7%

.

235B 51.4%

ACCURACY SCORE Pass@1 line (59.7%)

Engineering the future ofAl

Hidden Non-Slide Evidence

• `slide-001.jpg` — speaker_stage confidence 0.97; stage photo with speaker and audience; projected slide is not a clean presentation frame
• `slide-006.jpg` — sponsor_logo confidence 0.96; closing logo/branding card, not a content slide

Classification audit: raw/sources/slide-ai-classification/slides/TNwJ1LMiENk/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.