Reconstructed Slides: The State of AI Code Quality: Hype vs Reality — Itamar Friedman, Qodo

Source Video

The State of AI Code Quality: Hype vs Reality — Itamar Friedman, Qodo

Method

This deck is reconstructed from the existing video frame captures by detecting likely slide regions with OpenCV, cropping/upscaling those regions, deduplicating similar crops, and OCRing the cropped slide images locally. It is a cleaner companion to the full-stage frame deck.

Reconstructed Slides

• Source frame: slide-001.jpg
• Crop: full [0, 0, 960, 540] score 163.04

• Source frame: slide-002.jpg
• Crop: contour [0, 0, 960, 540] score 177.89

• Source frame: slide-003.jpg
• Crop: contour [0, 0, 960, 540] score 167.58

• Source frame: slide-004.jpg
• Crop: full [0, 0, 960, 540] score 177.61

• Source frame: slide-005.jpg
• Crop: full [0, 0, 960, 540] score 161.68

• Source frame: slide-006.jpg
• Crop: full [0, 0, 960, 540] score 163.81

• Source frame: slide-007.jpg
• Crop: full [0, 0, 960, 540] score 177.31

• Source frame: slide-008.jpg
• Crop: contour [0, 0, 960, 540] score 177.16

• Source frame: slide-009.jpg
• Crop: contour [0, 0, 960, 540] score 167.88

• Source frame: slide-010.jpg
• Crop: full [0, 0, 960, 540] score 176.3

• Source frame: slide-011.jpg
• Crop: full [0, 0, 960, 540] score 163.4

• Source frame: slide-012.jpg
• Crop: full [0, 0, 960, 540] score 163.02

• Source frame: slide-013.jpg
• Crop: full [0, 0, 960, 540] score 166.89

• Source frame: slide-014.jpg
• Crop: contour [0, 0, 960, 540] score 176.97

• Source frame: slide-015.jpg
• Crop: full [0, 0, 960, 540] score 164.16