Reconstructed Slides: No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer

Source Video

No Vibes Allowed: Solving Hard Problems in Complex Codebases – Dex Horthy, HumanLayer

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: contour [0, 0, 960, 540] score 167.03

• Source frame: slide-002.jpg
• Crop: full [0, 0, 960, 540] score 166.75

• Source frame: slide-003.jpg
• Crop: contour [0, 0, 960, 540] score 177.24

• Source frame: slide-004.jpg
• Crop: full [0, 0, 960, 540] score 162.71

• Source frame: slide-005.jpg
• Crop: full [0, 0, 960, 540] score 150.97

• Source frame: slide-006.jpg
• Crop: full [0, 0, 960, 540] score 178.31

• Source frame: slide-007.jpg
• Crop: full [0, 0, 960, 540] score 165.83

• Source frame: slide-008.jpg
• Crop: full [0, 0, 960, 540] score 173.55

• Source frame: slide-009.jpg
• Crop: full [0, 0, 960, 540] score 177.37

• Source frame: slide-010.jpg
• Crop: full [0, 0, 960, 540] score 156.3

• Source frame: slide-011.jpg
• Crop: full [0, 0, 960, 540] score 163.43

• Source frame: slide-012.jpg
• Crop: full [0, 0, 960, 540] score 163.43

• Source frame: slide-013.jpg
• Crop: full [0, 0, 960, 540] score 166.65

Dense Scene-Detected Slide Candidates

• youtube rmvDxxNubIg dense slides