---
title: "Reconstructed Slides: Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs"
category: "slides"
video_id: "APh1Vx0oLmQ"
sourceLabels: ["Cropped public YouTube video frames", "Local OpenCV slide-region detection", "Local RapidOCR"]
---

# Reconstructed Slides: Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs

## Source Video
[Deterministic Infra for Non-Deterministic AI Agents - Nishant Gupta, Meta Superintelligence Labs](https://www.youtube.com/watch?v=APh1Vx0oLmQ)

## 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
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-001.jpg]]

- Source frame: `slide-001.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `176.52`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-002.jpg]]

- Source frame: `slide-002.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `177.86`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-003.jpg]]

- Source frame: `slide-003.jpg`
- Crop: `contour` `[0, 0, 960, 543]` score `177.96`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-004.jpg]]

- Source frame: `slide-004.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `176.41`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-005.jpg]]

- Source frame: `slide-005.jpg`
- Crop: `contour` `[0, 0, 960, 543]` score `176.82`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-006.jpg]]

- Source frame: `slide-006.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `178.25`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-007.jpg]]

- Source frame: `slide-007.jpg`
- Crop: `contour` `[0, 0, 960, 543]` score `176.3`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-008.jpg]]

- Source frame: `slide-008.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `175.92`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-009.jpg]]

- Source frame: `slide-009.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `176.43`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-010.jpg]]

- Source frame: `slide-010.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `174.33`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-011.jpg]]

- Source frame: `slide-011.jpg`
- Crop: `contour` `[0, 0, 960, 543]` score `175.21`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-012.jpg]]

- Source frame: `slide-012.jpg`
- Crop: `contour` `[0, 0, 960, 543]` score `172.46`
![[assets/reconstructed-slides/APh1Vx0oLmQ/slide-013.jpg]]

- Source frame: `slide-013.jpg`
- Crop: `full` `[0, 0, 960, 543]` score `177.75`
## Dense Scene-Detected Slide Candidates
- [[youtube-APh1Vx0oLmQ-dense-slides]]