Dense Slides: Jack Morris: Stuffing Context is not Memory, Updating Weights is

Source Video

Jack Morris: Stuffing Context is not Memory, Updating Weights is

Method

This deck is slide-only. The existing captured video frame set supplies candidate frames, then local OpenCV rejects sponsor/title/speaker-only frames, crops visible slide surfaces, deduplicates, and saves the cropped slide images.

Cropped Visible Slides

Recreated text/layout view: open HTML recreation
AI slide classifier: content_slide confidence 0.98
Text source: agent_vision.
OCR decision: ready — Product-style screenshot with dense small on-slide text; OCR will be more reliable than manual transcription for the embedded UI content.

Slide text:

LLMs have fixed capacity

but probably know too much

Recreated text/layout view: open HTML recreation
AI slide classifier: content_slide confidence 0.97
Text source: none.
OCR decision: ready — Dense multi-column academic-paper comparison slide with small body text and citations; OCR is the right extraction path.

Recreated text/layout view: open HTML recreation
AI slide classifier: content_slide confidence 0.95
Text source: agent_vision.

Slide text:

ICL

RAG

Full Finetune

LoRA

Cartridges

Memory Layers

Classification audit: raw/sources/slide-ai-classification/dense/Jty4s9-Jb78/audit.json