The video editor's ingest layer executes commands to transcribe video, create proxies (converting 4K to smaller files for easier API handling), perform audio analysis, transcription, and video clipping to remove dead noise—all happening before structured data generation.

factualpending

Speaker

Adam

Evidence Quote

it's executing commands to transcribe that video, to create a proxy... We do audio analysis. We do transcription, and then we do video clipping, which is basically clipping out dead noise

Source

Karpathy's LLM Wiki Goes Further Than Everyone RealisedAdam Goodyer
Created: 8/13/2026, 9:47:09 AM

My Notes

Loading notes...