Understand this story
On November 4, 2026, Rohan Paul put forward the judgment that creative tools are learning taste from behavior rather than from prompts. This judgment appeared in his report on Selendis launching the video foundation model Archon. The report states that Archon can edit raw footage into a finished film zero-shot and continuously learns each creator's editing preferences through use; the preference signals come from the creator's operational decisions in the Selendis multiplayer editor, their past video works, and the reference videos they cite. Selendis says that with each video edited, the editor becomes more accurately adapted to that creator or team. There are currently no subsequent developments.
AI-generated from public reports
Developments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 4
Rohan Paul
Selendis launches video foundation model Archon, which can complete editing zero-shot and continuously learn according to creator preferences
Selendis launches video foundation model Archon, which can zero-shot edit raw footage into a finished video and continuously learn each creator's editing preferences during use. Preference signals come from three sources: the creator's operational decisions in the Selendis multiplayer editor, their past video works, and the reference videos they cite. Selendis says that with every video edited, the editor becomes more accurate for that creator or team.