Building an autopilot for long-form ads: GPT-6 Astra + Obsidian knowledge base
EXM7777 · x · 2026-09-10
Inspired by Andrej Karpathy's LLM Wiki concept, the author built an Obsidian knowledge base that stores everything their agents need for long-form AI video ads:
- Winning ad structures mined from the Meta Ad Library
- The sales spine, extracted before any script is written
- Script and master soundtrack mapping and cutting
- Character sheets locking characters, products and geography
- Timed sequences ready for video generation
The pipeline runs GPT-6 Astra with Higgsfield to go from research to final montage fully on autopilot; the full setup is documented in the linked article.
Related event: GPT-6 Astra Powers Fully Automated Long-Form AI Ad Pipeline(4 posts)→
More from coding & agent
- AIE Code Summit 2026 opens applications: 800 seats, keynotes streamed free — trq212 · 2026-10-27
- TRL adds Score Centering, a simple fix for RLHF training instability — lvwerra · 2026-10-27
- Precompute golden answers and match at runtime for exact wording control — colinmcnamara · 2026-10-27
- Dev argues there's still alpha in working with your coding agent interactively — alex_frantic · 2026-10-27
- Researchers launch AMA on patterns for safer AI agents used by citizen developers — Loose_Rip359 · 2026-10-27
- Gradio Adds In-Chat Human-in-the-Loop So ML Intern Pauses Before Training — Gradio · 2026-10-27