Agentic video's real story isn't watching 90 minutes—it's reasoning about where to spend compute
romitheguru · x · 2026-09-09
The author argues the interesting part of "agentic video" is not that AI can watch a 90-minute video, but that it doesn't have to. Instead of processing every frame equally, the emerging pattern is: question → search → candidate moments → inspect deeply → answer. AI is starting to reason about computation itself, allocating compute only where it matters.
More from Models
- Thomson Reuters' 397B Qwen-based legal LLM beats GPT-5.4 on domain factuality — DeepLearningAI · 2026-09-09
- 27B 1-bit model runs in the browser at 25-30 tok/s on a 6GB RTX 3060 laptop (WebGPU) — mentria-ai · 2026-09-09
- GPT-6 Astra Pro/Ultra review: first LLM to nail one-shot prompts nearly every time — rschu · 2026-09-09
- Raschka dissects GPT-6 Astra: looped transformers, recurrent depth, hidden CoT — rasbt · 2026-09-09
- GPT-6 Astra system card draws fire: OpenAI claims 'most aligned model' ever — TheZvi · 2026-09-09
- Muse reportedly makes phone calls in Croatian, but users say it denies the ability — nathanbenaich · 2026-09-09