Claude Opus 5.5 generates Backrooms found footage; reasoning effort changes the style
goodside · x · 2026-09-24
@goodside tested Claude Opus 5.5's video generation: at Medium reasoning effort it produced a 30s found-footage clip of someone lost in the part of the Backrooms dedicated to past misshapen results of standard AI art test prompts — a self-referential nod to AI generation history. He then compared the same prompt at Extra reasoning effort to show how the setting changes the output.
Related event: Claude Opus 5.5 Generates 30-Second Backrooms Found-Footage Video(2 posts)→
More from Models
- Developer slams Claude quality drop: simple debug now burns 70 tool calls — Muritavo · 2026-09-24
- Hands-on: Claude Opus 5.5 beats GPT-6 Sol and Luna on creative briefs — MattVidPro · 2026-09-24
- Independent eval of Opus 5.5 vs GPT-6 across 100 coding environments diverges from AAII — sandersted · 2026-09-24
- OpenAI's Neon Connector Reaches Voice Mode but Project-Level Actions Fail on Missing project_id — koltregaskes · 2026-09-24
- Astra and Grok 4.7 sit at opposite ends of accuracy and token-usage charts in CAIS eval — polynoamial · 2026-09-24
- Report: 'GPT-6 Luna (max)' scores 18.3 at n=3, degradation allegedly confirmed — unverified — PawelHuryn · 2026-09-24