Same prompt, same seed image: the coding harness still matters
NathanWilbanks_ · x · 2026-09-05
Using the exact same prompt and seed image ("create this as a real interactive UI in html / 3js"), the author shows that outputs differ noticeably across harnesses, concluding that the harness still matters even for the same underlying model.
Related event: Same Prompt, Different Results: Coding Harness Shapes Model Output Quality(3 posts)→
More from coding & agent
- The Inverted Prompt: A Satirical Guide to Resume-Driven Over-Engineering — adrianscottcom · 2026-09-05
- Together AI Ships Guide to Deploy a Chat API on Render Without Kubernetes — togethercompute · 2026-09-05
- GPT-6 Astra lands in Netlify AI Gateway and Agent Runners with zero config — thisiskp_ · 2026-09-05
- Dev tests fal.ai generative platform: streaming blocked by RTC issues, but Reactor is fun — flngr · 2026-09-05
- GPT-6 Astra base instructions run 16% longer than GPT-5.6 Sol's, cutting permission loops — WolframRvnwlf · 2026-09-05
- Entire proposes repo mirroring to stop agents re-cloning and hide team context — craigsdennis · 2026-09-05