Debate: does Claude's power come from model or harness?

Developer ryunuck sparred with Sean McClure over whether Claude's ability comes from the model or its harness, alleging Anthropic's "thinking" messages are just a 15-second timer rotation and that saying "Claude did it" launders human involvement.

2026-09-25 ~ 2026-09-25 · 3 related posts

• LLM vs Agent vs Harness: X Debate Erupts Over Whether Scaffolding, Not Models, Drives Capability Gains — sean_a_mcclure · 2026-09-25
• Dev disassembles Claude Code: the "thinking" status labels are just a 15-second timer — ryunuck · 2026-09-25
• Why Anthropic Says 'Claude Did' Instead of 'We Did' — A Take on Blame and Hacking Disasters — ryunuck · 2026-09-25