Rodin
6af8a6ee10
Break the monolithic 3249-line findings file into 29 individual files, one per experiment. Each file is named YYYY-MM-DD-NN-slug.md for easy chronological sorting and discovery. No content changes — purely structural reorganization.
1006 B
1006 B
Finding 4: GPT-5 defaults to delegation; Claude defaults to doing the work
Date: 2026-04-26 Task: PR review delegation to sub-agents How we used them: Both spawned as sub-agents from main session with same task description, same pr-review skill file, same Gitea credentials. Difference: GPT-5 got model override to gpt5, Sonnet used default model. Both got full skill instructions.
- GPT-5 first attempt: spawned sub-sub-agents and timed out
- GPT-5 with "do it yourself, no sub-agents" + step-by-step: worked
- Even with constraints, GPT-5 sometimes dumps raw tool output instead of synthesizing — needs explicit output format instructions
- Claude (Sonnet/Opus) given the same kind of task does the work directly
- Takeaway: GPT interprets complex task descriptions as delegation opportunities. Claude interprets them as work to do. For GPT: explicit single-actor instructions + output format. For Claude: can give broader mandate. Same skill file, very different behavior.