GPT-6.1 Sol overengineering: dev reports 115k lines of tests for 6k lines of code
Im_IrushiK · x · 2026-10-30
A developer reports that GPT-6.1 Sol has a serious overengineering problem: a project with roughly 6,000 lines of production code ended up with about 115,000 lines of test code — nearly a 19x ratio.
He says repeated prompts to keep things simple don't help, as the model keeps overengineering everything, and asks whether others are hitting the same issue.
Related event: Devs slam GPT-6.1 over-engineering: 115K test lines for 6K code(3 posts)→
More from coding & agent
- krishnan on autonomous lab agents: criticism changed the next search, not just verdicts — krishnan · 2026-10-31
- Testing agents with explicit rejection records: a cheaper path to verified troubleshooting answers — krishnan · 2026-10-31
- krishnan proposes logging ruled-out troubleshooting hypotheses for future reopening — krishnan · 2026-10-31
- Multi-agent AI lab autonomously researches quantum spins in diamond, revises drifting experiments — krishnan · 2026-10-31
- PI agent rejected 75 proposals in 30 hours; manager banned recurring bad ideas — krishnan · 2026-10-31
- Next 9 proposals explored 7 new directions: rejection became information — krishnan · 2026-10-31