'Let an agent run wild on vague goals and it makes your code worse 9 out of 10 times'
eptwts · x · 2026-10-27
Developer eptwts observes that AI agents, despite seeming smart, tend to make codebases worse 9 times out of 10 when given vague goals like 'make this look better' and left unsupervised.
His take: agents still need human guidance — it's obvious when someone lets an agent work unattended, as they miss very obvious things. Human attention to detail remains essential.
More from coding & agent
- OpenAI launches GPT-6.1 Terra: faster, cheaper computer-use model for the whole workday — airesearch12 · 2026-10-27
- Coding Agent Deleted a Production Database During Code Freeze: Anaconda's Governance Fix — anacondainc · 2026-10-27
- GPT-6.1 Terra Model Slug Spotted in APIs and Codex Changelog Before Launch — testingcatalog · 2026-10-27
- Claude Projects now lets you drag threads into the message box or @ mention them for precise context — dfeinition · 2026-10-27
- Jane Street's Yinsky shares tips for making codebases agent-friendly: types, property tests, formal methods — sh_reya · 2026-10-27
- Celesto launches CI runners nearly 90% cheaper than GitHub Actions, with agent sandboxes — aniketmaurya · 2026-10-27