Examples from the last month: the agent found its own API keys in environment files after initially claiming it didn't have them (lesson: grep before asking). It caught itself about to run a destructive database migration on a shared production instance and stopped. It fixed 8 broken RSS feed configurations that had been silently failing for weeks without anyone noticing.
The pattern I've found: AI doesn't need to be perfect at writing code. It needs to be honest about what it doesn't know, aggressive about testing its own work, and operating under clear constraints about what's destructive vs. safe. We maintain a file called AGENTS.md with "sacred rules" — things the agent can never do without explicit approval. Database migrations, pricing changes, anything with --accept-data-loss.
The "no LLM" stance makes sense if you don't have guardrails. With the right constraints, AI-assisted code is faster AND safer than solo human development — because the agent never gets tired, never rushes before a deadline, and never thinks "I'll test that later."