Vibe coders are not going to like this. UC San Diego just published the first real field study of experienced developers using AI agents. Th…

Vibe coders are not going to like this. UC San Diego just published the first real field study of experienced developers using AI agents. They watched 13 of them code in the wild and surveyed 99 more. Zero of them vibe coded. Not one developer "fully gave in to the vibes." Not one trusted the agent to ship. The researchers found the opposite of what every Cursor demo on your timeline implies. Experienced devs plan before they prompt. They load the agent with heavy context. They verify every diff and refuse to merge code they haven't actually read. "Flow and joy" coding, the whole Karpathy vibe coding pitch, got quietly rejected by every professional in the study. They said it's fine for throwaway prototypes. Not for anything that ships. The devs still liked using agents. They just don't let the agent drive. Turns out the people who've shipped software for a decade know something the vibe coding influencers don't. Huang et al., UC San Diego. December 2025. Paper in comments.

Related

• SWE-chat: Coding Agent Interactions From Real Users in the Wild
• From Helpful to Trustworthy: LLM Agents for Pair Programming
• Agent responsibly
• CodeTracer: Towards Traceable Agent States

Source: Gary Marcus (X) | 2026-04-22