“Vibe coding” – developing software by iteratively conversing with a large language model (LLM) – has exploded in popularity within the last year. However, developers report key limitations of vibe coding, including the accumulation of technical debt, security issues, and code churn. We argue that these pitfalls result from LLMs’ inability to reconcile accumulating human-imposed constraints during vibe coding, with developers inadvertently failing to resolve contradictions because LLMs prioritize user commands over code consistency. Given LLMs’ receptiveness to verification-based feedback, formal methods can help mitigate these pitfalls, making vibe coding more reliable. But, we posit that integrating formal methods must transcend existing approaches that combine formal methods and LLMs. We advocate for a sidecar system throughout the vibe coding process which: (1) \emph{Autoformalizes} specifications (2) Validates against targets, (3) Delivers \emph{actionable} feedback to the LLM, and (4) Allows intuitive developer influence on specifications.