· 4 min read
AI EngineeringAn LLM will confidently return malformed JSON, leaked prompts, or unsafe content. Treat its output as untrusted input and validate it like you would a form submission.
Read article· 4 min read
2 articles
An LLM will confidently return malformed JSON, leaked prompts, or unsafe content. Treat its output as untrusted input and validate it like you would a form submission.
You don't need an OpenAPI pipeline to get end-to-end types on fetch. Validate responses at the boundary and let inference do the rest.