{"slug": "two-gaps-in-every-hosted-ai-call-which-model-ran-and-who-saw-the-prompt-what-i", "title": "Two gaps in every hosted AI call: which model ran, and who saw the prompt. What I run to close both, and where each one still falls short.", "summary": "A developer outlines two gaps in every hosted AI API call — verifying which model actually ran and who saw the prompt — and describes the tooling they run to close both, along with where each approach still falls short. The writeup covers open-source and privacy-focused methods for auditing LLM providers rather than trusting them on faith.", "body_md": "Two ways to stop trusting your AI provider on faith\nGeorge Orwell\nGeorge Orwell\nGeorge Orwell\nFollow\nOct 11\nTwo ways to stop trusting your AI provider on faith\n#\nai\n#\nopensource\n#\nprivacy\n#\nllm\n3\nreactions\n2\ncomments\n4 min read", "url": "https://wpnews.pro/news/two-gaps-in-every-hosted-ai-call-which-model-ran-and-who-saw-the-prompt-what-i", "canonical_source": "https://dev.to/orwell1776/two-gaps-in-every-hosted-ai-call-which-model-ran-and-who-saw-the-prompt-what-i-run-to-close-aic", "published_at": "2026-10-12 23:45:03+00:00", "updated_at": "2026-10-12 23:55:37.821818+00:00", "lang": "en", "topics": ["large-language-models", "ai-tools", "ai-infrastructure", "ai-safety"], "entities": [], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/two-gaps-in-every-hosted-ai-call-which-model-ran-and-who-saw-the-prompt-what-i", "markdown": "https://wpnews.pro/news/two-gaps-in-every-hosted-ai-call-which-model-ran-and-who-saw-the-prompt-what-i.md", "text": "https://wpnews.pro/news/two-gaps-in-every-hosted-ai-call-which-model-ran-and-who-saw-the-prompt-what-i.txt", "jsonld": "https://wpnews.pro/news/two-gaps-in-every-hosted-ai-call-which-model-ran-and-who-saw-the-prompt-what-i.jsonld"}}