{
  "_meta": {"verified": "2026-07-31", "note": "Grox = X's LLM (Grok VLM) content-understanding layer, open-sourced as orchestration code with every prompt template and model config withheld (grox.prompts.template / grox.config imports don't exist in the repo). We know WHAT it scores, not HOW it decides."},
  "classifiers": [
    {"slug": "banger-screen", "name": "\"Banger\" quality screening", "file": "grox/classifiers/content/banger_initial_screen.py + grox/tasks/task_banger_screen.py + grox/plans/plan_initial_banger.py", "what": "An LLM pass that screens posts for quality — X literally runs a 'is this a banger' classifier over content. Output feeds quality/slop scoring used in content understanding.", "implication": "Content quality is machine-read by a language model, not inferred from engagement counts alone. Slop is detectable and detected."},
    {"slug": "spam", "name": "Spam detection", "file": "grox/classifiers/content/spam.py + grox/plans/plan_spam_comment.py", "what": "LLM spam classification including reply/comment spam — the reply-guy economy is machine-screened.", "implication": "Template replies, copypasta, and AI-generated reply-farming are exactly what an LLM classifier catches that keyword rules never could."},
    {"slug": "safety", "name": "Safety screens", "file": "grox/classifiers/content/post_safety_screen_deluxe.py + safety_ptos.py + grox/plans/plan_post_safety.py", "what": "Multi-tier safety screening (including a 'deluxe' pass and PTOS policy screening) whose verdicts feed the withheld visibility-filtering layer.", "implication": "The enforcement thresholds are not public; no external tool can tell you your safety verdict."},
    {"slug": "reply-ranking", "name": "Reply ranking", "file": "grox/classifiers/content/reply_ranking.py + grox/plans/plan_reply_ranking.py", "what": "Replies under a post are themselves ranked by an LLM pass — reply visibility is a judged competition, not chronological.", "implication": "A thoughtful reply can outrank earlier/louder ones; low-effort first-replies are demotable on content alone."},
    {"slug": "embeddings", "name": "Multimodal post embeddings", "file": "grox/embedder/multimodal_post_embedder_v2.py / _v5.py + summarizer/", "what": "Posts (text + media, with ASR for audio) are embedded and summarized by the VLM — this is the ONLY path by which your content's meaning reaches the recommendation system.", "implication": "The system reads what your post is about, including what's inside images and video audio. Alt-text games and keyword stuffing don't reach the ranker; meaning does."}
  ]
}