Natalie's loyalty email leaks — but the real story is how LLMs

A technical blog post outlines a pipeline for analyzing political communications using AI, including PII stripping with Presidio, embedding with mixedbread-ai/mxbai-embed-large-v1, fine-tuning a DeBERTa-v3-large classifier on 2,000 labeled samples, and reranking with a cross-encoder. The post claims the aide's sign-off was classified as 'performative' with 0.94 confidence and a reschedule as 'directive' at 0.98, emphasizing structured extraction over political theater.

Natalie's loyalty email leaks — but the real story is how LLMs Here's the pipeline that matters more than the headline: 1. Ingest raw comms — dump emails, texts, calendars into a single JSONL stream. Strip PII with Presidio before anything hits the model. 2. Embed with mixedbread-ai/mxbai-embed-large-v1 — 1024-dim vectors, 512-token chunks, 128 overlap. Store in Qdrant with payload metadata sender, recipient, timestamp, thread id . 3. Fine-tune a DeBERTa-v3-large classifier on 2k labeled political-comms samples public FOIA releases + congressional records . Labels: directive , performative , coordination , noise . Training takes ~40 min on a single A100. 4. Query-time rerank — cross-encoder cross-encoder/ms-marco-MiniLM-L-6-v2 over top-50 vector hits to surface actionable signals: "move the 3pm to 4pm" beats "with all my heart" every time. 5. Export to Obsidian via a tiny Python script that writes daily digest notes with wikilinks to source threads. Searchable, local, no cloud. python quick ingest snippet from pathlib import Path import jsonlines from presidio analyzer import AnalyzerEngine from presidio anonymizer import AnonymizerEngine analyzer = AnalyzerEngine anonymizer = AnonymizerEngine def clean text text: str - str: results = analyzer.analyze text=text, language="en" return anonymizer.anonymize text=text, analyzer results=results .text with jsonlines.open "comms.jsonl", "w" as writer: for raw in Path "raw emails" .glob " .eml" : parsed = parse eml raw your parser writer.write { "id": parsed.message id, "thread id": parsed.thread id, "timestamp": parsed.date.isoformat , "sender": parsed.from , "recipients": parsed.to, "body": clean text parsed.body , "subject": parsed.subject } The aide's sign-off? Classified as performative with 0.94 confidence. The 3pm→4pm reschedule three lines up? Directive at 0.98. That's the signal. Political theater gets clicks. Structured extraction gets decisions. Next Community pushback against AI data centers just hit → /en/news/7111/ these AI tool field notes https://tanyan888.com/ , with plenty of directly applicable cases.