Skip to content

Fast LLM + Human-in-the-Loop classification post; refresh featured post & series#160

Open
anishk123 wants to merge 3 commits into
scribd:mainfrom
anishk123:fast-llm-hitl-classification
Open

Fast LLM + Human-in-the-Loop classification post; refresh featured post & series#160
anishk123 wants to merge 3 commits into
scribd:mainfrom
anishk123:fast-llm-hitl-classification

Conversation

@anishk123

@anishk123 anishk123 commented Jul 11, 2026

Copy link
Copy Markdown
Contributor

This adds a new ML Data Engineering blog post and refreshes the homepage's Featured Post and Featured Series.

What changed

  • New post: _posts/2026-07-11-fast-llm-human-in-the-loop-classification.md"How a Three-Person Team Used Cheap, Fast LLMs + Human-in-the-Loop to Classify Hundreds of Millions of Documents in ~2 Months." Content adapted from the source doc; formatting cleaned up for the web (bulleting, code/table blocks, the recurring "Fast Model → Judge Model → SME Review → Ingest → Iterate" mantra styled as callouts) with the wording unchanged.
  • Tagged featured (dated 2026-07-11, so it becomes the newest Featured Post) and content-trust-series (so it joins the Featured Series).
  • PhotoDNA post: removed the content-trust-series tag from _posts/2026-01-20-photodna-csam-detection.md so it drops out of the featured series.

Visuals

Three on-brand SVG diagrams (Scribd palette) are embedded in the post:

  • The repeatable loop — under Workflow Overview (the spot flagged for a diagram): Fast Model → Judge → SME → Ingest → Iterate.
  • Breadth-to-precision funnel — under Sampling Strategy: 100% fast-model labels → 1% validation → 0.1% judge → SME reviews only disagreements.
  • Human-in-the-loop — under The Core Point: model proposes, humans decide, deterministic rules apply.

Assets live in post-images/2026-fast-llm-hitl/.

Review fixes

  • Added tag/llm/index.md so the new llm tag no longer 404s (Cursor Bugbot).
  • Fixed the Appendix B Mermaid (quoted node labels containing parentheses so it renders) and pointed it at the rendered diagram above.

Resulting homepage state

  • Featured Post: this new post.
  • Featured Series (site.featured_series: content-trust-series, shows 2): Dual-Embedding Trust Scoring + this new post. PhotoDNA is no longer in the series.

No _config.yml change needed — featured_series is already content-trust-series.


Note

Low Risk
Static Jekyll blog and image assets only; no runtime, auth, or config changes beyond post front matter and a tag index page.

Overview
Adds a new featured ML Data Engineering article on scaling document classification with fast LLMs, judge models, SME review in Google Sheets, and Databricks batch workflows, tagged for the content-trust-series so it surfaces on the homepage.

Homepage / series: The PhotoDNA post loses content-trust-series so the featured series slot (two posts under site.featured_series) shifts to Dual-Embedding Trust Scoring plus this new piece instead of PhotoDNA.

Assets & tags: Three branded SVGs under post-images/2026-fast-llm-hitl/ illustrate the loop, sampling funnel, and human-in-the-loop flow. A new tag/llm/index.md page fixes navigation for the post’s llm tag.

Reviewed by Cursor Bugbot for commit b159a27. Bugbot is set up for automated code reviews on this repo. Configure here.

anishk123 and others added 2 commits July 11, 2026 09:49
Pull in head repo main
…ries

New post 'How a Three-Person Team Used Cheap, Fast LLMs + Human-in-the-Loop
to Classify Hundreds of Millions of Documents in ~2 Months', tagged both
'featured' (becomes the featured post) and 'content-trust-series' (joins the
featured series). Removes 'content-trust-series' from the PhotoDNA post so the
series now shows Dual-Embedding Trust Scoring + this new post.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

@cursor cursor Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.

Fix All in Cursor

❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.

Reviewed by Cursor Bugbot for commit be422e8. Configure here.

Comment thread _posts/2026-07-11-fast-llm-human-in-the-loop-classification.md
- Add tag/llm/index.md so the new `llm` tag no longer 404s (Cursor Bugbot;
  matches the CONTRIBUTING generate-tags output format).
- Fix the Appendix B Mermaid: quote node labels containing parentheses so it
  renders (previously broken syntax). Heading and text otherwise unchanged
  from the source doc.
- Add three on-brand SVG diagrams (Scribd palette) grounded in the post text:
  - Workflow Overview: the repeatable Fast Model -> Judge -> SME -> Ingest ->
    Iterate loop.
  - Sampling Strategy: breadth-to-precision funnel (100% -> 1% -> 0.1% -> SME
    reviews the disagreements).
  - The Core Point: human-in-the-loop (model proposes labels, humans have the
    final say, corrections grow a versioned golden set, feeding back).
- Add horizontal-rule dividers between top-level sections for readability
  (mirrors the section breaks in the source doc).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@anishk123 anishk123 force-pushed the fast-llm-hitl-classification branch from 6b27f7f to b159a27 Compare July 11, 2026 19:53
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Development

Successfully merging this pull request may close these issues.

1 participant