How Pangram Smells AI

A pangram, or holoalphabetic sentence, phrase, or word, uses every letter of a given alphabet at least once.

The Pangram AI detection tool from Pangram Labs on the other hand identifies AI-generated content with high accuracy.

Pangram's detection model takes a comprehensive view of a document and uses a deep-learning based detector that synthesizes millions of signals about a particular text. 

From its extensive research it has identified nine patterns that occur frequently -

  1. Markdown formatting inserted into plain text contexts
  2. AI Phrases like "delve into" that appear far more often in AI-generated text
  3. Overuse of em dashes where human writers typically would not
  4. Bullet lists used to organize information systematically
  5. Triads like "past, present and future", grouping ideas in threes, a common AI rhetorical pattern
  6. "Not just X but Y" type of word choices and constructions common in AI writing - the best-known tic of AI writing called "contrastive phrasing" & "negative parallelism"
  7. Unusual Unicode characters that may indicate humanization attempts
  8. AI-style headers like "Certainly! Here's..." and other overly helpful introductions common in AI output
  9. Emojis inserted where human writers typically would not
The distinctive markers of AI writing keep evolving, and now those familiar AI quirks are showing up more often in spontaneous human conversation.

It's fascinating how AI writing has spawned AI detection tools, sparked forums where users trade tips about AI writing (using words like "Claudeisms" and "deslop") and fueled heated debates over its merits, further polarizing an already intolerant society. 

Comments

Post a Comment

Popular posts from this blog

30+ GitHub Products & Key Ecosystem Features You Should Know in 2026

Image
GitHub has grown far beyond a place to host code — today it's an entire ecosystem covering CI/CD, AI-assisted development, security, package management, and team collaboration. Whether you're new to the platform or just want a single reference point, here's an alphabetical list of GitHub's major products and features, each linked to its official page - GitHub Actions GitHub Advanced Security GitHub Apps GitHub CLI GitHub Code Review GitHub Code Security GitHub Codespaces GitHub Container Registry GitHub Copilot GitHub Copilot Business GitHub Copilot CLI GitHub Copilot Enterprise GitHub Copilot Extensions GitHub Dependabot GitHub Desktop GitHub Discussions GitHub Education GitHub Enterprise Cloud GitHub Enterprise Server GitHub Gist GitHub Importer GitHub Innovation Graph GitHub Issues GitHub Marketplace GitHub Mobile GitHub Models  (retiring July 30, 2026) GitHub Packages GitHub Pages ...
Read more

Uncle Bob vs. Grady Booch: Rethinking Code Reviews in the Age of AI

Image
In response to a question about the feasibility of effective code reviews for large (e.g., 500-line) AI-generated PRs like those from Claude, especially when reviewers lack deep codebase familiarity in new projects or fast-paced environments, Uncle Bob Martin and Grady Booch have contrasting views Uncle Bob Martin advocates metrics-based oversight (test coverage, complexity, dependencies) and higher-level management over line-by-line AI code review, while Grady Booch stresses manual verification for vulnerabilities, dead code, and performance factors. Uncle Bob Martin : " I don’t review code written by agents . I measure things like test coverage, dependency structure, cyclomatic complexity, module sizes, mutation testing, etc.  Much can be inferred about the quality of the code from those metrics. The code itself I leave to the AI.  Humans are slow at code. To get productivity we humans need to disengage from code and manage from a higher level." Grady Booch : "Unlike B...
Read more

HOW TO Download Open Food Facts Data for Any Country Using Google Colab and Push It to GitHub

Image
Open Food Facts has data on 4.6+ million food products worldwide. But if you only need data for one country, downloading the full 7.64 GB file  (size at the time of writing) hosted on Hugging Face is overkill. Hugging Face acts as a CDN for large ML datasets — it not only stores the full Parquet file but also handles versioning, caching, and fast global downloads. This guide co-written with Meta AI shows you how to use Google Colab to filter the dataset for just one country, add direct product links, and save the result to a public GitHub repo. Takes < 30 minutes total based on your familiarity with these tools & file size. No software installs needed. What you’ll end up with: A CSV like india_products_18392.csv with 16 columns, including a URL for each product. The same steps work for France, Canada, USA, UK, or any other country in the database. What You Need Before Starting A Google account to use Colab A GitHub account + an empty public repo where the CSV will live A Gi...
Read more