Claudette: Make Claude Stop Talking Like a BuzzFeed Article
A developer created a tool called 'Claudette' that uses Gemini to rewrite Claude's AI responses to remove 'millennial clickbait' and overly verbose corporate jargon. The article also includes a technical breakdown of specific bugs found in a sync pipeline.
Why it matters
Highlights the growing frustration with AI 'personality' and the practical engineering challenges of integrating multiple LLMs to improve output quality.
Obviously it's common knowledge by now that Anthropic has solely trained claude on old Buzzfeed articles (explaining its love for 90s nostalgia). So Claude and I built a Claude Code skill ( /debuzz ) that takes Claude's last response and runs it through the Gemini CLI to translate it from talking like a millennial clickbait to regular English. We're thinking of calling it "Claudette" but Cat Wu is famously litigious so it's definitely absolutely not called "Claudette".
Claudette is our solution to Claude being a great engineer with one incurable condition: it talks like it's delivering a TED talk about its own pull request. You ask why a test is flaky and you get a "load-bearing assumption," three numbered revelations, and a solemn note that the third one is the most instructive yet . Nothing is ever just a bug. There is always a kicker.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in