The Consensus 建立 AI 寫作特徵檢測器

Sponsor Image 1: ClickHouse ClickHouse Managed Postgres delivers up to 10x faster performance for I/O-heavy workloads on local NVMe, and natively integrates with ClickHouse for real-time analytics.Learn more ↗

Research, data, and tools for experienced programmers.

Join The Consensus Weekly Sign In

Home Exclusive Jobs Funding Feed Code Sponsor

Get new deep dives, plus jobs and funding in software infrastructure, free in your inbox every week.

Join The Consensus Weekly Want a peek? Check out the archives.

Image 3: ClickHouse

But first, a word from our sponsor

ClickHouse Managed Postgres delivers up to 10x faster performance for I/O-heavy workloads on local NVMe, and natively integrates with ClickHouse for real-time analytics.

Learn more ↗

The Consensus Blog

Has AI tells

A little AI tells detector helps us promote good writing.

By Phil Eaton October 14, 2026

You are getting early access to this article as a subscriber. Your support makes articles like this possible. Thank you.

A big goal of The Consensus is to promote good technical writing in software infrastructure. We feature more than just our own writing. We give you an interesting article every day in the at a glance section. We feature many more articles in our free weekly newsletter. And we filter for good technical articles in our free and public third-party feed.

But Cynthia Dunlop's survey on tech reader preferences has shown that people overwhelmingly dislike AI-written articles, preferring even "bad" human writing to "good" AI writing. And occasionally I'd feature something that turned out to read very strongly of AI-generated writing and internet commenters would call me out on it. Sometimes these egregiously AI-written articles were written by companies who spoke very passionately about temperate and responsible use of AI in communication. (That was disappointing).

Honestly, I can't stand reading AI-written prose either. It infuriated me to click on a random cool-sounding article in our feed just for the actual writing to grate. A waste of time.

There are high-quality commercial detectors like Pangram. The Consensus pays for my subscription to it. But running Pangram against every article that enters The Consensus feed is financially impossible. So for the past month I've been working on an AI tells detector that's integrated into the site.

Image 4: ClickHouse

But first, a word from our sponsor

ClickHouse Managed Postgres delivers up to 10x faster performance for I/O-heavy workloads on local NVMe, and natively integrates with ClickHouse for real-time analytics.

Learn more ↗

It is not a machine learning model, just a bunch of static rules built up by comparing many different aspects of pre-2023 writing to post-2023 writing, accounting for how writing has drifted each year since then.

The detector does not say that the article was written by AI. It only exists to say the article might remind you of AI writing. This is important because the AI tells detector is cheap and not always correct. It has occasionally labeled some of my own articles as quite certainly having AI tells.

With the AI tells detector in place, we label every article in the feed in the 99th percentile of having AI tells. Articles labelled like this are not eligible to show up in the daily At a Glance section of the homepage and on our social media. They are not eligible for the sparkle icon on the feed page that indicates it seems like an interesting article. And they are not eligible to be featured in the weekly newsletter.

Can this be gamed? Teaching the AI to write less like stock Claude and stock ChatGPT? Yes, absolutely. And honestly that would be great. Because half of the irritation is that all these AI-written article sound the same! If they're all being written with each individial's, each company's, own rules and preferences and character that'd probably be nice?

It is the prerogative of every company to decide how they communicate in public. Using AI to write doesn't make a person or company bad. And for now, we're not completely filtering out articles that have AI tells (though you can filter them out by clicking on the sparkle filter or setting aitells<90 in the feed search). But at least in terms of what we choose to freely promote, we'd like those articles to be thoughtfully written by a human.

Get new deep dives like this one, plus new jobs and funding news in software infrastructure, free in your inbox every week.

Join The Consensus Weekly Want exclusive articles and to back our work? Become a paid subscriber.

Phil Eaton

Phil is the founder of The Consensus. Before this, he contributed to Postgres products at EnterpriseDB, cofounded and led marketing at TigerBeetle, and was an engineering manager at Oracle. He runs the Software Internals Discord and the Software Internals Email Book Club. @eatonphil

Noticed a mistake? Have a question or comment? Write to the editor.

Comments

Developer Spotlight

Image 5: Deepthi Sigireddi

Deepthi Sigireddi is a developer with over 25 years of experience. She's worked on Vitess and Multigres. And she now serves as Head of Databases at Supabase.

Read the interview