Showing 1–15 of 128 articles

Journalists hate AI-generated PR just like the rest of us
Case Studies
Journalists hate AI-generated PR just like the rest of us
Annamieka AertsMax Spero
Annamieka Aerts and Max Spero
Sep 23, 2026
Can Pangram detect Claude Opus 5.5?
Case Studies
Can Pangram detect Claude Opus 5.5?
Yes. Pangram detects Claude Opus 5. 5 in 997/1,000 (99. 70%) of our tested examples.
Annamieka Aerts
Annamieka Aerts
Sep 23, 2026
All About False Positives in AI Detectors
AI Education
All About False Positives in AI Detectors
A deep dive into how Pangram achieves industry-leading false positive rates in AI detection, with a false positive rate of 1 in 10,000.
Bradley Emi
Bradley Emi
Sep 15, 2026
What is AI watermarking?
AI Education
What is AI watermarking?
How AI text watermarks like SynthID and Claude’s work, which providers use them, how they can be beaten, and what they mean for AI detection.
Annamieka Aerts
Annamieka Aerts
Sep 14, 2026
Pangram's Performance on a Colluding Agent Swarm
Case Studies
Pangram's Performance on a Colluding Agent Swarm
A brief report on how Pangram 4 performs when given a collection of items written by AI agents using an obscure web forum to help each other cheat on their assigned task.
Annamieka Aerts
Annamieka Aerts
Sep 10, 2026
Does Pangram Detect Fable 5.1?
News
Does Pangram Detect Fable 5.1?
Can Pangram 4 detect Anthropic's newest model, Fable 5. 1?
Annamieka AertsKatherine Thai
Annamieka Aerts and Katherine Thai
Sep 3, 2026
AI Helps Write Nearly 50% of Press Releases
Case Studies
AI Helps Write Nearly 50% of Press Releases
Pangram scanned 178,672 PR Newswire press releases and found AI-generated text in 34% of them over the past year, climbing to 48% by June 2026.
Annamieka Aerts
Annamieka Aerts
Sep 1, 2026
No, LLMs don’t just mimic human text
AI Education
No, LLMs don’t just mimic human text
LLMs are trained on human text, so why can AI detectors still tell the difference?
Bradley Emi
Bradley Emi
Aug 20, 2026
Pangram shows 0 false positives on diverse student essays
Case Studies
Pangram shows 0 false positives on diverse student essays
We evaluated Pangram 4 on 25,996 human-written student essays from the PERSUADE 2.
Katherine ThaiAnnamieka Aerts
Katherine Thai and Annamieka Aerts
Aug 19, 2026
Pangram's Model Market Share
Pangram's Model Market Share
How Pangram's models can show trends in AI provider market share.
Elyas Masrour
Elyas Masrour
Aug 11, 2026
Pangram 4 Migration Guide
Product Updates
Pangram 4 Migration Guide
All you need to know to migrate to Pangram's latest flagship model!
Elyas Masrour
Elyas Masrour
Aug 6, 2026
Third-Party Pangram Evaluations
Case Studies
Third-Party Pangram Evaluations
Pangram’s internal testing holds up to scrutiny from third-parties.
Destiny Akinode
Destiny Akinode
Aug 2, 2026
Introducing Pangram 4
Product Updates
Introducing Pangram 4
Introducing Pangram 4, the latest generation of our AI text detection model.
Max Spero
Max Spero
Jul 29, 2026
Pangram 4 Technical Overview
Product Updates
Pangram 4 Technical Overview
A technical overview of Pangram 4, our latest AI text detection model: how it was built, how it was evaluated, and how it compares to Pangram 3.
Annamieka Aerts
Annamieka Aerts
Jul 29, 2026
Introducing Pangram Image Detection (Research Preview)
Product Updates
Introducing Pangram Image Detection (Research Preview)
Introducing a research preview of Pangram's AI image detection model.
Rachel StajduharBradley Emi
Rachel Stajduhar and Bradley Emi
Jul 29, 2026