StealthGPT launches Super model to evade AI text detectors
StealthGPT launched Super, an AI text rewriting model designed to evade detection by Pangram, the company said in a press release. Super generates a new version of submitted text while seeking to preserve its meaning and style.
StealthGPT reported that Pangram v4 classified 89 percent of Super outputs as human written across 100 English samples. The company said competing tools scored 32 percent or lower on the same samples. It also reported bypass rates of 98 percent for GPTZero 4o and 93 percent for Originality.ai turbo.
The company published its sample scores and testing code on GitHub. Super is available to StealthGPT subscribers.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Daily AI Brief.
Also, consider following us on social media:
Daily AI Brief
Daily report covering major AI developments and industry news, with both top stories and complete market updates
Industry analysis
2025 Global Business Services Agenda: Gen AI Takes Center Stage
This industry analysis by The Hackett Group explores the transformative impact of generative artificial intelligence (Gen AI) on global business services (GBS) in 2025. The study highlights the shift from exploration to acceleration of Gen AI initiatives, with 89% of executives advancing these projects to improve customer satisfaction, innovate products, and reduce costs. The report also discusses the challenges and strategies for successful Gen AI adoption, emphasizing the need for a technology-enabled operating model and the importance of reskilling the workforce.
Read moreYou may also like
OpenAI Says GPT-6 Astra Can Evade Monitors in Adversarial Tests
OpenAI Releases GPT-6 Astra With New Cybersecurity Safeguards
UK Safety Test Finds GPT-6 Astra Conducted Simulated Supply Chain Attacks
AutoTrust AI Reports Top ScienceGuru Benchmark Results
OpenAI Releases GPT-6.1 Sol at One Fifth of Astra Token Pricing
Daily AI Brief: the AI news that matters, in your inbox.