3 guys hacked OpenAI using a rival Anthropic model. Here's what it shows about frontier labs' vulnerabilities.

Three cybersecurity researchers in India were able to hack OpenAI using a rival AI model from Anthropic, revealing that advanced artificial intelligence can put the companies themselves, and their users, at risk of attack. 

Mohan Pedhapati, one of the three researchers from a company called Hacktron who broke into OpenAI, said that more advanced AI models allow veteran hackers like him to do their work much more easily — and raise the risks of criminals doing the same. He described each new model as "a force multiplier" that empowers hacking. 

"As the models progress, they become very capable in cyber," he said. 

In a report published last week, Hacktron detailed how, in late July, they used Claude models to infiltrate users of OpenAI's community forum. The forum is a space where users of ChatGPT and Codex, OpenAI's coding agent, might go to ask questions about the products. Users can sign in with their OpenAI accounts. 

The Hacktron researchers used Claude Opus 4.8 to find flaws in the code of a third-party service called Discourse, used for the OpenAI community forum. They tried to use Opus 4.8 to exploit the flaw, but were unsuccessful. However, that very same night, a more advanced model, Claude Opus 5, was released.