Anthropic · OpenAI · Claude · ChatGPT · Wall Street · Dario Amodei · CBS News Technology
AI security experts say they tapped Claude to hack ChatGPT
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
◎ Multiple-sources
Software security researchers used Anthropic's Claude AI platform to hack OpenAI's ChatGPT tool, adding to mounting concerns about the vulnerability of leading large language models to cyberattacks.
Key facts
- The Hacktron AI team reported the intrusion to OpenAI, which responded promptly and paid researchers a $6,500 bounty, Hacktron AI said in its blog post
- In a recent interview with CBS News, Anthropic CEO Dario Amodei said he sees "real dangers" around AI, citing the Hugging Face hack as a warning sign
- The entire timeline from initial discovery to access to OpenAI repo access took place in less than 72 hours," Hacktron AI said in the post
- Researchers from Hacktron AI, an independent AI security platform that tests software code, disclosed the breach
Summary
Researchers from Hacktron AI, an independent AI security platform that tests software code, disclosed the breach . "The entire timeline from initial discovery to access to OpenAI repo access took place in less than 72 hours," Hacktron AI said in the post. The Hacktron AI team reported the intrusion to OpenAI, which responded promptly and paid researchers a $6,500 bounty, Hacktron AI said in its blog post. "The team immediately reported the initial vulnerability to OpenAI and Discourse and worked with them to coordinate the patch.