OpenAI's ChatGPT-4 Struggles to Audit Smart Contracts, According to Testing
06/01 14:25
OpenAI's ChatGPT-4 was tested by blockchain security firm OpenZeppelin's Mariko Wakabayashi and Felix Wegener to determine whether AI tools could replace human auditors. The AI model passed a majority of the levels in the Ethernaut security challenge, but struggled with newer ones introduced after its September 2021 training data cutoff date. ChatGPT-4 was able to find the exploit and pass 20 of the 28 levels, but needed some additional prompting to help it solve some levels after the initial prompt. While ChatGPT-4 is currently unable to replace human auditors, it can still be used as a tool to boost the efficiency of smart contract auditors and detect security vulnerabilities.
全部评论0最新最热