The co-founder of Ethereum, Vitalik Buterin, expresses his views on how AI (artificial intelligence) could help detect and fix bugs in the Ethereum codebase. In a recent tweet, Ethereum’s creator, Buterin, said that Ethereum’s “biggest technical risk” is the possibility that the Ethereum smart contracts will have errors/bugs.
With the major Dencun upgrades scheduled to launch on March 13th, ensuring the reliability and security of Ethereum’s code is more crucial than ever. Dencun aims to improve Ethereum’s scalability and prepare it for even more complex applications.
Buterin believes AI-assisted formal code verification could significantly improve detection rates for bugs and other issues. He stated that progress on AI auditing solutions “would be amazing.”
This vote of confidence comes shortly after AI code assistant ChatGPT received criticism for often writing vulnerable smart contracts. In July 2023, a series of experiments conducted by OpenZeppelin utilizing OpenAI’s GPT-4 model were able to successfully identify bugs in Ethereum test code in 20 out of 28 cases.
When GPT-4 failed to identify flaws, it could often be prompted to correct its mistakes quickly. However, at other times, OpenZeppelin found that the AI had actually invented a vulnerability that had never existed in the first place.
However, Buterin has warned developers about the risks associated with overreliance on AI, especially for critical on-chain processes. He advises particular care when using AI to power oracles, predict markets, stablecoins, and other applications handling substantial value.
“It is important to be careful: if someone builds, e.g., a prediction market or a stablecoin that uses an AI oracle, and it turns out that the oracle is attackable, that’s a huge amount of money that could disappear in an instant,” Buterin stated.
Also Read: Ethereum’s Dencun Upgrade is Live On Sapolia Testnet
