Spectral Labs, a crypto development company focused on artificial intelligence, wants to make it easier for non-programmers to build on blockchains. On Tuesday, the company is launching Syntax, an AI app that can help anyone – coders and non-coders alike – create a spin-up smart contracts for Ethereum and dozens of other blockchains.
While Syntax represents an impressive technical achievement, Spectral still faces the hurdle of convincing users to trust AI with their precious digital assets.
Those familiar with Chat GPT and similar chatbots will be at home with the Syntax interface, which is powered by a crypto-specific large language model (LLM) and can have SMS-like conversations with users.
In addition to answering blockchain-related questions, such as “what is the circulating supply of ETH,” the web app can turn user prompts into production-ready Solidity code – the programming language used by Ethereum and other blockchains based on the Ethereum Virtual Machine ( EVM) standard.
“Syntax users can compile, debug, and deploy AI-generated solidity code,” Spectral Labs said in a statement, adding that NFTs, arbitrage bots, and rollups are among the technology’s potential use cases.
“Say I want to encrypt an ERC-20 token called ‘ABC’ with a supply of 100 million,” Spectral Labs CEO Sishir Varghese told CoinDesk in an interview. “Syntax would generate all the code for the user. The user would be able to compile, test for vulnerabilities, test for gas efficiency and code optimization, and then deploy the app directly to the chain directly from the interface.”
AI-powered coding assistants are nothing new: engineers have been using ChatGPT to generate code for the past year, and GitHub Copilot, Microsoft’s AI-powered coding expert, has become a mainstay of the modern programming arsenal since its release in 2021.
“I would say there hasn’t really been an LLM aligned with Solidity,” Varghese said.
In addition to being specifically tailored to Solidity’s development, Syntax is new in that it plugs directly into EVM-compatible blockchains, meaning users can press a button to immediately deploy their Syntax-created “agents” to blockchains such as Ethereum, Arbitrum or Coinbase’s Base.
The app can be configured with private keys and other data to give the agents control over real crypto funds, meaning that the agents – depending on what they are programmed for – can be unleashed to buy, sell and trade tokens as if they were real people.
When it comes to using LLMs, there’s always the tricky issue of “hallucinations” – where AI can make things up or, in the case of coding, create correct-looking code that is error-prone or behaves unexpectedly. When the AI-generated code is tasked with handling real money, hallucinations become an obvious problem.
“We have tried to put some safeguards in place around vulnerability detection and code efficiency,” Varghese said. “These are all already more or less built in. In addition, there will be some ready-made agents that will also help detect vulnerabilities.”
Syntax is trained on a specially curated set of audited smart contracts, security reports and developer documents, he added.
“Creating a high-quality data set is quite crucial because that’s what you want the LLM to reproduce in terms of code,” says Varghese. “If you just take everything that has ever existed, you’re not really going to get good results.”
The CEO of Spectral Labs admitted that using an AI tool like Syntax inevitably comes with some risks: “I think experienced developers are still quite apprehensive about all the copilot stuff – except in Web2. For Solidity, this becomes a completely new experience, to be honest.”
Varghese expects that retailers, rather than experienced programmers, will be the main users of Syntax.
“I don’t expect them to jump in and rely on it,” he said in reference to experienced developers. “I think the cooler thing is that a retailer who has never implemented a contract or even generated Solidity code will be able to do this quite seamlessly and easily.”