Source: Cointelegraph

Compiled by: BitpushNews an

Imagine if ordinary people could write smart contracts in their native language, it could bring “billions of new blockchain users.”

“Smart contract programming is hard,” said Emin Gün Sirer, founder of Ava Labs, which built the Avalanche blockchain. “It’s hard to capture the ‘intention,’ it’s tricky to write the code, and verification remains a challenge.”

“This is the main problem that is preventing smart contracts from flourishing,” Sirer said at the recent Cornell Blockchain Conference in New York City.

But imagine if artificial intelligence (AI) like ChatGPT or Llama could do all the smart contract coding for you. Lawyers may soon become the primary writers of smart contracts, rather than programmers.

Even more interesting is that ordinary people will be able to write smart contracts in their native language in a peer-to-peer manner, which will become as easy as writing a bank check.

Sirer further elaborated on this vision for the future during a speech at the Cornell Blockchain Conference in New York City on April 26:

“You’re all familiar with the process of writing a check, right? That’s the most sophisticated financial instrument that our banks offer. Right now, our options are pretty limited. For example, I can write a check to ‘John’ that says, ‘I hereby transfer $5,000 to John’ — and that’s basically it.”

But if we can do the same thing and add additional conditions, Sirer goes on to illustrate:

‘I’m offering John $5,000 if he raises $5,000,000 by the end of September to make a movie. If he doesn’t, I want my money back.’ I can just put it in there.”

Sirer said the scenario he envisions is probably still five to 10 years away, but if it does happen it would be "transformative."

“We’re going to be able to onboard billions of new (blockchain) users.”

Currently, most smart contracts are written in Solidity, a programming language that is not widely known even among programmers.

However, Avalanche has already begun developing a new type of virtual machine in the field of artificial intelligence and blockchain technology. Sirer said that this virtual machine "supports programming in natural language. You can choose to write your program in English, German, French, Tagalog, Chinese, any natural language that your mother taught you in her native language."

the problem still exists

But is this just a pipe dream? There are still many problems that need to be solved before what Sirer calls “coin-operated proxies” can be widely adopted.

First, legal issues must be dealt with. Keywords and terminology need to be precisely defined. For example, a term like "software" may need to be defined very carefully before it can be used in a smart contract. This may take some time to complete.

There is also the question of whether AI “agents” are ready to write legally binding documents. After all, large language models (LLMs) can sometimes produce false information, a phenomenon sometimes referred to as “hallucination.”

“Everyone has seen [AI-generated] images of people with seven fingers,” Sirer noted.

Some of these issues can be solved in the short term, however. For example, transactions could be submitted to ChatGPT 3.5 and Llama simultaneously, requiring both agents to agree before a smart contract solution is adopted. "That way, at least you get two trusted executors, and you're taking the intersection of their actions."

“Instructions for writing smart contracts in plain English”

Others say that smart contracts that can process “natural” language are already here — or are within reach.

“In today’s world, the ability for everyone to be their own programmer already exists,” Sam Friedman, chief solutions architect at Chainlink Labs, told Cointelegraph.

Friedman mentioned one of the projects in Chainlink’s BUILD initiative, Council, an AI agent framework developed by ChainML, which “allows developers to provide plain English instructions and instantly convert them into executable code. Right now, that code is mostly Python or SQL, but to implement smart contract functionality, it would only take a single upgrade.”

He also mentioned the “Ask the AI” feature in the Chainlink Developer Center, which returns a complete smart contract when a user submits a request in plain English. For example, a user can ask: “Please show me an example of a smart contract that allows a user to request a random number between 1 and 10 and that uses Chainlink VRF (Verifiable Random Function).”

However, the current product may not yet fully realize all the functions Sirer envisioned, and Friedman told Cointelegraph that there is still a lot of work to be done.

“Although AI agents that write smart contracts are available, they are not yet in their final form. They still need further improvement in quality and sophistication,” he said. To achieve this, AI models need to be trained with constantly updated content.

Even so, Friedman can still imagine some application scenarios in which multiple AI "agents" with different roles work together to complete the life cycle management of smart contracts. For example:

An agent helps define requirements;

Another agent is responsible for writing smart contracts;

There is also an agent that performs quality and security testing;

Another agent is responsible for deploying the contract;

The last agent continuously maintains or adjusts the parameters or global variables in the contract after the contract is deployed.

At the Cornell Blockchain Conference, Sirer acknowledged that there are still “huge unknowns” and that progress will require guidance from all sides and the involvement of people who “have both technical backgrounds and ethical and humanistic backgrounds.”

Do lawyers have a place?

During the Q&A session after the speech, Sirer was asked who would write smart contracts in the future if Solidity was no longer needed and they could be encoded in ASCII text?

So who would be the ideal programmer? At first glance, software programmers would seem to have the upper hand. After all, they are already skilled at using precise language to define and specify conditions.

“But the people who really understand how to craft contracts using regulatory language are the lawyers. So they’re going to be the leaders in that space […] They’re the ones who are really going to be able to thrive in this system.”

What about regular users? “I think they are fully capable of defining basic transactions,” Sirer said. In fact, he expects these new features to be built on “democratic, open platforms” that “are equally accessible to anyone.”

Overall, this new approach to smart contracts is so intriguing and promising that “we can’t just put it aside,” Sirer concluded.