Imagine if ordinary people could write smart contracts in their native language, it could bring “billions of new blockchain users”.
Emin Gün Sirer, the founder of Ava Labs and creator of the Avalanche blockchain, said, “Smart contract programming is hard. Capturing ‘intent’ is difficult, writing code is tricky, and verification remains a challenge.”
Sirer, speaking at the recent Cornell Blockchain Conference in New York City, stated, “This is the primary problem that inhibits the flourishing of smart contracts.”
But imagine if artificial intelligence (AI) like ChatGPT or Llama could assist in all aspects of smart contract coding. Lawyers might quickly become the primary authors of smart contracts instead of programmers.
Even more interestingly, ordinary people would be able to write smart contracts in their native language in a peer-to-peer manner, making it as simple as writing a bank check.
Sirer further elaborated on this future vision during the Cornell Blockchain Conference on April 26 in New York City, saying, “You’re all familiar with the process of writing a check, right? That’s the most complex financial instrument our banks provide. And yet, our choices are pretty limited. I can hand a check to John that says, ‘I hereby transfer $5,000 to John’ — that’s basically it.”
But what if we could do the same and add additional conditions? Sirer continued with an example, “I hereby offer John $5,000, with the condition that he must raise $5 million by the end of September to shoot a movie. If he can’t do it, I want my money back.’ I can write that explicitly.”
Sirer stated that this envisioned scenario may take another 5 to 10 years to become a reality, but if it does, it would be “transformative.”
“We will be able to onboard billions of new (blockchain) users.”
Currently, most smart contracts are written using the programming language Solidity, which is not widely known even among the programming community.
However, Avalanche is already developing a new virtual machine in the field of AI and blockchain technology integration. Sirer stated that this virtual machine “supports programming in natural language. You can choose to use English, German, French, Tagalog, Chinese, any natural language your mother taught you.”
Issues still remain.
But is this just a fantasy? There are still many issues that need to be resolved before what Sirer calls “coin-operated agents” can be widely adopted.
First and foremost, legal issues need to be addressed. Keywords and terms need to be precisely defined. For example, the word “software” may require a very specific definition before it can be used in smart contracts. This work may take some time.
Additionally, whether AI “agents” are ready to produce legally binding documents is another question. After all, large language models (LLMs) sometimes generate incorrect information, a phenomenon known as “hallucination.”
Sirer pointed out, “We’ve all seen pictures of people with seven fingers [generated by AI].”
However, some of these issues can be addressed with short-term solutions. For example, transactions can be submitted to both ChatGPT 3.5 and Llama, and both agents must agree before the smart contract solution is adopted. “That way, you at least get two trusted executors, and you’re taking the intersection of their actions.”
“Writing smart contracts in plain English”
There are also indications that smart contracts capable of handling “natural” language have already been developed or are within reach.
Sam Friedman, Chief Solutions Architect at Chainlink Labs, stated to Cointelegraph, “The ability for anyone to be their own programmer already exists in the world today.”
Friedman mentioned a project within the Chainlink BUILD program called Council, which is an AI agent framework developed by ChainML. This framework “allows developers to provide simple English instructions and have them immediately turned into executable code. Currently, the code is mainly in Python or SQL, but it would only take one upgrade to enable smart contract functionality.”
He also mentioned the “Ask AI” feature in the Chainlink Developer Center, where users can submit requests in plain English and receive a complete smart contract in return. For example, a user can request, “Please show me an example of a smart contract that allows users to request a random number between 1 and 10 using Chainlink VRF (Verifiable Random Function).”
However, the current products may not fully realize all the functionalities envisioned by Sirer. Friedman stated in the interview with Cointelegraph that there is still a lot of work to be done in the future.
He said, “Although AI agents that write smart contracts have emerged, they are not yet in their final form. They still need further improvement in terms of quality and complexity.” To achieve this, AI models need to be trained with constantly updated content.
Despite this, Friedman can still imagine scenarios where multiple AI “agents” in different roles work together to manage the lifecycle of smart contracts. For example:
– One agent helps define requirements.
– Another agent is responsible for writing smart contracts.
– Another agent conducts quality and security testing.
– Another agent is responsible for deploying contracts.
– The last agent provides continuous maintenance or adjustment of parameters or global variables in the deployed contracts.
During the Cornell Blockchain Conference, Sirer acknowledged that there are still “huge unknowns” and progress requires guidance from various perspectives, involving individuals with “both technical backgrounds and ethical and humanistic backgrounds.”
Is there a place for lawyers too?
During the Q&A session following his speech, someone asked Sirer who would be the ideal programmers if Solidity language was no longer needed and coding could be done in ASCII text.
“So, who would be the ideal programmers? At first glance, software programmers seem to have the advantage. After all, they already know how to use precise languages to define and specify conditions.”
“But the ones who really know how to use specification languages to write contracts are lawyers. So, they will be the leaders in that field […] The people who really thrive in this system are the ones who truly understand how to craft contracts using a specification language.”
As for ordinary users, what about their situation? “I think they are fully capable of defining basic transactions,” Sirer said. In fact, he expects these new functionalities to be built on “democratic, open platforms” that “anyone can use equally.”
Overall, this new approach to smart contracts is very appealing and full of hope. “We cannot just put it aside,” Sirer concluded.
Twitter:
https://twitter.com/BitpushNewsCN
Bitpush Telegram Community:
https://t.me/BitPushCommunity
Bitpush Telegram Subscription:
https://t.me/bitpush
Bitpush Btok Subscription:
https://btok360.com/bitpush
This article is from Bitpush. Reproduction of the article must be indicated.
Original article link: https://www.bitpush.news/articles/6698609
Tags
WEB3
Cryptocurrency
Blockchain
Source link:
https://cointelegraph.com/news/ai-smart-contracts-ava-labs-blockchain
