API

GPT-4 apps BabyAGI and AutoGPT could have disruptive implications for crypto

Crypto users are getting excited over the prospect of automating their trades with future-facing technologies built with the GPT-4 API.

A recent spate of applications built on OpenAI’s GPT-4 API has the crypto community buzzing with designs toward the development of a fully-autonomous, self-correcting cryptocurrency trading bot.

Two such apps, dubbed “BabyAGI” and “AutoGPT,” have received particular notice, with many users attempting to build crypto trading applications on top of them.

The big idea behind both apps involves task management for GPT-4. Currently, GPT-4 excels at natural language processing, as is evidenced by the demonstrable usefulness of the ChatGPT interface, but it has no capacity for memorization.

Applications built on the GPT API are basically limited to single-session use, meaning the model can’t recall information from previous interactions. This has to do with the amount of data (referred to as the number of “tokens”) that individual queries require, as well as GPT’s tendency to hallucinate — a problem that becomes increasingly noticeable as token counts rise.

Users are, essentially, starting with a clean slate whenever they query the machine. In terms of building a crypto trading application capable of self-correction and historiographic analysis — adjusting to real-time market conditions while simultaneously keeping short and long-term trends in focus — this means even the most robust bot built on the GPT API would typically require heavy human supervision.

Related: Tech giant Alibaba to roll out ChatGPT competitor AI

Some clever developers may have discerned a potential method for circumventing these limitations by building applications that take advantage of GPT’s ability to generate code and connect to external sources.

We’ve seen our fair share of trading bots, but the goal of these particular apps goes beyond simply automating crypto news aggregation or teaching a machine learning agent how to recognize the dip.

AutoGPT, for example, uses GPT-4 to generate code and then exploits GPT-3.5 to create what appears to be a virtual artificial memory space wherein information is combined and shuttled between the two.

Another effort, BabyAGI, combines GPT-4 with LangChain, a coding framework, and Pinecone, a vector database, to spawn new agents in order to complete complex tasks without losing focus on the original objective. 

Both apps could have the potential to serve as the backbone for a multi-agent, fire-and-forget AI application capable of managing a crypto portfolio from top to bottom based on little more than plain language prompting.

While it appears neither app was specifically designed with the cryptocurrency market in mind, we’ve spotted several efforts across social media and on GitHub to adapt one or both for autonomous trading.


ConsenSys eyes Web3 notification service refinement with Hal acquisition

The acquisition will allow ConsenSys’ Web3 API provider Infura to integrate Hal’s configurable webhooks or notification service in its developer stack.

Blockchain technology services provider ConsenSys acquired Hal, a no-code blockchain development tooling platform, to disrupt alerts and notifications at the protocol level in Web3.

The acquisition will allow ConsenSys’ Web3 API provider Infura to integrate Hal’s configurable webhooks or notification service in its developer stack. As a result, the move will help developers create alerts and notifications at the protocol level for various signals.

According to ConsenSys, Infura offers a suite of tools to connect apps, which the developer community can use to connect apps to the Ethereum network and other decentralized platforms.

A workflow showing how Infura facilitates access to Web3. Source: ConsenSys

Infura co-founder Eleazar Galano revealed the company intends to fill the gaps in the building process of apps for the crypto ecosystem. Speaking about ConsenSys’ acquisition of Hal, Galano stated: 

“Enabling developers a seamless end-to-end experience is a key goal and one of the most important trends is low code / no code solutions.”

In February 2022, ConsenSys acquired Ethereum wallet interface provider MyCrypto to improve the security of MetaMask and its user experience. 

ConsenSys acquired Hal to build upon this year-old initiative and enable MetaMask to offer a dynamic, personalized notification system.

Related: ConsenSys founder ‘bullish’ on Ethereum following crypto winter performance

ConsenSys CEO Joe Lubin recently told Cointelegraph that “we’ve retained virtually all of our capabilities” despite having to lay off 11% of its workforce.

Lubin highlighted concerns around raising cash in the crypto ecosystem at the Web3 builder-focused event, Building Blocks 23, in Tel Aviv, Israel. He added:

“And VCs are not kind and generous. They’re going to withhold until some sort of shakeout happens in the tech space, I believe.”

Regarding the job cuts, Lubin believes ConsenSys is now in a stronger position to withstand unforeseen global economic troubles.

Digital pound could co-exist with private stablecoins — UK central bank

The central bank wants an e-GBP to be retail-focused and could form part of a “mixed payments economy” alongside cryptocurrency stablecoins.

The United Kingdom is a step closer to launching a central bank digital currency (CBDC) after releasing a consultation paper explaining the proposed digital pound, which the public has nicknamed “Britcoin.”

The 116-page consultation paper was jointly released on Feb. 7 by the Bank of England (BoE) and the U.K. Treasury. A technology working paper was also released delving into the technical and economic design considerations.

Despite the rise of privately-issued stablecoins in recent years, the paper said that CBDCs such as the digital pound can co-exist in what they expect to be a “mixed payments economy.”

“In much the same way that cash exists alongside private money, the digital pound does not need to be a dominant form of money in order to meet its public policy objectives. The digital pound could exist alongside other forms of money, including stablecoins.”

While the BoE and the Treasury hope to have a digital pound launched by 2025 “at the earliest,” at this stage, they’re still not 100% certain that it will be launched at all.

“The Bank and HM Treasury consider a digital pound is likely to be needed in the UK though no decision to introduce one can be taken at this stage,” the paper stated.

The paper explained the primary motivator behind launching the digital pound is to ensure U.K. central bank money remains “an anchor for confidence and safety” in the country’s monetary system and to “promote innovation, choice, and efficiency in domestic payments.”

The model for the digital pound as outlined in the consultation paper. Source: Bank of England.

To achieve this feat, the e-GBP would need to be largely adopted in the retail ecosystem through a series of “public-private partnerships.”

“For the digital pound to play the role that cash plays in anchoring the monetary system, it needs to be usable and sufficiently adopted by households and businesses.”

Users will be able to access e-GBP by connecting to private sector-run API that in turn connects to the core ledger.

The platform model of the digital pound. Source: The Bank of England.

Other programmability features including smart contracts and atomic swaps — which enables assets to move across networks — will be enabled.

While the paper states the private sector would help build such infrastructure, it also considers imposing individual limits between 10,000 to 20,000 British pounds ($12,000 to $24,000) to essentially prevent its use as a savings account:

“A limit on individual holdings would be intended to manage those risks by constraining the degree to which deposits could flow out of the banking system. That is important during the introductory period as we learn about the impact of the digital pound on the economy.”

Privacy concerns that many in the crypto community have voiced were also acknowledged. Without going into detail, the paper stated an e-GBP would be subject to “rigorous standards” of privacy and data protection.

It further explained that users will “have at least some level of privacy” because transactions will be recorded anonymously on the core ledger.

The paper said a “digital pound will not be anonymous” as user verification is needed “to prevent financial crime” but added neither the government nor the BoE would have access to personal data. Source: The Bank of England

Related: Bank of England governor questions need for digital pound

The paper outlined, however, that an e-GBP may impact the business models of commercialized banks through what is known as “bank disintermediation” — where fewer deposits are made into commercial banks.

“The digital pound would not fundamentally alter the traditional channels of money creation, but it might affect monetary stability. […] Bank disintermediation might affect the transmission of monetary policy to the real economy,” the consultation paper stated.

The central bank also believes the digital pound could bring about more financial inclusivity among the U.K. population.

Bank of England thinks digital pound can co-exist with private stablecoins

The central bank wants an e-GBP to be retail-focused and could form part of a “mixed payments economy” alongside cryptocurrency stablecoins.

The United Kingdom is a step closer to launching a Central Bank Digital Currency (CBDC) after releasing a consultation paper explaining the proposed digital pound, which the public has nicknamed “Britcoin.”

The 116-page consultation paper was jointly released on Feb. 7 by the Bank of England (BoE) and His Majesty’s Treasury. A technology working paper was also released delving into the technical and economic design considerations.

Despite the rise of privately-issued stablecoins in recent years, the paper said CBDCs such as the digital pound can co-exist in what they expect to be a “mixed payments economy.”

“In much the same way that cash exists alongside private money, the digital pound does not need to be a dominant form of money in order to meet its public policy objectives. The digital pound could exist alongside other forms of money, including stablecoins.”

While the BoE and the Treasury hope to have a digital pound launched by 2025 “at the earliest,” at this stage, they’re still not 100% certain that it will be launched at all.

“The Bank and HM Treasury consider a digital pound is likely to be needed in the UK though no decision to introduce one can be taken at this stage,” the paper stated.

The paper explained the primary motivator behind launching the digital pound is to ensure U.K. central bank money remains “an anchor for confidence and safety” in the country’s monetary system and to “promote innovation, choice, and efficiency in domestic payments.”

The model for the digital pound as outlined in the consultation paper. Source: Bank of England.

To achieve this feat, the e-GBP would need to be largely adopted in the retail ecosystem through a series of “public-private partnerships.”

“For the digital pound to play the role that cash plays in anchoring the monetary system, it needs to be usable and sufficiently adopted by households and businesses.”

Users will be able to access e-GBP by connecting to private sector-run API which in turn connects to the core ledger.

The platform model of the digital pound. Source: Bank of England.

Other programmability features including smart contracts and atomic swaps — which enables assets to move across networks — will be enabled.

While the paper states the private sector would help build such infrastructure, it also considers imposing individual limits between $12,000 (£10,000) and $24,000 (£20,000) to essentially prevent its use as a savings account:

“A limit on individual holdings would be intended to manage those risks by constraining the degree to which deposits could flow out of the banking system. That is important during the introductory period as we learn about the impact of the digital pound on the economy.”

Privacy concerns that many in the crypto community have voiced were also acknowledged. Without going into detail, the paper stated an e-GBP would be subject to “rigorous standards” of privacy and data protection.

It further explained that users will “have at least some level of privacy” because transactions will be recorded anonymously on the core ledger.

The paper said a “digital pound will not be anonymous” as user verification is needed “to prevent financial crime” but added neither the government nor the BoE would have access to personal data. Source: Bank of England

Related: Bank of England governor questions need for digital pound

The paper outlined, however, that an e-GBP may impact the business models of commercialized banks through what is known as “bank disintermediation” — where fewer deposits are made into commercial banks.

“The digital pound would not fundamentally alter the traditional channels of money creation, but it might affect monetary stability. […] Bank disintermediation might affect the transmission of monetary policy to the real economy,” the consultation paper stated.

The central bank also believes the digital pound could bring about more financial inclusivity amongst the U.K. population.

‘Decentralized Infura’ may help prevent Ethereum app crashes: Interview

The initial Decentralized Infura marketplace, which is currently in development, is expected to include up to 10 Web3 data providers.

Infura is developing a decentralized marketplace of data providers that will help to prevent Web3 app crashes in the future, according to a Feb. 6 Cointelegraph interview with Infura researcher Patrick McCorry.

McCorry stated that the new “decentralized Infura” will help to ensure that blockchains remain decentralized by distributing data provider services among multiple providers in a marketplace. It will have “up to 10 providers initially” that will “work together to bootstrap the network and then […] Gradually iterate and get more players.” Some potential partners will meet at ETH Denver in late February or early March to discuss the project’s next steps.

The new project will not be a new blockchain. Instead, it will be a marketplace that matches consumers of blockchain data with data providers. The current centralized Infura will simply be one of the providers on the network, as McCorry explained:

“There’ll be a marketplace where basically the new providers will sign up […] They can place the resources that they have available, so they can say, ‘I can satisfy these requests at this price.’ Users could come along and then buy those resources and then it’s like a matchmaking service of users.”

McCorry believes this will make the Web3 ecosystem more resilient by allowing users to rapidly switch to a new provider if the one they are currently using experiences an outage. He also stated that the new decentralized Infura might be more censorship-resistant than the current service because providers will be spread out over many different geographical areas and operating under different jurisdictions.

“I think what’s important to highlight here is that the goal of decentralized Infura is not to fight against censorship, or to even enable that. The whole point of decentralized Infura is a reliability project, to guarantee that if we were to go offline another node will come along and pick up the traffic,” he said. However he added that the network would have providers in countries that are in different jurisdictions and subject to different rules.

“The way you get censorship resistance is geographical location. Now, if you’re in a country where you don’t have to abide by certain sanctions, you can facilitate the request. “

“It’s not the goal of decentralized infura to facilitate sanctioned transactions, but there will be nodes there who will be from different geographical location so they could potentially serve the request. Infura themselves as of course, an entity on that network will of course adhere to any sanctions or any requests in that regard.”

Related: Are we still mad at Metamask and Consensus for snooping on us?

Infura is a suite of APIs and developer tools that is used by Web3 app developers to pull data from blockchains. It is used by many different Web3 apps, including MetaMask, Gnosis, Aragon and others. It is also used by many centralized exchanges to track deposit and withdrawal transactions.

Although blockchain networks charge transaction fees to prevent too many transactions from overloading servers, these fees are only charged to users writing data to the blockchain. Infura has emerged as one way to charge developers or users for reading data, which does not usually incur a transaction fee on-chain.

As Infura has become increasingly used by developers, it has come under fire for allegedly being too centralized. In November 2020, the MetaMask wallet app stopped working for most users when Infura servers went down, and some centralized exchanges were prevented from getting accurate transaction data from it anymore. This led some critics to question whether Ethereum can be genuinely decentralized as long as developers depend on Infura to provide data for their users.

Parts of this article were based on an interview with Patrick McCorry conducted by Cointelegraph’s Andrew Fenton at Starkware Sessions 2023 in Tel Aviv.