Autonomous Agents aka AI Agents are like your own person assistants. They can do anything you program them to do and we mean anything… From responding to emails, to writing code to even running marketing campaigns. Entire companies will be built with agents doing all the work. It remains to be seen how countries will choose to impose taxes on these AI agents.

There are also many nefarious use cases for these agents such as phishing schemes, more sophisticated robocalls, and an army of unlimited hackers.

BabyAGI is a slimmed down version of an agent called Task-driven Autonomous Agent. BabyAGI is a helpful digital assistant that can complete tasks and take actions on the internet. It’s not a really an artificial general intelligence (AGI) as the name suggests. BabyAGI is very simple to use, in fact it’s creator Yohei Nakajima is a hobbyist coder and a full time investor.

BabyAGI helps you link together a series of prompts, also known as prompt chaning without the need for plugins. Think of prompt chaining as takin the output of one request to an AI agent and then using that as the input for the next task. Ex. I can ask GPT to write me a tweet on cats, then take that tweet and ask another AI agent to post it to twitter.

AutoGPT is a competitor to BabyAGI but also the category that BabyAGI falls under. It was created by Toran Bruce Richards but is more complicated to use as it’s borrowing programming patterns from the video game industry.

These tools, such as BabyAGI, AgentGPT, Godmode, Do Anything Machine, Microsoft’s JARVIS, AI Legion, CAMEL, and GPTRPG, are quickly evolving and offer various features, from task automation to role-playing with AI agents. While some are open-source projects, others are web-based or part of ongoing research. These AI tools are changing the way we interact with technology and can help solve tasks more effectively.

If you choose to use it with OpenAI’s models with your agent, keep a tab on your usage as you can easily run up a huge bill.

OpenAI has unveiled GPT-4, the latest breakthrough in its quest to scale up deep learning. The multimodal AI model, capable of image and text-understanding, is being offered through an API to the company’s paying users. Developers can also sign up to the waitlist for access. GPT-4 is available through ChatGPT Plus, with a usage cap. The model performs at human-level on professional and academic benchmarks and is capable of generating text and accepting image and text inputs, a significant improvement on its predecessor GPT-3.5.

Several companies have already started using GPT-4, including Stripe, Duolingo, Morgan Stanley and Khan Academy. Stripe is using GPT-4 to scan business websites and summarise the information to customer support staff. Duolingo has built GPT-4 into its new language-learning subscription tier. Morgan Stanley is creating a GPT-4-powered system to retrieve information from company documents and deliver it to financial analysts. Meanwhile, Khan Academy is leveraging GPT-4 to build an automated tutor.

One of the key features of GPT-4 is its ability to understand images as well as text. OpenAI is testing its image understanding capability with Be My Eyes. Powered by GPT-4, Be My Eyes’ new Virtual Volunteer feature can answer questions about images sent to it. The feature can not only identify what is in an image but can also analyse it to determine what can be prepared with those ingredients.

Steerability tooling is another improvement in GPT-4. OpenAI has introduced a new API capability, “system” messages, that allow developers to prescribe style and task by describing specific directions. These messages set the tone for the AI’s next interactions and establish boundaries. GPT-4 is still far from perfect, and OpenAI admits that it can “hallucinate” facts and make reasoning errors. Nonetheless, it represents a significant milestone in deep learning.

Ethereum has implemented the ERC-4337 standard to change how users interact with wallet services by enabling users to use smart contract wallets with arbitrary verification logic. This would allow users to add more controls or features to their accounts, such as two-factor authentication or recovery options with a friend or lawyer. Unlike externally owned accounts (EOAs), account abstraction enables users to use any cryptographic signature of their choosing and authorizes transactions securely through cell phones.

ERC-4337 is an opt-in standard that will create a standard for account abstraction, enabling developers to build customized Web3 transaction flows and wallets using the latest ERC-4337 smart contract. Existing products such as Gnosis Safe and Argent have already implemented features such as social recovery but would have to connect to a centralized relayer to maintain them. ERC-4337 will introduce a new mempool for user operations, serviced by bundlers on an accounts function level, and one of the first protocols to comply with the standard is Stackup.

The implementation of the ERC-4337 standard has been in the works for over nine years, and it has been difficult to reach a consensus and change an entire protocol to support it. But with the introduction of the standard, users can enjoy a more flexible and secure user experience, and developers can build wallets and transaction flows on any EVM chain using the latest ERC-4337 smart contract.

Stable coins have become increasingly popular in the cryptocurrency world, as they offer a way to hedge against the volatility of cryptocurrencies like Bitcoin and Ethereum. But what if there was a new type of stable coin that was even more stable and secure than traditional stable coins? Enter Flatcoins.

Flatcoins are a new type of stable coin that are designed to maintain a constant value against a basket of currencies, rather than just one currency like the US dollar. This diversification helps to reduce the overall volatility of the coin and makes it a more stable store of value.

One of the key advantages of Flatcoins is their ability to maintain stability even in times of market turmoil. Traditional stable coins are often pegged to a single currency, such as the US dollar, and can become vulnerable to fluctuations in the value of that currency. Flatcoins, on the other hand, maintain their value against a basket of currencies, making them less susceptible to any one currency’s fluctuations.

Another advantage of Flatcoins is their decentralization. Unlike traditional stable coins, which are often backed by a single entity, Flatcoins are backed by a decentralized network of nodes that work together to maintain the stability of the coin. This makes them less susceptible to censorship or control by any single entity, which is an important consideration for many cryptocurrency enthusiasts.

So how exactly do Flatcoins maintain their stability? The answer lies in the way that they are designed to be used. Unlike traditional stable coins, which are intended to be used as a store of value, Flatcoins are designed to be used as a medium of exchange. This means that they are meant to be used in everyday transactions, just like traditional currencies.

When a user wants to buy or sell a Flatcoin, they send a transaction to the network, which is then processed by the nodes. The nodes use algorithms to determine the appropriate price of the coin at any given time, based on the current supply and demand. If the price of the coin begins to fluctuate, the nodes work together to adjust the supply and demand until the coin returns to its target value.

Overall, Flatcoins represent a major leap forward in the world of stable coins. With their diversification and decentralization, they offer a more stable and secure option for those looking to hedge against cryptocurrency volatility. Whether you’re a seasoned crypto trader or just getting started, Flatcoins are definitely worth keeping an eye on.

In this part of our tutorial we will be creating a react NFT Minter App to interact with our smart contract. The full NFT101 Course is available here.

In this tutorial we use OpenZeppelin’s ERC-721 Smart Contract for our NFT Collection. The full NFT101 Course is available here.

In this quick video walk through we show you how to setup a decentralized end point with POKT (Pocket Network) so you can deploy contracts to the Ethereum testnet in this case we’re using Rinkeby.