How Will Generative AI Be Used in the Future? Answer: AutoGen

21

October

2023

No ratings yet.

The generative AI we know of today is ChatGPT, Midjourney, and DALL·E 3 and many more. This generative AI is very good and advanced, but there are some flaws, like not being able to perform long iterations. Now there is something new called AutoGen. AutoGen is an open-source project from Microsoft that was released on September 19, 2023. AutoGen at its core, is a generative AI model that works with agents; those agents work together in loops. Agents are in essence, pre-specified workers that can become anything, so there are agents that can code well and agents that can review the generated code and give feedback. Agents can be made to do anything and become experts in any field, from marketing to healthcare.

An example of what AutoGen can do is the following: if I want to write some code to get the stock price of Tesla, I could use ChatGPT, and it will output some code. Most of the time, the code that is written by chatGPT via the OpenAI website will have some errors. But with AutoGen, there are two or more agents at work: one that will output code and the second one that is able to run the code and tell the first model if something is wrong. This process of generating the code and running the code will go on until the code works and results in the correct output. This way, the user does not have to manually run the code and ask to fix the errors or other problems with AutoGen it is done automatically.

I also tried to create some code with AutoGen. I first installed all the necessary packages and got myself an API key for openAI GPT4. Then I started working on the code and decided to create the game “Snake”. Snake is an old and easy game to create, but it might be a challenge for AutoGen. I started the process of creating the snake game, and it had its first good run. I was able to create the first easy version of the game. I then came up with some iterations to improve the game. The game now also has some obstacles that, if the snake bumps into one, the game will end. This was also made by AutoGen without any problems. After palying around, I was really amazed at how powerful this AutoGen is, and I can only imagine what else can be created with AutoGen.

AutoGen is a very promising development and will be the future of professional code development or atomization tasks. If the large language models (LLMs) get more powerful, this AutoGen will also be more powerful because all the individual agents will be more powerful. It is interesting to follow this development and see if this AutoGen could create games that are not yet existing.

Please rate this

The Silver Bullet That the Software Industry Has Been Waiting For

5

October

2022

5/5 (2)

Hardware is one of the fastest improving sectors in the technology industry. Over time, our computers are decreasing in price while their speed is increasing exponentially. This idea is otherwise referred to as Moore’s law. However, where technological hardware has seen six orders of magnitude price-performance gain in 30 years, software improvements are lacking behind (DBA lecture 1, 2022). It is not that software improvement is slow, but rather that hardware improvements happen relatively very fast. Fred Brooks (1987) emphasises that there is no silver bullet for software development that promises to deliver price-performance gains even slightly comparable to those seen in the hardware industry. Brooks writes that

“there is no single development, in either technology or in management technique, that by itself promises even one order-of-magnitude improvement within a decade in productivity, in reliability, in simplicity.”

However, that silver bullet might have arrived after all with the arrival of a new software development technique. GitHub Copilot is an extension to your coding environment that serves as an AI pair programmer. There are two primary ways in which it supports software developers. Firstly, it makes suggestions on how to finish code whilst it is being written. An example is displayed in image 1. When a software developer starts typing a function to generate random numbers (the line of code marked in colour), Copilot will recognise what the developer is doing and do suggestions on how to finish the code (the line of code marked in light grey).

Image 1

Its second primary function is to generate code based on a request by a software developer. Image 2 shows the request of the developer (the line of code marked in light grey), and the suggestions done by Copilot that have been accepted by the developer (the line of code marked in colour).

Image 2

Copilot’s two primary functions can help to drastically improve the productivity of software development. Processes that require simple and repetitive coding will be done in the blink of an eye as Copilot will be able to do such coding for software developers on request. However, there is more. Whereas the examples that I just discussed are simple, more complex possibilities lie on the horizon. Imagine software developers being able to request entire software projects, and that Copilot offers them the relevant code. As software projects tend to vary it is not likely that Copilot will be able to deliver the exact code that the developers will need. Rather, the code offered by Copilot then functions as the foundations upon which the developers can build their software projects. Having the foundations of a software project quickly upon request can likely prove to be the order of magnitude improvement that the software industry has been waiting for. In that sense, Copilot promises to be software development’s silver bullet!

Please rate this