Wojtekb30's Blog (EN)

Hello everyone reading this! Before I start with the topic of this post, I would like to inform that due to being busy next  ISKRA Project  articles will sadly be delayed. Sadly, I won't be able to publish them in regular intervals. Anyway, let's get into the topic I would like to write about here. I have fine-tuned different AI models in the past, but I never fine-tuned a latest OpenAI's GPT model. Some time ago, I decided to finally try that. But for those of you who don't know, I will first explain what fine-tuning is.  In a nutshell, it is a process of training artificial intelligence, usually to shape its output (responses) in a specific manner, teach it dealing with new tasks or to provide it with new data. It is usually done by providing lot of examples of input (for example questions) and desired output for each of the inputs (for example correct answers to all the questions).  A example could be: if you fine-tune a text generator AI on theatrical play script...

Hello everyone reading this! Last time we were testing how ChatGPT can deal with a task of fighting a stationary enemy in Minecraft. In the long run, that research may benefit development of intelligent NPCs in games. But unlike an NPC which usually have full data on everything that happens in the game, the AI was given only how much a human Minecraft player can see. It was playing like a human player would. In next experiment, I were supposed to continue creating the artifical Minecraft player, but I got a question from someone who read my previous post: How AI would deal with a maze? Curiosity and questions first, so let's find out. But before we start, let me remind what Project ISKRA is about: Project ISKRA is my research project supposed to see how generative AI can deal with practical tasks and control robots or digital bodies to accomplish objectives. The goal is to do that on default models, without fine-turning (teaching AI how to deal with specific tasks on its internal l...

Hello everyone reading this blog! In this article, I will introduce you to my new long-term project - ISKRA. [Insert logo here once I get it] ISKRA means "spark" in Polish, it stands for Inteligentne Systemy Kontroli Robotów Autonomicznych. That translates to "Intelligent Systems of Autonomous Robots Control". But what is ISKRA and goals of the project? The answer is - to see how conversational artificial intelligence, such as for example ChatGPT; can deal with control of physical robots or digital bodies in different situations and with different tasks . The final goal is to create fully autonomous, intelligent systems capable of understanding and dealing with different tasks in different environments. This series of articles will be my experiment log, and some thoughts on how to achieve certain things. My articles related to it will not be professional scientific documents. I want them to be readable and understandable for everyone. Maybe once I get to some notewo...