Wojtekb30's Blog (EN)

ISKRA experiment 02_10_2024-1 - "Defeat the Minecraft Creeper" Hello everyone! In this post, I will describe my recent and first public ISKRA Project experiment. I have conducted some experiments before, but I believe they are not worth publishing. Let's consider this one the first official ISKRA Project experiment. Let's begin with the description of it. I've built an installation in Minecraft Bedrock Edition: This was the starting point and viewport of our AI: The goal of the AI was to defeat the Creeper by using a set of pre-defined control commands: W - move forward 1 block S - move backwards 1 block A - strafe left 1 block D - strafe right 1 block P - place a brown dirt block in front of you R - destroy block in front of you F - punch to attack/fight The commands P and R were never actually implemented since they were unnecessary for this experiment. The Creeper was trapped in a structure to prevent...

Edit 03.11.2024: The blog is again visible in search results. Hello everyone reading this! I noticed that my blog does not appear in search results of any search engine. Suspecting it got shadowbanned because of words used in first ISKRA experiment post, I decided to hide the post about experiment 02_10_2024_1, which was about making AI fight a creeper in Minecraft. Once my blog returns to being visible, I will try to publish it again, rewritten in a way that would not make web browser algorythms see it as controversial and hide existence of this blog.

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...