Tag Archives: The Existential Risk

Final Delivery

Posted on by

The Final Solution: KoopaKonstruct Manager

The BPMN diagram below is a simple representation of our KoopaKonstruct Manager.

In summary we are using Hololenses to inspect a chosen area where we want to e.g. hang up a coat rack, build a table, and similar. In order to make the Hololenses smart, we have integrated OpenAI. We are using Function calling to provide instructions about the requested project, information about necessary materials and quantity.This is where we are making our KoopaKonstruct really smart.

As real #Crawlers we use OpenAI’s Function calling to dynamically create the search criterias based on natural language. Google Speach to text is used to capture the natural language query. We are really integrating into everything that flips bits #Embedding numbnuts! With help of the search criterias, we are able to provide critical information further into the supply chain, meaning all the way down to the FinOps where we are improving critical business processes (this will be explained later in this blog post).

Below is a picture from the Hololenses where we use a button to speak with AI:

GPTVision helps us interpret work drawings and breaks it down into the steps needed, so that we can get a clear instruction of what materials we need, how many and how to build the desired object. Using Power Automate, we are able to share and send the item details and necessary quantity into FinOps.

As an addition to the OpenAI magic, we have also created a canvas app that is integrated in the Hololense #PlugN’Play. From this app you can perform business processes, such as triggering sales orders, check inventory status, and 4 different Power BI reports to monitor sales orders and follow up late deliveries #Dash it out.

And here is where we really improve business processes; when the information is sent to FinOps we use X++ code to check inventory status. If materials are in stock, a sales order is created and sales order confirmation is sent. If there are no (or not enough) materials in stock, we also create a purchase order in addition to the sales order. A link between the purchase order and sales order is created, enabling the ability to understand where the demand is coming from. Additionally, to make the KoopaKonstruct Manager adaptable to e.g. construction companies, we have created the possibility to link the purchase and sales orders with projects. This provides a lot of possibilities for detailed project management for the finance geeks.

Below is our argumentation to why we believe we should score high on all 4 categories!

Most Extreme Business Value

Our team embarked on a quest to redefine the meaning of business value, and we present to you KoopaKonstruct Manager – a solution that not only orders products through Hololenses but catapults business efficiency into a realm beyond imagination.

Automating the Complete Supply Chain with Hololenses

We harnessed the power of Hololenses to revolutionize the way products are ordered. One user, equipped with the mighty Hololens, registers the necessary quantity with a mere wave of the hand, triggering a Power Automate flow like a seasoned Mario collecting power-ups.

The adventure doesn’t stop there! Our Power Automate flow seamlessly transmits the order information to FinOps using the Execute action. The magic unfolds as FinOps automatically generates a sales order and a purchase order based on inventory stock. But here’s where the plot thickens – these orders are not solitary entities; they are linked together, creating a dynamic duo that unravels the mystery behind each purchase. There is no need to spend as much as a second wondering how or why the orders were created; the link indicate that there is a demand behind each purchase order.

See yourself sitting in an ordering office at a company where the customers are able to generate sales orders by only entering a demand. And, in addition to the automatic creation of sales order, imagine that you did not have to study the master plan to generate the purchase order as it is automatically created! And as a side salsa, you did not even have to trigger the sales order confirmation as it is sent automatically. So, while you are sitting there wondering about what to do with your life (and how long it takes before the CEO finds out that you are useless as the power of Power Automate and X++ took your job), you can relax and focus on other more important things in life, such as playing a Super Mario game.

Power Stars: Automated Project Linkage

But wait, there’s more! We also increased the business value for construction and engineering enterprises. With the ability to automatically link both the purchase and sales orders to projects, we’ve bestowed upon industries that thrive on projects a golden opportunity to enhance their efficiency and project management. It’s not just about ordering; it’s about constructing a bridge to a new era of project-linked prosperity.

The Warp Whistle to Most Extreme Business Value

We make a bold claim for the “Most Extreme Business Value” category in this year’s ACDC Hackathon. Here’s why our adventure deserves the highest score:

  1. Efficiency: Our solution isn’t just about ordering; it’s about efficiency power-ups that automate the entire supply chain process, from order initiation to linkage in FinOps.
  2. Dynamic and Time-saving: The automatic creation of linked sales and purchase orders provides unparalleled visibility into demand and supply, laying the foundation for strategic business decisions.
  3. Project Linkage: For construction and engineering businesses, our automated project linkage is a treasure trove of golden coins, offering enhanced project management capabilities and business value beyond the ordinary.
  4. Adaptable: Our solution is not only limited to the B2B-market, but can also be used for the B2C-market. Making the app available to customers, they can create orders automatically and receive high quality service as the complete supply chain has become even more efficient.

Excellent User Experience

We have created a Super Mario inspired canvas app that is adapted into the Hololenses. In other words, our app transforms ordinary into extraordinary!

Features:

Killer AI

Whether you’re a seasoned AI veteran or just dipping your toes into the mushroom-filled waters of innovation, our solution is a testament to the power that AI holds in shaping the future.

KoopaKonstruct Manager is not just a game-changer; it’s a game-transformer. Through the mastery of machine learning, we’ve empowered our solution to evolve, adapt, and learn from the challenges it encounters. From predicting order quantities to optimizing supply chain processes in the real world (and in FinOps), our AI-driven approach is a power-up for efficiency and foresight.

In the quest for the Killer AI “crown”, KoopaKonstruct offers more than just automated processes. It also includes magic in form of predictive insights, providing a glimpse into the future of demand, supply, and project landscapes. Strategic decision-making becomes second nature as our AI-driven system transforms data into actionable intelligence.

A mind of its own

In the pursuit of the existential risk badge, our AI solution goes beyond mere execution—it thinks, learns, and adapts with a mind of its own. Through autonomous decision-making capabilities, it navigates the complexities of supply chain processes and provides responses not even a 20 year old is able to find without searching the web.

KoopaKonstruct isn’t just smarter than a 5th grader; it engages in intelligent conversations that transcend the limitations of a classroom. It doesn’t just provide answers; it grapples with FinOps and supply chain complexities, understands nuances, and offers insights that reflect a level of intelligence resembling a dynamic dialogue.

Why KoopaKonstruct Manager deserves the Killer AI “crown”

  1. Innovation Beyond the Blocks: KoopaKonstruct isn’t confined to the traditional boundaries. It breaks through the blocks of conventional solutions, paving the way for a new era of AI-driven innovation.
  2. Adaptability in Every Pixel: Our solution dynamically adapts to the ever-changing business environment, ensuring resilience and adaptability in every pixel of our solution.
  3. Mind Mastery: Our AI isn’t just a tool; it’s a mastery that elevates KoopaKonstruct into a symphony of efficiency, intelligence, and strategic foresight.

Pandoras Box

Equipping a Hololens with AI that can answer questions, order materials, and assist in selecting the right materials and tools for any project based on online instructions transforms DIY into an accessible experience for the less handy. This technology takes the guesswork out of building, offering tailored advice on what to build, the best materials and tools for the job, and even suggesting projects that match your interests and available space. It’s like having a personal tutor and assistant rolled into one, guiding you through the entire process from conception to completion. This seamless integration of technology with hands-on work not only makes crafting projects more approachable for beginners but also enriches the experience with educational value, ensuring that anyone can undertake and succeed in their DIY endeavors with confidence.

The Existential Risk

Posted on by

We are really deep diving into AI being at the heart of our solution. The questions for compliance training are AI generated based on topic, and the answers are matched up against the original question by AI to see if the answer provided is sufficient enough to prove that you understand the scenario.

First question is random question generated by AI:

The user enters the answer

Being open to changes, and not judging people by their background. The more people with different backgrounds the organization has, the better viewpoints it is able to get

AI will then define if this answer proves that you understand what you have been reading.

In this case IA deemed the answer correct.

With AI working in clever ways we are eliminating the need for a USER to evaluate the question that is free text, and making the Q&A more advanced than the multiple choice.

Relying on AI can be a risk and it can be a problem for people creating the training. In theory this could create the whole game from scratch eliminating the need for employees to control the flow of knowledge.

Using AI to create a game

Posted on by

AI has been core to the development of our game in several ways. Almost all graphics has been generated by an AI, the story has largely been influenced by an AI and, an AI is a key component that you can talk to within the game itself!

Story and media

Both the story and media assets within the game has been created using custom GPTs from OpenAI. https://chat.openai.com/g/g-rjjz1GE5I-pixel-art has proven itself to be able to create imagery with a remarkable consistent look and feel based on our prompts, and https://chat.openai.com/g/g-dmgFloZ5w-storyteller has been a great sparring partner in the development of the story

The village butler

Meet the village butler, a core character in our game. He is omnipresent on your adventure and is always ready to answer any questions our adventurers may have.

The butler lives as a custom prompt in Copilot studio, and gets his personality there. In addition we feed him with context aware information based on where the adventurer is in the game together with every prompt he is sent, in this way adventurers can probe him for possible game clues or sometimes straight up answers to the clues.

Also, our guy knows who Botten Anna is, if that isn’t existential risk, we don’t know what is!

Integrating OpenAI GPT4 in Canvas App (The Existential Risk)

Posted on by

In this project, we demonstrate and integrate an AI system that can perform a simple task: identifying good or bad characters in Mario World for Princess Peach. However, we also explore the ethical and moral implications of this system, and whether it has a conscience or not by customizing the prompt and the AI behavior for custom output to the user and narrowing its conciousness as well.

The system consists of three components: a Power Automate flow that connects to the OpenAI Web API Service, a customized prompt that instructs the AI to analyze images of Mario World characters and swipe them left or right depending on their alignment, and a feedback from OpenAI based on our choices and a summary of the character relationship between the user and the character subject.

In this example we can somewhat restrict the behaviour and the information flow it spits out in the context of ethical response in relation to GDPR rules.

Putting Security-central Koopas out of Work: Automatically detecting miscreants for “apprehension”

Posted on by

One of our team members, Odin, has had the unfortunate experience of working in the security industry for 11 years. And he does not want anyone else to suffer the same fate.


That’s part of the reason why we created the Mario Detection System!

By creating a system for automatically detecting unwanted person (GDPR be damned), many security centrals around Bowsers kingdoms can now be emptied of all fault-prone flesh-based detection mechanisms!

And fewer Koopas have to be bored out of their mind on a 12-hour Sunday night shift in a dark and lonely security central 😉

How to see without eyes?

Posted on by

Azure Custom Vision!

We had a problem. A huge problem. We needed to know where in our floor plan the different components are placed.

By training our own custom vision model based on training data of bathroom floor plans, we managed to obtain an AI model able to detect components such as:

  • Toilet
  • Shower
  • Bath tub
  • Sink
  • Main pipes
Bathroom components detection with our custom vision model
Model scores on the training data

The model was published and the API made available for our backend application in C# to consume.

Super easy!

Copilot. The Rise of Machines

Posted on by

We claim badges:

  • Existential risk – for risk of existence of software developers

App should collect, list, track or managed the incidents that was assigned to engineers. The table must contains technical info for resolving the incident. Also the app should include the chart with summary of incident statuses. 

Specify prompt for app generation and submit:

Wait until the entities are created

Adjust if needed and proceed with app creation:

Just 10 seconds and you have an app that you are not ashamed to show on a demo to a client or to prove to a manager that you have been actively working and here are the results of your work. Isn’t it?

Find the right Mario for you

Posted on by

We claim badges:

  • Plug N’ Play – for Dynamics 365 plugin that updates Mario for each support request based on the context using OpenAI
  • The Existential Risk – for AI decision making and work assignment without human involvment
  • Go With The Flow – for automating of the technician assignment
  • Crawler – for an innovative approach of searching for the right Mario technician

Sometimes Princesses are confused and don’t know where to start from when they have technical issues. So we are here to help them with AI! Princesses just need to add the description of the problem and the Dynamics Plugin will suggest Marios that are currently available and best match the case.

So the Princess creates a new support request, and that’s were plugin is triggered. The plugin sends the problem to OpenAI’s smart ChatGPT. The prompt:
Given the following case description, rate its severity on a scale of 1 to 4, where 1 is minor and 4 is critical:

I seem to be having a bit of a predicament with our kingdom’s email system, and I’m in dire need of assistance. This morning, when I attempted to send out invitations for the upcoming royal ball, I noticed that none of my emails were being delivered. They seem to be stuck in the outbox, and no matter how many times I try to resend them, they simply won’t go through.

The result of the OpenAI request is the severity level, in our case it is 3. So the plugin is looking for Marios who can cope with this severity and assigns the case to this Mario. Also, plugin updates the details of the case:

It is an extraordinary way to search for an engineer, but also a risky for administrators of the support team, as AI is taking away their job! On the other hand – it follows the flow and automate the routine process, which is a major benefit for the business itself….

Mario Onboarding Center

Posted on by

We claim badges:

Hipster: We protect privacy by not saving any user information except the name in our database. Also, provide cartoon avatars instead of real face of the employees.

The Existential Risk: Our AI generates interesting background stories where humans may fail to do so.

Mario badge: Gamification of the onboarding process. Instead of boring onboarding we provide users a game character creation experience when joining the company

Thieving Bastards: We use paid ChatGPT api to do api requests.

Do you want a fast onboarding process for your agents? We have the right solution.

In our company, we use AI to generate images that look like your agents. We have customizable prompts to generate different characters. We can create a quick backstory for an immersive customer experience.

You can choose different appearance options. For Image generation, we will need a prompt and an image of the person. Based on the selected character AI will make your avatar a lookalike.

Take your picture and generate an image. We are using chatgpt API for image generation. It is a subscription model for text generation and pay as you go model for image generation. Using existing api instead of building a stable diffusion solution save from time. We use power automate cloud flows to call API requests and retrieve responses. We let the ai combine user picture and prompt to create a cartoony avatar.We do not save any user information in our dataverse to keep up with privacy requirements

Choose your theme for the background. AI will create a nice-looking story for you. Based on what is said in your story it will set a skill level too. This time we are using text generation apis of chatgpt with flows. Based on selected background option ai will generate a background story and skill level. Skill level considers generated story too, so it is meaningful.

.

Let us show you our potentyally world destroying AI

Posted on by

Responsible AI implementation is critical, especially as we delve deeper into advanced technologies. Microsoft is leading the way with its six foundational principles of responsible AI. In this post, our spotlight is on one of these key principles: reliability and safety.

Consider a scenario where a language model, which I developed, exercises complete control over another language model’s instructions. This setup immediately poses a challenging question of accountability, particularly if the subordinate language model engages in undesirable behavior, such as generating insults. While it might seem straightforward, the responsibility ultimately falls on me, as the developer. This underscores the importance of integrating robust oversight mechanisms and ethical guidelines in AI systems to ensure they operate within the realms of reliability and safety. By doing so, we can not only mitigate risks but also enhance the trustworthiness of AI applications in our increasingly digital world.

The described solution represents a high-level design overview. Leveraging the Bot Framework, it analyzes user sentiment and feeds this data into PromptFlow. However, it’s at this juncture where we encounter the more nuanced, potentially contentious aspect of our solution.

Our current PromptFlow process is straightforward yet effective. It primarily requires two inputs: sentiment and text input. Utilizing the meta-prompter LLM, the system communicates with an OpenAI instance located in Norway East. The core function here is to relay instructions to a secondary language model, ensuring the generated content aligns with the specified sentiment.

While this mechanism might not seem revolutionary, its effectiveness is largely due to the robust moderation capabilities of Azure’s OpenAI instances. These safeguards are crucial in preventing misuse or unintended consequences.

However, it’s important to acknowledge the potential risks. In the hands of someone with advanced prompt engineering skills and access to the right language models, this system could be manipulated into producing outputs that are ‘very non-compliant’ with ethical guidelines.

We recognize that our self-prompting AI solution might not be groundbreaking in practical applications, but it has already earned us the Dooh badge, showcasing our innovative approach within this technological space.