Joseph Fluckiger's Blog

  Github Copilot is an AI-powered developer tool that has revolutionized the software development process. With its latest features, Copilot has become an indispensable tool for developers around the world. In this article, we will explore the new capabilities of Copilot and how it is changing the way developers work. Introduction Github Copilot has come a long way since its inception. It started as a code completion tool, but it has evolved into much more. With the power of natural language processing and machine learning, Copilot can now assist developers in various aspects of the software development life cycle. The Genesis of Copilot The journey of Copilot began in 2020 when a group of talented engineers got their hands on a raw version of OpenAI's GPT-3 model. They wanted to explore whether an automated pair programmer could be a reality. To their surprise, the model was able to solve 93% of the programming exercises they fed into it. This was the moment that won over even th

Tableau Bridge is now availble on Linux Containers. Yay! Now what does this mean and how do I build and run Linux Containers? We will discuss the advantages of running Bridge on Linux Containers the steps to build them, and finally, we will provide some automation script ideas for monitoring and scaling Linux Bridge agents. Tableau Bridge Today Until recently, Tableau Bridge was only available as a Windows application running on a Windows VM. It supported only one bridge agent per Virtual or Physical Machine. Advantages of Bridge in Containers Better Hardware Utilization: Linux containers are more efficient than Windows VMs, requiring only about 1/50th of the disk space. Ability to Spin Up Multiple Bridge Agents: With Linux Containers, it becomes easier to spin up multiple bridge agents on a single machine, improving scalability and resource utilization. Infrastructure Automation: Linux Containers enable easier automation of provisioning bridge agents and upgrading Tableau Bridge, the

Imagine talking to someone who forgets half of what you said a minute ago. Frustrating, right? This is the challenge many artificial intelligence models face today. Artificial Intelligence and LLMs have made significant advancements in 2023, but one significant limitation is the Context window size limits. Context window is analogous to short term memory. When you ask a question to an LLM, it can only remember so much about the context of your question. A recent research paper introduces memGPT, which aims to provide AI with unlimited short term memory. The Challenge of Limited Memory in AI AI models have a fixed context window that restricts the amount of information they can process. While improvements have been made, these models still have limitations. MemGPT proposes a system inspired by the memory hierarchy in traditional operating systems. Introducing memGPT: Towards LLMs as Operating Systems MemGPT effectively manages its own memory through function calls, allowing the AI model

I've used Excel for over 20 years. I've used Excel for everything from personal finance, to data center capacity planning. I even wrote a reporting program based off of Excel which used Excel formulas to render data and images! The application was TraceFinder and was used in the 2016 Olympics in which our ThermoFisher Analytical Chemestry instruments and reporting software were use to ensure that Usain Bolt and Michael Phelps and the rest of the Olympic athletes were drug free during the competition. This was an awesome application made possible by the power of Excel. But Excel formulas are a pain to write, and nowhere near as powerful as a fully turing complete language like Python which is the workhorse of DataScience.  If you've used Microsoft Excel, you're among the 750 million people across the globe who rely on this powerhouse productivity app. The recent integration of Python into Excel, announced by Microsoft, is an exciting development that is poised to elevate

In my daily software development I have begun to use AI Tools like Chat GPT and Microsoft Copilot to become a more productive software developer. I would say I've gotten a 1.2 - 10x productivity gain by using these tools depending on the task. Also in some tasks these tools are a distraction and reduce my productivity, but overall there is a significant improvement in productiivty and also in the joy and fun I feel when writing code. So this got me thinking: How far can we take this? If Chat GPT can write specific snipits of code for me, can it also perform all my other tasks that me and my team perform on a daily basis to produce working software? In the future I will just be managing a team of AI Agents? Below is what I found, and it seems that this future is closer than you might think. In today's tech landscape, AI agents have emerged as revolutionary tools, akin to AI professionals capable of executing complex tasks autonomously. Key components of AI agents include their p