Welcome and opening remarks by the Program Chair Sebastian Meyen.

In a world where loneliness is an epidemic, could artificial intelligence be the answer? Are ‘friends’ truly electric?

In 1979, Gary Numan asked this in his hit song ‘Are ‘Friends’ Electric?’, inspired by Philip K. Dick’s novel “Do Androids...

Nowadays, when AI agents play the role of junior developers, things will change. Soon, teams will be composed of a human Team Lead and virtual, AI based developers. What are the best practices for managing such a team? How can you optimize its vel...

Large Language Models like ChatGPT are extremely powerful. You can throw almost any task at them and they will solve it for you. But they are not without their shortcomings…LLMs are notorious for hallucinating random information and giving d...

When tackling your complex software projects how do you choose to represent your data? Do you simply pass around arrays of JavaScript objects of the any type that you get from your API calls? Have you ever found yourself writing too much code and ...

Training and running ML models can be a time consuming and expensive process, when using high-end cloud compute resources. But why should you? Your organization already owns a lot of computing resources - the employees' machines. Those machines ar...

Generative AI is so powerful and apparently trivial for everyone to use that nearly everyone is sure to have the killer app of the next millennium. Most of the ideas, though, are revamped or rebranded versions of ChatGPT when not, worse yet, LLM m...

Believe it or not, there are already over a million LLMs available on Hugging Face, including public-facing GPTs like ChatGPT, Claude, Gemini, Grok, Mistral, Qwen, DeepSeek, and many more. For programmers, this field is equally rich, with a ...

AI seems to be synonymous with Deep Learning Learning these days. Yet, there was a time before AlexNet when there was a large field of Artificial Intelligence research that seems totally alien and forgotten now, only a decade and a half later. But...

LLMs have experienced a significant boom. Among the most popular use cases are intelligent knowledge search engines, or put simply - chatbots. Whether on an airline's website, facing customers, or as the new search tool in your company's intranet,...

Vision transformers have been all the rage for computer vision, as they have pushed the performance of computer vision systems to new heights thanks to the pretraining and scaling abilities they inherit from their LLM cousins. For a while it seeme...

Even though the first chatbot was introduced in 1966, it took us until 2022 to finally have a chatbot that people actually liked using.
In this talk I will briefly take you through the history of chatbots and all of their sh...

With models like o1 from OpenAI and r1 from DeepSeek we have proof that LLM's can be trained to think longer and explore alternatives to make better advice and decisions. How will this impact RAG applications that use companies private data in the...

Explore a mind-bending feature of functional programming, how you can easily get started with GPU programming, and learn about underappreciated SQL features that you didn't know you needed. Having facilitated code retreats for years, I’ve witnesse...

In the era of AI-driven software development, numerous tools aim to help developers work more efficiently and creatively. GitHub Copilot is widely regarded as the market leader, setting a high bar for AI-assisted coding. But could there be a...

Running multiple experiments efficiently is a key component of Machine Learning (ML) workflows. It allows us to test hypotheses quickly and gain insights for the next iteration, moving us closer to production-level quality. By using Amazon Sagemak...

Embedding models are at the core of search, recommendation, and retrieval-augmented generation (RAG) systems, transforming data into meaningful representations. We can adapt state-of-the-art large language models (LLM...

The evolution of artificial intelligence (AI) provides a compelling narrative of innovation and cautionary lessons. Drawing on the themes explored in Rebels of Reason, a new book by John Willis, ...

What do acronyms like RAG and GPT really mean? What is the math behind the “magic” of deep learning? What is a “perceptron” and why is it called a “neural network?” This talk demystifies AI’s field of machine learning for AI-curious technical and ...

OpenAI's GPT language models are powerful on their own, but their true potential is unlocked when enhanced with hosted tools like knowledge retrieval, code interpreter, and function calling. In this session, Rainer Stropek takes you on an in-depth...

Multi-modal models are breaking barriers by integrating diverse data types—text, images, and audio—into a unified understanding. This talk delves into the transformative potential of multi-modal AI, with a spotlight on OpenAI’s GPT-4 Vision. We’ll...

AI is one of the hottest trends currently. Everyone talks about generative AI, and thinking about how to add AI capabilities and use LLMs to extend the business capabilities of their servers. In this talk, Tamar will build a "Question-An...

Over the past year, OpenAI's API capabilities have significantly evolved, introducing powerful features such as the Assistant API with streaming support, retrieval tools, function calling, and the advanced code interpreter. These enhancement...

How do you build a strategy that takes into account the many possibilities of the future? The future is inherently unknown, but it can be explored. In this workshop, we'll work through steps to explore the future of AI (or your own topic), w...

The AI Agent Bootcamp: LLM Development with TypeScript is a hands-on, two-day workshop tailored for developers and engineers eager to build intelligent agents powered by Large Language Models (LLMs) using TypeScript. The bootcamp covers fou...