|
Ben Young presents an Ignite presentation at Edge Field Day 2 |
This Presentation date is October 4, 2023 at 14:00-15:30.
Presenters: Ben Young, Brian Knudtson, Gina Rosenthal, Jim Czuprynski
Follow on Twitter using the following hashtags or usernames: #EFD2
Bridging the IT Security Gap With Brian Knudtson
Watch on YouTube
Watch on Vimeo
In this Edge Field Day Delegate Ignite Talk, Brian Knudtson discussed the communication challenges between IT and security teams in businesses. Typically, IT focuses on maintaining efficient information flow, while security prioritizes data protection and preventing breaches, often leading to the misperception of the security team as a “Department of No.” To foster effective collaboration, both teams must gain a better understanding of each other’s roles. Collaboration between security and businesses is crucial for enabling and supporting business objectives and secure data use. Backup infrastructure plays a pivotal role in data cataloging, protection, and threat detection, aiding in disaster recovery and digital forensics. Knudtson emphasized the need for aligning communication and actions between IT and security teams and adapting to emerging trends like entropy detection for compromise indicators. Customized backup integration with security workflows and proactive measures such as diverse backup policies were also highlighted as essential components of successful collaboration in safeguarding the organization.
Personnel: Brian Knudtson
Leveraging Generative AI for Accurate Career Path Predictions with Jim Czuprynski
Watch on YouTube
Watch on Vimeo
In this Edge Field Day Delegate Ignite Talk, Jim Czuprynski introduced an innovative tool developed by his team that harnesses generative AI within Oracle databases. This tool draws from a data pool of 600,000 IT professionals’ profiles, offering not only predictive insights into an individual’s IT career but also a glimpse into how colleagues perceive them. Czuprynski’s talk emphasizes the value of this technological advancement and its potential to challenge cognitive biases. He offers a compelling narrative on the intersection of technology, intuition, and cognitive bias in our lives, stressing the importance of relying on data-driven insights rather than intuition alone.
Personnel: Jim Czuprynski
Generative AI Tools – What Could Go Wrong? with Gina Rosenthal
Watch on YouTube
Watch on Vimeo
In this Edge Field Day Delegate Ignite Talk, Gina Rosenthal discusses the promising growth of generative AI technology, which leverages machine learning to generate predictive data and discern patterns. However, she emphasizes the potential pitfalls associated with generative AI. The technology can perpetuate bias, particularly when trained on data from the internet, which may have inherent biases due to historical demographics. Additionally, the environmental and ethical concerns surrounding generative AI are significant, from the high computational power and energy requirements to the potential for creating or spreading harmful content. Rosenthal calls for a more cautious and responsible approach to utilizing generative AI, emphasizing the importance of understanding its limitations and risks while recognizing that human creativity and critical thinking remain essential, ensuring a balanced perspective on its practical applications without undue reliance.
Personnel: Gina Rosenthal
Falling Down a LLM Rabbit Hole with Ben Young
Watch on YouTube
Watch on Vimeo
In this Edge Field Day Delegate Ignite Talk, Ben Young shares his journey into building a chatbot web interface, with a specific focus on creating a chatbot for the Veeam knowledge base articles using OpenAI models. Along the way, he delves into the concept of retrieval augmented generation (RAG) and the challenges of relying solely on large language models, such as limited access to private data and high retraining costs. To overcome these challenges, Young emphasizes the importance of understanding the chatbot’s inner workings, from document retrieval to interpretation and answer generation. He describes the process of building the knowledge base dataset and the API, highlighting the role of embeddings in matching queries to relevant information within the database. Young also explores different options for data storage, including vector databases and traditional databases with vector support, while noting the use of tools like Superbase and Langchain to manage queries and interactions with the data. Ultimately, he underscores the power of language models like Vani GPT in providing accurate and targeted responses, emphasizing the significance of crafting effective queries and prompts for optimal results.
Personnel: Ben Young