Dynamic retrieval-augmented generation (RAG) with short-term memory + Detecting AI-Generated Text
Talk #0: Introductions and Meetup Announcements
By Chris Fregly and Antje Barth, Generative AI Engineers @ AWS
Talk #1: Dynamic RAG with short-term memory
By Vasily Vasinov, CTO @ Griptape
The way RAG is used today assumes some prior content vectorization. Griptape allows developers to build agents that can use CoT with tools for content retrieval and consequent search/summarization/QA. For example, you can ask a Griptape agent to search a web page for X. Griptape will use the WebScraper tool to load the content into STM, then use another tool to dynamically vectorize it, and query it for X—no preloading needed.
Talk #2: Detecting AI-Generated Text
By Nikita Kozodoi, Applied Scientist @ AWS
Large language models excel in generating realistic text, which emphasizes the need for systems that detect whether a text is generated or written by a human. Detecting generated text is crucial in many applications such as identifying fake news, filtering product reviews, and assessing student assignments. In this talk, I will discuss typical differences between generated and human text, and overview the prominent state-of-the-art text detection approaches, including watermarking, supervised and zero-shot methods. We will also touch on limitations of the existing detectors and discuss emerging approaches to evade them.
RSVP Webinar: https://www.eventbrite.com/e/webinark...
Zoom link: https://us02web.zoom.us/j/82308186562
Related Links
===========
Generative AI - Free Course - DeepLearning.ai: https://bit.ly/gllm
O'Reilly Book: https://www.amazon.com/Generative-AWS...
Website: https://generativeaionaws.com
Meetup: https://meetup.generativeaionaws.com
GitHub Repo: https://github.com/generative-ai-on-aws/
YouTube: https://youtube.generativeaionaws.com
![[WORKSHOP] Generative AI and Large Language Models: Fine-tuning with SageMaker + PEFT + RLHF + PPO](https://images.videosashka.com/watch/fLPNMleobgY)
