A faster way to solve complex planning problems
By eliminating redundant computations, a new data-driven method can streamline processes like scheduling trains, routing delivery drivers, or assigning airline crews.
Clario enhances the quality of the clinical trial documentation process with Amazon Bedrock
The collaboration between Clario and AWS demonstrated the potential of AWS AI and machine learning (AI/ML) services and generative AI models, such as Anthropic’s Claude, to streamline document generation processes…
Python Machine Learning
If you're looking to dive deep into the world of machine learning and deep learning using Python, then this book is a must-have for your collection. Python Machine Learning, 3rd…
Training LLMs to self-detoxify their language
A new method from the MIT-IBM Watson AI Lab helps large language models to steer their own responses toward safer, more ethical, value-aligned outputs.
AI
In "The Last Job: AI will eliminate millions of jobs. What are people going to do?" readers are taken on a thought-provoking journey into the future where artificial intelligence has…
Building an AIOps chatbot with Amazon Q Business custom plugins
In this post, we demonstrate how you can use custom plugins for Amazon Q Business to build a chatbot that can interact with multiple APIs using natural language prompts. We…
How TransPerfect Improved Translation Quality and Efficiency Using Amazon Bedrock
This post describes how the AWS Customer Channel Technology – Localization Team worked with TransPerfect to integrate Amazon Bedrock into the GlobalLink translation management system, a cloud-based solution designed to…
AI Hacks
"Transform Your Business: AI Hacks to Maximize Profit & Minimize Cost" is a game-changer for any business looking to stay ahead in today's competitive market. The book breaks down the…
Defending against Prompt Injection with Structured Queries (StruQ) and Preference Optimization (SecAlign)
Recent advances in Large Language Models (LLMs) enable exciting LLM-integrated applications. However, as LLMs have improved, so have the attacks against them. Prompt injection attack is listed as the #1…
New method efficiently safeguards sensitive AI training data
The approach maintains an AI model’s accuracy while ensuring attackers can’t extract secret information.