Skip to content Skip to sidebar Skip to footer

Generative AI

How Mend.io discovered concealed patterns in CVE data using Anthropic Claude on the Amazon Bedrock platform

The field of cybersecurity is continually evolving, and AI solutions that can efficiently handle and analyze vast amounts of data are the need of the hour. One such solution is provided by Anthropic Claude on Amazon Bedrock, a generative AI model that can analyze the unstructured data in Common Vulnerabilities and Exposures (CVEs) reports. MEND.io,…

Read More

Safe AccountingAI Chatbot: Lili’s Adventure with Amazon Bedrock

This blog post was written in collaboration with Lili, a financial platform that offers advanced business banking along with integrated accounting and tax preparation software. The post focuses on how Lili used Amazon Bedrock's artificial intelligence (AI) capabilities to design AccountantAI, an intelligent chatbot specifically developed to provide on-demand accounting advice to small business owners. Given…

Read More

How Mixbook employed generative AI to provide customized photobook experiences.

Mixbook, the number one rated photo book service in the US, has harnessed the capabilities of generative artificial intelligence (AI) in Amazon Web Services (AWS) to make personalized photo book experiences. User photos are interpreted and creatively enhanced with Mixbook Smart Captions. The service does not fully automate the creative process, but guides the users'…

Read More

Ten Capabilities GPT-4 Offers that GPT-3.5 Could Not Achieve.

GPT-4, the latest version of OpenAI’s Generative Pre-trained Transformer models, breaks new ground with its array of advanced capabilities that allow it to perform tasks unattainable by its predecessor, GPT-3.5. These enhancements span various domains and include ten main functions, which underscore GPT-4's potential and versatility. Firstly, GPT-4 integrates advanced multimodal functionalities enabling the simultaneous processing…

Read More

GenSQL: An AI System that Utilizes Generative Mechanisms to Enhance the Application of Probabilistic Programming in Synthesizing Tabular Data Analysis.

A team of researchers from MIT, Digital Garage, and Carnegie Mellon has developed GenSQL, a new probabilistic programming system that allows for querying generative models of database tables. The system extends SQL with additional functions to enable more complex Bayesian workflows, integrating both automatically learned and custom-designed probabilistic models with tabular data. Probabilistic databases use algorithms…

Read More

Enhance the precision of RAG using meticulously adjusted embedding models on Amazon SageMaker.

Retrieval Augmented Generation (RAG) enhances the performance of large language models (LLMs) by incorporating extra knowledge from an external data source, which wasn't involved in the original model training. The two main components of RAG include indexing and retrieval. Despite their merits, pre-trained embeddings models, trained on generic datasets like Wikipedia, often struggle to effectively portray…

Read More

Utilizing Agents for Amazon Bedrock to interactively produce infrastructure as a code.

In the evolving landscape of cloud infrastructure, Agents for Amazon Bedrock stands as a promising tool for enhancing infrastructure as code (IaC) processes. This platform employs artificial intelligence to automate the triggering and orchestration of user-requested tasks, augmenting them with company-specific information. The process involves analyzing cloud architecture diagrams, which are then converted into Terraform…

Read More