Understanding RAG Part VI: Effective Retrieval Optimization
Be sure to check out the previous articles in this series: •
PR Agencies in the Age of AI
TL;DR We compared Grok 3 and o3-mini’s results on this topic. They both passed. Since Grok 3 was released we thought it would be interesting to compare Grok 3 and o3-mini’s responses to a prompt about PR agencies in the age of AI. This is what we asked: With AI becoming such a driving force …
How Rocket Companies modernized their data science solution on AWS
This post was written with Dian Xu and Joel Hawkins of Rocket Companies. Rocket Companies is a Detroit-based FinTech company with a mission to “Help Everyone Home”. With the current housing shortage and affordability concerns, Rocket simplifies the homeownership process through an intuitive and AI-driven experience. This comprehensive framework streamlines every step of the homeownership …
Read more “How Rocket Companies modernized their data science solution on AWS”
Optimizing image generation pipelines on Google Cloud: A practical guide
Generative AI diffusion models such as Stable Diffusion and Flux produce stunning visuals, empowering creators across various verticals with impressive image generation capabilities. However, generating high-quality images through sophisticated pipelines can be computationally demanding, even with powerful hardware like GPUs and TPUs, impacting both costs and time-to-result. The key challenge lies in optimizing the entire …
Read more “Optimizing image generation pipelines on Google Cloud: A practical guide”
Supergiant Games battles back accusations it is working around SAG-AFTRA strike
After a public callout, the developers of Hades took to social media to clarify that they are not intending to recast union voice actors.Read More
DOGE Put Him in the Treasury Department. His Company Has Federal Contracts Worth Millions
Experts say the conflicts posed by Tom Krause’s dual roles are unprecedented in the modern era.
AI unlocks the emotional language of animals
Groundbreaking study shows machine learning can decode emotions in seven ungulate species. A game-changer for animal welfare? Can artificial intelligence help us understand what animals feel? A pioneering study suggests the answer is yes. Researchers have successfully trained a machine-learning model to distinguish between positive and negative emotions in seven different ungulate species, including cows, …
Evaluating Sample Utility for Data Selection by Mimicking Model Weights
Foundation models are trained on large-scale web-crawled datasets, which often contain noise, biases, and irrelevant information. This motivates the use of data selection techniques, which can be divided into model-free variants — relying on heuristic rules and downstream datasets — and model-based, e.g., using influence functions. The former can be expensive to design and risk …
Read more “Evaluating Sample Utility for Data Selection by Mimicking Model Weights”
Generate synthetic counterparty (CR) risk data with generative AI using Amazon Bedrock LLMs and RAG
Data is the lifeblood of modern applications, driving everything from application testing to machine learning (ML) model training and evaluation. As data demands continue to surge, the emergence of generative AI models presents an innovative solution. These large language models (LLMs), trained on expansive data corpora, possess the remarkable capability to generate new content across …
An SRE’s guide to optimizing ML systems with MLOps pipelines
Picture this: you’re an Site Reliability Engineer (SRE) responsible for the systems that power your company’s machine learning (ML) services. What do you do to ensure you have a reliable ML service, how do you know you’re doing it well, and how can you build strong systems to support these services? As artificial intelligence (AI) …
Read more “An SRE’s guide to optimizing ML systems with MLOps pipelines”