Month: July 2024

Load Balancing For High Performance Computing Using Quantum Annealing:Smoothed Particle Hydrodynamic

by

:::info Authors: (1) Omer Rathore, Department of Physics, Durham University; (2) Alastair Basden, Department of Physics, Durham University; (3) Nicholas Chancellor, Department of Physics, Durham University and School of Computing, Newcastle University; (4) Halim Kusumaatmaja, Department of Physics, Durham University and Institute for Multiscale Thermofluids, School of Engineering, The University of Edinburgh. ::: Table of … Read more

This Week in AI: With Chevron’s demise, AI regulation seems dead in the water

by

Hiya, folks, and welcome to TechCrunch’s regular AI newsletter. This week in AI, the U.S. Supreme Court struck down “Chevron deference,” a 40-year-old ruling on federal agencies’ power that required courts to defer to agencies’ interpretations of congressional laws. Chevron deference let agencies make their own rules when Congress left aspects of its statutes ambiguous. … Read more

Who’s Harry Potter? Approximate Unlearning in LLMs: Conclusion, Acknowledgment, and References

by

:::info Authors: (1) Ronen Eldan, Microsoft Research (email: roneneldan@microsoft.com); (2) Mark Russinovich, Microsoft Azure and Both authors contributed equally to this work, (email: mark.russinovich@microsoft.com). ::: Table of Links Abstract and Introduction Description of our technique Evaluation methodology Results Conclusion, Acknowledgment, and References Appendix 5 Conclusion The ambitious endeavor of teaching a Large Language Model (LLM) … Read more

Who’s Harry Potter? Approximate Unlearning in LLMs: Results

by

:::info Authors: (1) Ronen Eldan, Microsoft Research (email: roneneldan@microsoft.com); (2) Mark Russinovich, Microsoft Azure and Both authors contributed equally to this work, (email: mark.russinovich@microsoft.com). ::: Table of Links Abstract and Introduction Description of our technique Evaluation methodology Results Conclusion, Acknowledgment, and References Appendix 4 Results We tested our method in two settings: Meta-llama/Llama-7b-hf-chat (a 7B-parameter … Read more

Gamified Learning With An AI Board Game Tournament: Conclusion, Software and Data

by

:::info Authors: (1) Ken Hasselmann, ECAM Brussels School of engineering, Brussels, Belgium and Universite libre de Bruxelles, Brussels, Belgium; (2) Quentin Lurkin, ECAM Brussels School of engineering, Brussels, Belgium. ::: Table of Links Abstract and 1. Introduction Course design Course assessment Conclusion, Software and Data, Acknowledgements, and References 4. Conclusion We have presented our design … Read more

Who’s Harry Potter? Approximate Unlearning in LLMs: Evaluation methodology

by

:::info Authors: (1) Ronen Eldan, Microsoft Research (email: roneneldan@microsoft.com); (2) Mark Russinovich, Microsoft Azure and Both authors contributed equally to this work, (email: mark.russinovich@microsoft.com). ::: Table of Links Abstract and Introduction Description of our technique Evaluation methodology Results Conclusion, Acknowledgment, and References Appendix 3 Evaluation methodology To adequately assess the efficacy of our unlearning technique, … Read more

Who’s Harry Potter? Approximate Unlearning in LLMs: Description of our technique

by

:::info Authors: (1) Ronen Eldan, Microsoft Research (email: roneneldan@microsoft.com); (2) Mark Russinovich, Microsoft Azure and Both authors contributed equally to this work, (email: mark.russinovich@microsoft.com). ::: Table of Links Abstract and Introduction Description of our technique Evaluation methodology Results Conclusion, Acknowledgment, and References Appendix 2 Description of our technique Assume that a generative language model has … Read more

Who’s Harry Potter? Approximate Unlearning in LLMs: Appendix

by

:::info Authors: (1) Ronen Eldan, Microsoft Research (email: roneneldan@microsoft.com); (2) Mark Russinovich, Microsoft Azure and Both authors contributed equally to this work, (email: mark.russinovich@microsoft.com). ::: Table of Links Abstract and Introduction Description of our technique Evaluation methodology Results Conclusion, Acknowledgment, and References Appendix 6 Appendix 6.1 Further examples Figure 6 gives further examples for prompt … Read more

Who’s Harry Potter? Approximate Unlearning in LLMs: Abstract and Introduction

by

:::info Authors: (1) Ronen Eldan, Microsoft Research (email: roneneldan@microsoft.com); (2) Mark Russinovich, Microsoft Azure and Both authors contributed equally to this work, (email: mark.russinovich@microsoft.com). ::: Table of Links Abstract and Introduction Description of our technique Evaluation methodology Results Conclusion, Acknowledgment, and References Appendix Abstract Large language models (LLMs) are trained on massive internet corpora that … Read more

Build your multilingual personal calendar assistant with Amazon Bedrock and AWS Step Functions

by

Foreigners and expats living outside of their home country deal with a large number of emails in various languages daily. They often find themselves struggling with language barriers when it comes to setting up reminders for events like business gatherings and customer meetings. To solve this problem, this post shows you how to apply AWS … Read more

Medical content creation in the age of generative AI

by

Generative AI and transformer-based large language models (LLMs) have been in the top headlines recently. These models demonstrate impressive performance in question answering, text summarization, code, and text generation. Today, LLMs are being used in real settings by companies, including the heavily-regulated healthcare and life sciences industry (HCLS). The use cases can range from medical … Read more

Introducing guardrails in Knowledge Bases for Amazon Bedrock

by

Knowledge Bases for Amazon Bedrock is a fully managed capability that helps you securely connect foundation models (FMs) in Amazon Bedrock to your company data using Retrieval Augmented Generation (RAG). This feature streamlines the entire RAG workflow, from ingestion to retrieval and prompt augmentation, eliminating the need for custom data source integrations and data flow … Read more

Marvel’s What If…? series to end with third season

by

Image: Marvel Studios The premise of Disney Plus’ What If…? made it seem like the animated Marvel series might run indefinitely as the studio keeps putting out live-action projects, but it looks like this chapter of the big multiverse story is just about over. Though What If…? season 3 doesn’t have a premiere date, Entertainment … Read more

Prompt engineering techniques and best practices: Learn by doing with Anthropic’s Claude 3 on Amazon Bedrock

by

You have likely already had the opportunity to interact with generative artificial intelligence (AI) tools (such as virtual assistants and chatbot applications) and noticed that you don’t always get the answer you are looking for, and that achieving it may not be straightforward. Large language models (LLMs), the models behind the generative AI revolution, receive … Read more