#80: Is AWS Bedrock the OpenAI killer, with Randall Hunt
Aug 15, 2023
auto_awesome
Randall Hunt, VP of Cloud Strategy and Innovation at Caylent, discusses AWS Bedrock and its advantages, debunking AWS's supposed weakness in AI. They explore tokenization, vector stores, prompt injection, and the challenges of using AWS Lambda with chat GPT. Learn about the adoption of Bedrock in different industries and the benefits of response streams in both Lambda and Bedrock.
AWS Bedrock offers serverless inference with benefits over other services.
Large language models have had a significant impact on the AI space.
Ethical concerns surrounding AI require thoughtful consideration and regulation.
Deep dives
Randall Hunt's Background and Role at Kalent
Randall Hunt is the VP of Cloud Strategy and Innovation at Kalent, a Premier AWS Consulting Partner. He has experience working at companies like Vandyre, Facebook AI, and AWS. Kalent focuses solely on AWS and has extensive expertise in the platform. The company is growing rapidly and has been recognized as one of the fastest-growing companies in its industry.
Randall's Experience as an AWS Partner
Randall discusses his transition from being an AWS engineer to working as an AWS Partner. He talks about the advantages and opportunities that come with working in the AWS partner network, as well as some of the challenges and the varying utility of different partner functions.
Randall's Previous Work at Facebook AI
Randall shares his experience working at Facebook AI, specifically leading the PyTorch team. He discusses the onboarding process and the need to contribute code to the project before working on the team. He also mentions the power of large language models and how they have impacted the AI space.
Introduction to AWS Bedrock
Randall explains the concept of AWS Bedrock, a service for serverless inference. He highlights the benefits of using Bedrock over other services and provides a demo of its functionalities, including integration with Amazon Kendra, multi-token embeddings, and prompt construction using the Lovable and Lineage Python SDKs.
The Future of AI and Ethical Considerations
Randall expresses his optimism about the future of AI and its potential for various industries. He discusses the ethical concerns surrounding AI, such as hallucination and prompt injection, and emphasizes the need for thoughtful consideration and regulation. While acknowledging the challenges, Randall believes that AI offers valuable efficiency gains and opportunities for innovation.
In this episode, I spoke with Randall Hunt, who's the VP of Cloud Strategy and Innovation at Caylent and had previously worked at Vendia, Facebook AI, AWS and SpaceX.
We talked about AWS Bedrock, what is it and how it works and saw a demo of a simple AI application built with Bedrock and LangChain. Randall explained the advantages of using Bedrock and why tales of AWS's supposedly weakness in AI are far-fetched.
I had a lot of fun talking to Randall and learnt a lot from the conversation and I hope you will too. This episode includes some live demo, which is best enjoyed if you watch the episode on YouTube here.
For more stories about real-world use of serverless technologies, please subscribe to the channel and follow me on X as @theburningmonk.
And if you're hungry for more insights, best practices, and invaluable tips on building serverless apps, make sure to subscribe to our free newsletter and elevate your serverless game!