OpenNashPodcasts

Topic

Amazon Bedrock

5 facts from 3 episodes, in date order. These are what speakers said on the shows, each linked to the moment it was said. They aren't independently verified.

2024

Garman says Amazon's Titan embeddings model is the most popular embeddings model in Amazon Bedrock, used for building search indices.

“the Titan embeddings model is by far the most popular embeddings model that we have inside of Bedrock today for people that are building search indices”

Matt Garman · Cloud Strategy in the AI Era with Matt Garman, CEO of AWS, 0:18:59

2024

Garman says customers using Amazon Bedrock never interact with a GPU directly; they send tokens in and receive tokens back.

“if you go use Bedrock models today, you never interact with a GPU, right? You just you send it tokens, you get tokens back”

Matt Garman · Cloud Strategy in the AI Era with Matt Garman, CEO of AWS, 0:40:03

Undated

Garman says guardrails matter because a financial-services chatbot that gives financial advice could lead to large fines.

“if you're building a chatbot on a financial services website, you can actually get find a lot of money if that thing starts giving out financial advice.”

Matt Garman · Cloud Strategy in the AI Era with Matt Garman, CEO of AWS, 0:23:46

Undated

Kapireddy says Truist's generative AI approach includes using services such as Azure OpenAI and Amazon Bedrock, which has Anthropic models behind it.

“using the services, APIs, Azure Open AI is as a service, for example, the bedrock as a service, uh, with the anthropic behind the scene.”

Chandra Kapireddy · Overcoming AI Hallucinations: Truist’s Chandra Kapireddy, 0:03:42

Episodes