Amazon's CTO Created a Meeting Summarizing App for Some Reason | TechCrunch - Latest Global News

Amazon’s CTO Created a Meeting Summarizing App for Some Reason | TechCrunch

How does Amazon CTO Werner Vogels – a man worth untold millions who completely bought the small Airbnb in the center of Amsterdam where he had been living during the COVID-19 pandemic – spend his days? What it looks like: Developing AI-powered meeting summarization apps. Imagine that.

In a post this week on Vogels’ personal blog, he goes into detail about Distill, an open source app he developed with his “OCTO” (Office of the CTO) team to transcribe and summarize their conference calls. Distill takes an audio recording of a meeting (in formats like MP3, FLAC, and WAV), analyzes it, and creates a summary along with a list of items to complete. Optionally, this summary and list can be spit out to platforms like Slack via custom integrations.

A sample summary from the Vogel’s Distill meeting summary provided by Amazon Tech.
Photo credit: Distill

As you might expect from an app from Amazon’s CTO, Distill conspicuously relies on paid Amazon products and services to do the computationally intensive work. AWS Transcribe performs Distill transcription; Amazon S3 provides storage for the meeting audio files; and Bedrock, Amazon’s generative AI development suite, handles the synopsis.

But why create a meeting summary when there are countless tools that would serve this purpose? Well, I have to imagine Vogels thought, why not? After all, he has plenty of resources and enough free time for hobby programming projects. According to the blog, he is already trying to port Distill’s code from Python to Rust. Being a CTO is a nice job if you can get it.

What’s unique about Distill is that you can choose which AI model does the meeting summarization. By default it is Sonnet, a mid-range model from Anthropic’s Claude 3 family. (Amazon’s massive stake in Anthropic may have something to do with this design decision.) But any model hosted in Bedrock will work, like Meta’s Llama 3 and models from AI startups Mistral, AI21 Labs, and Cohere.

Vogels doesn’t promise that Distill won’t make mistakes.

“Remember, AI is not perfect,” he writes. “Some of the summaries we get back… have errors that require manual correction. But that’s okay because it still speeds up our processes. It’s just a reminder that we need to continue to be critical and involved in the process. Critical thinking is as important today as ever.”

I would argue that the need to be involved in summarization defeats the purpose of automatic summarization. You might as well hire a stenographer. But you’ll never catch Vogels talking badly about the technology his employer sells. And I bet that’s why he’s still CTO.

Sharing Is Caring:

Leave a Comment