Bloomberg's Generative AI

_{Sign up to receive Surface Area or follow me on Linkedin or Twitter. Book a meeting here to talk about ghostwriting from my agency, Principals Media}.

Bloomberg LP has quietly turned on its first generative AI application.

Clients of the terminal can now create AI summaries of conference call transcripts.

A friend who is a money manager walked me through a demo showing how summaries are accessible via the Document Search function.

The feature is a small, but significant development for financial professionals.

It illustrates both the opportunity and challenge of integrating generative AI into terminals used by more than 325,000 Wall Street traders and investors.

Large legacy data providers such as Bloomberg, FactSet and others are trying to balance the opportunity of incorporating the ChatGPT technology that OpenAI unveiled in late 2022 with the risks that it produces hallucinations.

Bloomberg has taken an incremental approach. The new summaries are delivered from hard-coded prompts on a narrow range of documents. Unlike ChatGPT, the system doesn’t allow users to submit follow up questions.

Here’s how it works: Using the Document Search function clients can select a company and then any of the recent documents that display a summary icon.

The summary has predefined categories including guidance, capital allocation, labor, the macro environment, supply chain, pricing and product development.

It’s easy to use and includes a nice feature: when you click on any of the sections it links back to the original transcript to provide transparency.

There appears to be no way to ask follow-up questions, which is one of the defining features of ChatGPT. It doesn’t tap into the broader Bloomberg database for numbers and news.

Nor can the summary handle multiple documents at the same time to identify longer-term trends.

The summaries also don’t include the questions asked by analysts.

So, you cannot ask: “What are the biggest issues Tesla faced in the past quarter? Or what did the analysts ask Apple CEO Tim Cook? Or did Google talk about its business in Europe?

Bloomberg’s earnings call summaries do a better job than the ones produced by other LLMs, such as Microsoft’s Bing or Google’s Bard.

That’s largely because they are limited to the conference call transcript. It doesn’t use the open web, which can introduce more errors.

It’s not clear whether the company is using its proprietary BloombergGPT large language model to generate the text.

There are scores of startups leveraging generative AI to analyze transcripts as well as other documents that provide more flexibility and greater depth.

Bloomberg is likely taking the cautious approach because there is so much more at stake when you are the market leader.

The larger the data sets and the more open-ended the queries the greater risk of errors and hallucinations.

Still, without the ability to customize questions you lose some of the magic.

BRIEF OBSERVATIONS

SHIPPING LANES: This reminds me of Covid. It’s incredibly disruptive but people just find a way around the issue.

CULTURAL SHIFT: Andrew is a friend of mine who throws parties. I’ve been to them and also noticed people seem to be drinking less.

NEVER LISTEN TO YOUR FRIENDS: There isn’t enough humor online.

PEAK DAD: More humor.

PERCEPTION VS REALITY: I’m a fan of the reality versus perception meme and this one in particular hits home.