OpenNashPodcasts

Person

Pete Johnson

1 episodes · 20 quoted claims

IBM researcher E. F. Codd wrote the original paper that gave rise to SQL in June 1970.

“June of 1970 is when EF Codd, who's an IBM researcher, wrote the original white paper that gave birth to SQL”

The Cognitive Revolution · 0:06:31

MongoDB stores documents on disk in BSON, a binary form of JSON, which Pete Johnson says keeps one format from disk to client and makes it fast.

“we're storing it on disk in a binary form of JSON we call BSON, and that's part of why we're so fast”

The Cognitive Revolution · 0:09:39

Pete Johnson said MongoDB's revenue for fiscal 2026 was about $2.5 billion.

“we're about 2.5 billion is what we ended our revenue. That was our revenue number for our fiscal twenty six”

The Cognitive Revolution · 0:12:24

In 2020 MongoDB noticed customers running their own Apache Lucene servers beside their clusters for keyword search.

“So in 2020, we noticed that a common use case for MongoDB was for people to stand up their own Apache Lucene servers co-located with wherever their their MongoDB clusters might be”

The Cognitive Revolution · 0:23:22

MongoDB's managed service, Atlas, can be deployed in the data centers of Amazon, Google and Azure.

“which you can deploy your instances on any cloud hyperscaler data center you'd like amongst Amazon, Google, and Azure”

The Cognitive Revolution · 0:23:50

MongoDB introduced Atlas Search, keyword search on its managed service, in 2020.

“So in 2020, we introduced what's now known as Atlas Search, which is on the managed version, the managed version of MongoDB”

The Cognitive Revolution · 0:24:25

MongoDB acquired Voyage AI, an embedding model company, in 2025.

“we purchased Voyage in 2025, which created this better together story”

The Cognitive Revolution · 0:28:23

MongoDB announced two aggregation pipeline stages, rank fusion and score fusion, that merge keyword and vector search results in a single query.

“we just announced a a pair of features, one's called Rake Fusion and one's called Score Fusion”

The Cognitive Revolution · 0:30:26

Pete Johnson said Uber used up its entire 2026 token budget in thirteen weeks.

“Like in the wake of what happened at Uber earlier in the year, with them burning through their token budget for 2026 in thirteen weeks”

The Cognitive Revolution · 0:16:24

Pete Johnson said Voyage released version three of contextualized chunking last summer and version four in the six weeks before the recording.

“we released version three of that last summer. We just released four of that in the last six weeks”

The Cognitive Revolution · 0:41:43

Pete Johnson said embedding vectors typically have from 256 to as many as 2048 dimensions.

“you tend to have at least 256 dimensions and sometimes as high as 2048”

The Cognitive Revolution · 0:44:05

Pete Johnson said Voyage AI models typically rank at the top of a Hugging Face embedding benchmark, which the transcript calls RTab.

“Hugging Face has a benchmark out there called RTab, that Voyage AI models are typically at the top of”

The Cognitive Revolution · 0:48:50

Pete Johnson said Anthropic has no embedding model of its own and recommends MongoDB's Voyage models.

“Anthropic does not have an embedding model in market. They recommend us.”

The Cognitive Revolution · 0:50:00

MongoDB's auto embeddings feature automatically re-embeds a document's chosen field whenever it changes and updates the stored vector.

“Anytime an existing document with that attribute and it changes, we will automatically take that new, let's say it's text, put it through the embedding model, update the vector in the document”

The Cognitive Revolution · 0:52:25

Pete Johnson said ChatGPT launched at the end of 2022 with a simple design: a query went into the context window and the model answered.

“When ChatGPT came out in 2022, in the end of 2022, it had a very simple application architecture”

The Cognitive Revolution · 0:54:15

Pete Johnson said that, depending on the use case, a re-ranker can improve retrieval quality by about five to ten percent.

“you can get like a five to 10% boost at retrieval quality just by using a re-ranker on top of whatever your embedding model of choice is”

The Cognitive Revolution · 1:03:37

Pete Johnson cited ElevenLabs as an example of a company running multiple smaller agents per customer.

“There's a company called Eleven Labs out there, they have multiple agents per customer, this sort of micro-agent approach”

The Cognitive Revolution · 1:05:51

Pete Johnson said Voyage 4 includes a free, open-weight 'nano' embedding model that can be downloaded from Hugging Face.

“But we also introduced something called the nano, which is open weight and free for anybody to download in off of Hugging Space”

The Cognitive Revolution · 1:28:18

Pete Johnson said Anthropic published the Model Context Protocol on the Monday before Thanksgiving two years earlier, and competitors adopted it by March.

“MC published MCP on like Monday before Thanksgiving two years ago, and by March, all of their competitors had embraced it as a protocol”

The Cognitive Revolution · 1:29:35