“They are hyper specialized in doing vector search at a cost performance ratio that's much better than everyone else”
♫
Said on The MAD Podcast: How AI Gets Built - with Matt Turck
“‘We started actually putting long-term memory in vector databases… MongoDB Atlas Vector Search.’”
Omar Santos · Security & GRC Decoded · The Agents Ran All Weekend. They Came Back With Zero Days. ft. Omar Santos, Distinguished Engineer, AI Security @ Cisco
Play from 36:35
36:35
Audio streams from the publisher’s own feed. Verbatim does not host or copy it.
What was described
Stored long-term memory in a vector database (MongoDB Atlas Vector Search) for context compression and retrieval
Said nearby on the same subject
“We represented molecules as a vector of the probability of creator… 1800 element vector… top-5 accuracy of 60%… it does as well as if you use chemical formulas”
♫
Said on Latent Space: The AI Engineer Podcast
“America.gov is designed… it just has a big old LLM search box… it stores no data, that it doesn't have user accounts… an LLM front end to, like, five million government databases.”
♫
Said on The Vergecast
“We have maybe 20% of the people who work at X aren't on one of the projects… they act as a kind of vector, transplanting interesting ideas and learnings from one team to another.”
AT
Astro Teller X
Think Fast Talk Smart: Communication Techniques ·
Moments like this, every Monday
The strongest new moments on your topics, in the speakers' own words. Free for three topics.
No card. No password. One-click unsubscribe.
Track a competitor?
Pro watches up to 25 names or phrases and emails you the morning after they are said.
See Pro, $29 a monthVerbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.