“We store a lot of our information we take it out of the KB cache put it onto SSD and then you can get away with bypassing RAG”

John Davis · ThursdAI - The top AI news from the past week · ThursdAI - Nov 5 - Is it completely over for AI?

Play from 1:09:49
1:09:49

Audio streams from the publisher’s own feed. Verbatim does not host or copy it.

What was described

store information from the KB cache onto SSD and bypass RAG to retrieve data

Said nearby on the same subject

“When you get back the answer… it comes with a timestamp… you can keep that information for a day… caching infrastructure”
♫
Said on The Peterman Pod
Why it worked TTL up to a day Share this moment
“First is production, so drafting, summarization, information retrieval. The second is like more diagnosis, so recurring variance analysis, preparing forecasts, explaining what's changed. And then the third is like decision support.”
EL
Eric Lin
FP&A Today ·
How they work Share this moment
“By doing this you put in all the information in one place where it can retrieve it easily it can process it and very very quickly have a full understanding of of what you do who you serve where you serve them what you charge your guarantees”
♫
Said on AI SEO & Business Automation Podcast
How they work Share this moment
“If you come back after one hour and one minute, that cache is gone… cache writes are expensive… leaving sessions idle for more than an hour is expensive.”
DS
Dave Slutzkin
The Startup Podcast ·
Automation 5 minutes; 1 hour Share this moment

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 month

Verbatim quotes a short extract and links to the episode; the episode belongs to its publisher. Remove a show.