4.8 • 521 Ratings
🗓️ 6 October 2024
⏱️ 77 minutes
🧾️ Download transcript
Click on a timestamp to play from that location
0:00.0 | Well, have you guys talked about large language models on TechPod before? |
0:04.1 | Tells you how much I listen to the podcast. |
0:05.6 | It's fine. |
0:06.0 | I don't expect friends to listen to it. |
0:07.5 | But like I don't expect my partner. |
0:09.5 | I don't expect my friends to listen to the podcast. |
0:11.4 | It's totally acceptable in the modern context because everybody makes podcasts. |
0:15.5 | That's right. |
0:16.3 | We have talked about LLMs. |
0:18.3 | I am generally pretty bearish on generative stuff, but I think it's pretty cool for like |
0:24.5 | taking spoken language and making it parsible English and stuff like that. |
0:30.1 | Generally, like, I don't know, call me old fashioned. |
0:32.5 | Teaching computers to lie seems like a mistake. |
0:35.3 | Well, this is teaching computer or something else. |
0:37.0 | So Google has a project called Notebook LM and it's a service where you can upload documents. |
0:44.3 | So research papers, your notes, you know, a whole corpus that you upload. |
0:50.1 | It could be voice memos. |
0:51.2 | It could be whatever it is. |
0:51.9 | And the idea is that helps you gather information and then you can then prompt it. |
0:56.0 | And this becomes the corpus that it pulls information from. |
1:00.0 | And you can find patterns. |
1:02.0 | So people use it to summarize legal documents. |
... |
Transcript will be available on the free plan in -177 days. Upgrade to see the full transcript now.
Disclaimer: The podcast and artwork embedded on this page are from Nice Segue, LLC, and are the property of its owner and not affiliated with or endorsed by Tapesearch.
Generated transcripts are the property of Nice Segue, LLC and are distributed freely under the Fair Use doctrine. Transcripts generated by Tapesearch are not guaranteed to be accurate.
Copyright © Tapesearch 2025.