Evidence receipt / recommendation
Published · transcript-backedJeff Holmes: recommendation
23 Dec 2025 Conversations with Tyler Conversations with Tyler 2025 Retrospective
“I will say that it can definitely help brainstorm and find new guests and people who would be good for specific things, like who would be good for a live show.”
Source trail
Everything needed to verify it.
- Speaker
- Jeff Holmes
- Attribution
- Verified speaker
- Claim type
- recommendation
- Recorded
- 23 Dec 2025
- Publisher
- Conversations with Tyler
Transcript context
…No, it’s helped us do many more episodes. If you take Donald Lopez, the Buddhism scholar, maybe I read 30 books on Buddhism, which is a fair number, but I had so many GPT queries on Buddhism. I saved a few hundred dollars and a lot of time. I could just get right to the point and learn what I wanted to know. We could not have done as many episodes as we did had it not been for Large Language Models. It did change the production function. Things in terms of editing and producing the show beyond the interview and the prep, there have been marginal improvements. There are things that make editing a little easier, these machine learning algorithms that allow you to do a pass of the episode and get rid of ums and ahs and things like that. Those have been around for a while. They’re getting better. It certainly helps. I will say that it can definitely help brainstorm and find new guests and people who would be good for specific things, like who would be good for a live show. There is some prompting techniques that you have to use there because it will tend to regurgitate very well-known names. Who’s it saying we should do? Do you remember?…
Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.