Elicit, every mention
23 scenes · ← back to Elicit
tap a year for its mentions
every year anyone Jungwon Byun 15James Brady 10Andreas Stuhlmüller 4Adam Wiggins 3
Verbatim, from the transcripts: the passages where Elicit comes up
Beating Google at Search with Neural PageRank and $5M of H200s — with Will Bryk of Exa.ai
- ▶ 30:09 unnamed speaker Also, we've had illicit on the podcast.
How To Hire AI Engineers (ft. James Brady and Adam Wiggins of Elicit)
- ▶ 0:06 unnamed speaker Actually, this is the first one that we're doing around a guest post, and I'm very honored to have two of the authors of the post with me, James and Adam from Elysset. 6 times in the scene
- ▶ 10:11 Adam Wiggins And so you need to work with this medium, and the, I guess the nuanced, or the thing that came out of Elisa's experience that I thought was so interesting is quite a lot of working with that is things that come from distributed systems… 3 times in the scene
- ▶ 21:58 James Brady And, um, in our particular case inside of Elicit, we do have fallbacks for a number of kind of crucial functions where it's going to be very obvious if, very obvious if something has gone wrong, but we 2 times in the scene
- ▶ 24:06 unnamed speaker I'm curious because you guys have had experience working at both, you know, illicit, which is a smaller operation, and, and larger companies. 4 times in the scene
- ▶ 34:58 James Brady But from our perspective, as, uh, when we're building illicit, what we primarily care about is what can these models do? 4 times in the scene
- ▶ 39:56 unnamed speaker Uh, the first is elicits, um, ML reading list, which I, I, I found, uh, so delightful after, uh, talking with Andreas about it. 4 times in the scene
- ▶ 1:01:36 James Brady So, you know, that's not, not the only reason why people would want to join Elicit, but, uh, as an example of 2 times in the scene
- ▶ 1:04:55 James Brady We try to make the interview process that's illicit 2 times in the scene
Supervise the Process of AI Research — with Jungwon Byun and Andreas Stuhlmüller of Elicit
- ▶ 0:09 unnamed speaker Hey, and today we are back in the studio with Andreas and Jawan from Illicit. 5 times in the scene
- ▶ 8:20 Jungwon Byun And so a big part of how, then, like, how Elicit is built is,
- ▶ 9:04 unnamed speaker Do you mind if I, uh, because I think you're about to go into more modern art and illicit.
- ▶ 11:15 unnamed speaker What, what clicked, uh, for you to like move into Elicit and then we can cover that story too? 2 times in the scene
- ▶ 13:47 unnamed speaker So what's the history of what Elicit actually does as a product? 6 times in the scene
- ▶ 19:47 Jungwon Byun So the very first version of the list that actually wasn't even a research assistant, it was a, it was like a forecasting assistant.
- ▶ 27:28 Jungwon Byun When we launched this workflow, now that GPT four was available, um, basically we had, Alyssa was at a place where given a table of papers, we like, we have very tabular interfaces. 2 times in the scene
- ▶ 30:47 Andreas Stuhlmüller In, in illicit, if you run a query, it'll return papers to you, and then it will summarize each paper with respect to your query for you on the fly, and that's a, like, really important part of illicit because you, like, illicit does it so… 4 times in the scene
- ▶ 38:07 Jungwon Byun Three new workflows into illicit, but make illicit really generic to lots of workflows. 3 times in the scene
- ▶ 42:50 Jungwon Byun I really want, kind of, evaluation both from an interface perspective and from, like, a technical perspective and operation perspective to be a power, super power for illicit, because I think over time models will do more and more of the… 3 times in the scene
- ▶ 54:11 Jungwon Byun Yeah, I would say it's, they're just kind of different tasks right now, and the task that Elicit is mostly focused on is what do these papers say? 2 times in the scene
- ▶ 54:34 unnamed speaker Alright, this was, uh, we see a lot of, a lot of details, but just to zoom back out a little bit, what are maybe the most underrated features of Elicit, um, and what is one thing that maybe the users surprised you the most by, by using it? 5 times in the scene
- ▶ 58:30 unnamed speaker How do you think about these use cases and maybe how illicit can help drive more research?
- ▶ 1:02:44 Jungwon Byun Like illicit is not going to make any money if it's a bad product, if it doesn't actually help you discover truth and, and, and do research, research more rigorously. 3 times in the scene