Latent Space: The AI Engineer Podcast
00:30:36 · Shawn Wang, Jacob Lauritzen, Alessio Fanelli
[00:30:36] S1: Yeah. You call... You call it model arbitrage. Yeah. You have different favors. You you did some research on this where you were firmly anthropic at the start of the year. Yeah. Grok is improving a lot. Yeah. You wanna give an example of a model that wasn't ranked highly overall, but, like, you wanna shout it out as surprisingly good? [00:30:55] S0: Yeah. I think not overall good. Gemini, one of the early Geminis is, yeah, extremely good for certain types of transcription and speaker attribution. So we use that for trans... Transcription actually. [00:31:07] S1: Oh, so you have a [00:31:09] S2: Yeah. What you gonna transcribe? [00:31:09] S0: Like a granola? We don't have... We actually probably will build, like, a meeting thing Yeah. But this is just, like, talk to speech, speech to text, text to speech, just like in in any other app that has this. And we do actually also transcribe files. If you upload hearings or whatever, we'll then transcribe them, put them into text, and so we can do all of our analysis on it. ElevenLabs. ElevenLabs, for DPA reasons. Same thing as like the data processing agreement, I should say. So like, our data processing agreement has very few vendors on it. [00:31:37] S1: Yeah. You just need to keep [00:31:38] S0: it Exactly. Need to keep it super tight on where any data goes. And so
00:31:38 · Jacob Lauritzen, Shawn Wang, Alessio Fanelli
[00:31:38] S0: it Exactly. Need to keep it super tight on where any data goes. And so [00:31:43] S1: I think, no, that that is one of the benefits of, like, a Gemini and OpenAI where they're like, you you come to us, we have most of the things that you need, and that is actually very valuable. Even if it's like... It doesn't have to be, like, state of the art. It's always just, like, mostly good enough for all tasks Yep. Then who cares? [00:31:59] S0: Yep. Yeah. No. Absolutely. I should actually shout out also Microsoft's transcription model. They made one Transcribe? Yeah. Okay. It's great. [00:32:08] S1: Okay. [00:32:08] S0: It's better than the old Gemini. [00:32:10] S1: Yeah. Yeah. Yeah. They they they did some good results. I don't know... Don't even know. Like, I think, like, usually, all of them are, like, top two, top three, top four in terms of, like, the the arena scores, and that's good enough. [00:32:20] S0: Yeah. Exactly. And it's like, you have all the governance and it's super scalable, and it's like, then that's probably good [00:32:24] S2: enough. Yeah. I was gonna say, like, at this point, are pretty much the speech to text models, like, good enough to where you're like, oh, one word here or there, if it's off, [00:32:32] S1: that's No? [00:32:33] S0: No? No. [00:32:33] S1: For sure. Like, I've done this a lot.
00:32:33 · Shawn Wang, Jacob Lauritzen
[00:32:33] S1: For sure. Like, I've done this a lot. [00:32:35] S0: And particularly in legal, there's like some... We We had this thing where I think it's... I forget if it's like in Australia where there's like a certain name for like a person in court, and it would consistently prescribe it as condom. Oh. So there, yeah, there's certain things that you don't want there. [00:32:52] S1: Yeah. But... So usually you run an LLM layer on top of it, and then you you extract some keywords and then you run the transcription model again with the keywords. Like, this is kind of my my workflow so far. But, yeah, if you... If if you've just done this on any large scale, you will pick up tons and tons of transcription errors on any domain that is not, like, average day to day conversation. [00:33:12] S0: Yeah. Yeah. Absolutely. If there's any sort of jargon in there Yeah. It's gonna be tough. [00:33:18] S1: Yeah. Like, I think Whisper and Eleven Labs still transcribe cloud code as cloud code. Yeah. And, like, it's Yeah. I've I've actually had that already. Very common. Yeah. So so, like, that's that's how you know there's, like, a lot more to improve. Yeah. Absolutely. I do want to cover a little bit on the the agent product side. So we've covered a few of, like, the the top level stuff. Right? We've already named job tabular review. We named jobs intake. Yep. And you've you've got some other stuff that we haven't even touched on yet, but I just wanna cover the the big two. Let's call it like Yep. It... That is is that fair to say that they are the big two?
00:33:18 · Shawn Wang, Jacob Lauritzen, Alessio Fanelli
[00:33:18] S1: Yeah. Like, I think Whisper and Eleven Labs still transcribe cloud code as cloud code. Yeah. And, like, it's Yeah. I've I've actually had that already. Very common. Yeah. So so, like, that's that's how you know there's, like, a lot more to improve. Yeah. Absolutely. I do want to cover a little bit on the the agent product side. So we've covered a few of, like, the the top level stuff. Right? We've already named job tabular review. We named jobs intake. Yep. And you've you've got some other stuff that we haven't even touched on yet, but I just wanna cover the the big two. Let's call it like Yep. It... That is is that fair to say that they are the big two? [00:33:52] S0: Agent and Tabular Review? And our projects. Probably. Yeah. And our Word add in Okay. Is also something... Because that's... A lot of people work work inside of Word, so our Word add in is is a huge... And and Outlook add in also. [00:34:03] S1: Yeah. So I just wanna cover, like, the the big ones that everyone must know. Yep. So Tabular Review is basically, like, fan out of, like, a lot across each document. You can ask the same question across all all documents, select it on the table Yeah. And then work back and forth. And then Yep. A million is impressive. What's... Any other, like, engineering considerations or performance things? Or, like, what... What's hard about this? [00:34:24] S0: I feel [00:34:24] S1: like before we do [00:34:25] S2: that, can you just, like, walk through, like, what is a user experience for a lawyer? And then, like, actually, you wanna you use a tabular view? Yeah.
00:34:25 · Alessio Fanelli, Shawn Wang, Jacob Lauritzen
[00:34:25] S2: that, can you just, like, walk through, like, what is a user experience for a lawyer? And then, like, actually, you wanna you use a tabular view? Yeah. [00:34:31] S1: Yeah. Yeah. Like... [00:34:32] S2: So, like, what are they doing, like, with tabular review? Yep. And then we can go into that. [00:34:35] S0: Sure. Yeah. Yeah. So they... It's typically... I mean, a good example is just a due diligence, right, where it's like, we need to review all employment contracts, all supply contracts, all of whatever, and so employment contracts, you put 10,000 employment contracts in there, and [00:34:48] S2: then you Like, each cell is one employment contract?
00:34:48 · Alessio Fanelli, Jacob Lauritzen
[00:34:48] S2: then you Like, each cell is one employment contract? [00:34:51] S0: Each row is one employment contract. And then for cells, you ask questions, basically. So, like, the first question... The first... Sorry, per column. So the first column might be, what's the termination period? And then it's gonna, like, fill out for everyone. It's thirty days or whatever it is. And the next question is, like, is there an IP assignment clause or whatever? Next one is, like, how much, you know, how much do we have to pay them if we fire them? Or whatever it is, like, much are they getting paid? And then it's gonna fill out the entire thing. You can also just ask the agent to do this. Like, if you just drop 10,000 files into the agent and say, like, do a due diligence on this, it will spin up a tabular review and run all of them and wait for it to be done, and then analyze the results, and it can then highlight, like, red flags. Okay. This... The CEO is getting paid an outrageous amount, or there's, like, this weird bonus structure. Okay. Then, like, obviously, we need to look at that, and then the agent from that can draft a memo to send to the client, or it can just do the review and then have, you know, a lawyer, the user, just be like, okay, let's let's look at this. Here are the red flags. There's also collaboratives that you can comment on it for other people to look at, etcetera. [00:35:51] S2: And why do you choose that, like, spreadsheet format?