Every argument clarity score on this site is built from rows on this page. Each
question and answer was assessed with names hidden, the host's own answers included, on
four things from 1 to 5:
directness (does it answer the question asked), coherence (do the ideas follow),
precision (concrete details and clear references), compression (says a lot per word). The weighted
mix (30/30/25/15) is the exchange score. A person's published score averages their exchange
scores on raw tape only, at least 8 of them, shrunk toward the cohort mean.
Full method →
Answered raw tape
D 5 · C 5 · P 4 · Cm 4 4.60
Q So what's the, what's the idea behind Minion?
A Yeah, I think I mentioned, uh, making bots that do stuff for you. It's a, um, broad topic, and, um, I think that's where we see it going. You know, the next few years are, are, um, in the eyes taking action, not just, uh, answering questions or, um, writing copy. But actually, um, helping us in our daily lives. Um, things like, um, organizing my schedule, or booking flights, or finding a trip for me to take, or, uh, doing my taxes, or, um, uh, telling me which contacts I haven't talked to in a long time and should reach out to, you know. Um, there's a lot of stuff that we can do by giving Uh, AI's access to information and letting them act on that information in a controlled way that, um, checks to make sure that we're, that we're aligned. And yeah, I think that'll be a really fun feature. I think, you know, almost like you can imagine Copilot applied to everyday activities, right? Like Copilot gives you a little bit of help. So I want Minion to give you a little bit of help, uh, outside of your code editor.
AI assessment note: “making bots that do stuff for you... Copilot applied to everyday activities”
Answered raw tape
D 5 · C 4 · P 4 · Cm 4 4.30
Q Was that proposed by OpenAI or by GitHub or who kind of initiated it all?
A So I don't know the exact skittings. I know that, uh, OpenAI and Microsoft were working on a deal for supercomputers. Um, so they wanted to build a big cluster for training and there was a big deal that was being worked out and there was some software kind of provisions thrown in, I think Office and Bing probably. And GitHub was like, oh, okay, well, maybe we can, let's like, uh, let's, um, Maybe there's something GitHub can do here. Uh, I think OpenAI threw a small, threw a small fine-tune over and was like, here's a, here's a small model trained on, um, on some code, see if this is interesting, you know. So we played around with it, and...
AI assessment note: “I think OpenAI threw a small, threw a small fine-tune over”
Answered raw tape
D 5 · C 4 · P 4 · Cm 4 4.30
Q And, uh, Was there support to, like, build real support for it within the organization?
A It's a little complicated. I, I guess, you know, we were pretty much a Skunkworks project, so no one really knew You know, no one knew about us. So we would go to like the, if you go to VS Code people and be like, Hey, we need you to go implement this very complex feature. Like, I don't even know who you are. Like, what are you talking about? Um, and, uh, yeah, there was, there was definitely some politicking that happened to, to get the VS Code people to, um, to dedicate some resources to that on a short, short timeframe. Like we were moving really fast, you know, it was less than a year before from beginning to ship public, public, public launch.
AI assessment note: “there was definitely some politicking that happened to, to get the VS Code people”
Answered raw tape
D 4 · C 4 · P 4 · Cm 4 4.00
Q Was there a certain, um, metric where you're like, this is good enough, like we need to actually put it in the public product?
A Yeah, there was, I mean, we had a long, we had a nice long window of public access before GA. So where it was free and you could use it and, um, and we did a bunch of optimizing for different groups of people that would be, you know, okay, well, you know, do we want more experienced people? Do we want more new people? Um, who want people from this area or this area? And, uh, um, that gave us a bunch of really good stats. So we were able to learn that, for instance, like, Uh, speed is the only thing that matters. Um, so, uh, yeah, there's something crazy thing. Like every 10 milliseconds is one percent fewer completions that people would do. That adds up. 10 milliseconds is pretty fast. Uh, we learned that because, uh, somewhere in our first few months of public release, we noticed that Indian completions were really low. Like the, for whatever reason, they were just significantly lower than, than Europe.
AI assessment note: “every 10 milliseconds is one percent fewer completions that people would do.”
Answered raw tape
D 4 · C 4 · P 3 · Cm 3 3.60
Q Um, Was that the first like product idea you guys had for it?
A I don't know that we had that idea. I think that was kind of like, uh, Beyond High idea. Yeah, yeah, yeah. That was more like, uh, um, It'd be nice, you know, be nice if you could make something that competed with Stack Overflow because we have all this code. Wouldn't it be nice to leverage it? Um, yeah. And so we made some UIs, but like early on, you know, it was like, early on it was bad. So it'd be like, you'd watch it and it, it would run and most of them would be bad and be like, and there'd be like one success and be like, oh, sweet. I got a success, but I had to wait, you know, some number of seconds for success.
AI assessment note: “I don't know that we had that idea. I think that was kind of like”
Partly raw tape
D 2 · C 4 · P 4 · Cm 4 3.40
Q And then how'd you end up going to, um, Microsoft?
A Oh, there was a bunch of other, yeah, there was a bunch of other stuff along with. There was, um, so after that I did, uh, Uh, I got into crypto. Uh, my friend was doing H captcha, which, uh, was like, uh, sort of a captcha marketplace, which is now like something like the number one or number two captcha service in the world, which is crazy. Yeah. So kind of launched that. That was fun. Uh, you know, annoyed people the world over for many, many man hours in aggregate, and then worked on, uh, left that to work with Uh, Moxie on, on a cryptocurrency for Signal. Um, so that was really fun, um, complicated, and it all worked in a few seconds. Um, so, you know, we were shooting for Venmo quality, which I think pretty much it.
AI assessment note: “Oh, there was a bunch of other, yeah, there was a bunch of other stuff”
