YouSaid · the spoken record

Alex Graveley

lines on the record
47
first
2023-03-30
most recent
2023-03-30
sittings or episodes
1
sources
podcast

Every line below is reproduced as it was said and linked to the record it came from. Nothing here is summarised or generated. Directory · Search · Corrections

  1. A great point. The crazy thing is that these things work at all, right? And not only that, but they scale and they improve a scale, right? Most things break at scale. Almost everything breaks at scale. And that's what you hire people to deal with. Every doubling, you usually, something breaks, you got to fix it. It's a pretty crazy thing to think of what kind of emergent properties might still be out there if we can get these things 10 times bigger. So I'm always in favor of people pushing those limits. It doesn't make sense. Even the best people can't explain what's going to happen when you go bigger. Built the large hadron collider for that reason, too, you know? We think maybe we'll find some stuff. These endeavors are valuable. And like, yeah, I'm grateful to be a Lactarian during

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  2. Definitely not intuitive. Yeah, I mean, I would say I have some intuition now and people that are, again, on that experience spectrum have some intuition. It's not intuitive. There's many kinds of different learners, and there's many kinds of different programmers, right? It takes a certain kind of programmer to be comfortable with this idea of like, I don't know what's going to work. Let me try some stuff. It turns out that's similar attributes to the web or product making, being able to test stuff, look at the right metrics, find the right metrics. Yeah, those are useful skills, I think, that are reusable. But the intuition and the tenacity that it takes to like, you know, this doesn't work at all. What do I do? That's still rare, I think, in that field because there's so much uncertainty that it's easy to go like, I tried 10 things and it didn't work. So like, this is impossible. Like, okay.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  3. It's not an age thing. It's more like you tell someone who's very naive and you tell someone who's very experienced, I can make magic. Here's how I can do it. And then the very naive person is like, that's awesome. And then the very experienced person is like, ah, maybe. You know But the response from almost everybody else is that's not possible. Or I don't see it. But yeah.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  4. Yeah, it's been strange. It seems very bimodal, like very senior people get it, and very young people get it. And so I don't know that the middle has really caught up yet or realizes that.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  5. Don't usually write code to do their taxes, but sometimes it's kind of the same thing. You go through a list of your pay stubs. That's executing a for loop. Also, I like data sets that don't exist. So people clicking on stuff on the web is a gigantic data set, which is currently unowned. And so I think that's pretty exciting. I think there's a lot of stuff to learn from that.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  6. You say, hey, computer, file my taxes, and it does the right thing. And I think we can get there. Certainly, in the next few years, but it's also fun to think about how to break these things down. And it turns out breaking down tasks in the same way that humans do take a complex task. You figure out, you know, you write a list of things to go through it. Same kind of thing works for AIs as well. So you break down complex tasks, you figure out if there's any information you need. And maybe you have to write some code. Maybe you have to ask some questions. Maybe you have to query some data. Same thing a human do.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  7. This one's hard, yeah. It's getting hard, I think. Part of that is, they're these fun things you kind of learn along the way that keep you like engaged, right? Like the thing with code with copilot is like it turns out code is pretty special, right? Like you can run it. So if an AI generates some code and it runs, then you know something about that code that you wouldn't know necessarily the text. And accomplish like doing agent-like work on the internet or on apps has a lot of these similar kind of properties where it's like, oh yeah, you can learn something here. We can learn what we can learn from what people do or we can see if it's a success or a failure and then learn from that or we can optimize what works based on what doesn't work or figure out what's annoying and try to improve it. So I think these things all compound in some really interesting way. The goal, right, is straight out of sci-fi, right? You want to make a thing where

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  8. That's what we want. Let's go make it. I don't know. It's like maybe I can use the excitement from co-pilot to launch into something which is incredibly hard, but which I believe the technology is around for if we can figure it out. So yeah, that's it. That's the only reason I've ever gotten to startups actually is like, okay, I want to do a startup so that I can do a harder startup. Or I want to do a project so I can do a harder project.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  9. So basically I stopped working at Magic. I quit because I couldn't figure out how to hook up the AI to data. I was like, in order to improve the quality, I need a PhD in math. Like, I don't know what to do now. And it just sort of, the models got better enough where that specific problem seems solvable. Yeah, so the tech got better. And so that specific problem is where interacting with the real world broke down in the past. You know, like I said, floods get delayed, prices change, not just like a little bit all the time. They might not have the seat you want at the concert that you want to go to. And so, you know, AIs are this kind of compression of everything that in their training set, but they're not a real-time mechanism. Anyway, so that was the idea. It was like, okay, well, I think we can work on this old problem of how to make a bot do stuff for people.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  10. Doing my taxes or telling me which contacts I haven't talked to in a long time, I should reach out to, you know. There's a lot of stuff that we can do by giving AIs access to information and letting them act on that information in a controlled way that checks to make sure that we're aligned. And yeah, I think that'll be a really fun feature. Almost like you can imagine co-pilot 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 outside of your code editor.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  11. I think I mentioned making bots that do stuff for you. It's a broad topic. And I think it's where we see going. You know, the next few years are in AI's taking action, not just answering questions or writing copy, but actually helping us in our daily lives. Things like organizing my schedule or booking flights or finding a trip for me to take or

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  12. Yeah, I think every if that's the goal we want to get to as people, like I think every barrier to that is achievable. So we can code review only the dangerous parts or only the confusing parts or we can do things like train a model on functions before and after changes to say like, okay, this looks like a more polished version of this function would be this. Or yeah, we can do things like just start the very basic main loop and then add everything piece by piece with tests so that it's what works and what doesn't and then just have the I keep generating what's the logical next feature. All these things will get figured out. So if that's what we want to do, that's what's going to happen.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  13. Yeah, it's hard. I don't know. I think it's hard for me to, you know, it's hard for me to imagine with what that world looks like because it's such a shift from like, I have my hands on something and I know that it's right to where we are now, which is I mostly know it's right or I have a sense that it's right, but I have to test it and see it run to know that it's right to then just write this and I'll trust that it's going to work. Like those are pretty crazy transitions, right? Yeah. They exist

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  14. Oh, yeah, estimates were wildly off. Wildly off. Yeah. So we got estimates that were like, you know, it'll be $30 a month for on average, right? And then once Microsoft was able to like do some kind of do their Azure infrastructure, we were able to then fork off little bits so we could do more accurate projections. And there was a bunch of like moments where like, how much is it going to cost? You'd like wait for these results. The first big one was 10 bucks a month. It'll cost 10 bucks a month. And I was like, oh my God, it's so much cheaper than we expected. And then we optimize it. And that was like, we hadn't even optimized on price yet. And then we optimized on price a bunch. And yeah, now it's less than that. So like it was very fortuitous, right? Like we were thinking like, okay, well, maybe it's enterprise only because that's the only people who are going to be willing to pay for this.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  15. No, I mean, our retention rate was 50%. It never went months later. It was still above 50% by weekly cohort, which is like insane. And we didn't know if people would pay for it. That was one thing. I lobbied pretty hard for going cheap and capturing the market.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  16. We need you to do that in the next month. So, can we let's figure out how to make this happen? So, because we wanted to run a bunch of GPUs in Europe so we could hit Asia. You know, there was no other place that we could run them in Europe. We could run them on West Coast, we could run them in Texas at the time. So Microsoft stepped up there. We got it running. And then pretty much after that, we launched. And

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  17. Yeah, it turns out these models are really great at finding patterns. So once we have the UI mechanism that worked, so we knew on something like that. And then it was just this like wheezing as much performance as we could get out. We basically never found the bottom of we made as fast as we could and it was still improving on completions. And then that perpetuated like, okay, okay. I know there's this plan for Azure to run OpenAI in six months.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  18. Yeah, and so once we figured that out, we knew that we had something awesome, right? Like people that were close to Texas were like, this is freaking great. We had a Slack channel and people were posting it all the time. And the most fun stuff was like these people that would pop up and be like, I don't program, but I just like learned how to write this 100-line script that like does this thing that I need. It's like, oh my God.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  19. Yeah, and it turns out because OpenAI only had one data center, so it was all in Texas. And so it was going, if you can imagine, you're like typing. And so that goes from India through Europe over the water down to Texas and back and back and back. And now if you've typed something that doesn't match the thing that you requested, then that's useless. So you don't get a completion.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  20. Yeah, there was, I mean, we had a nice long window of public access before GA, so where it was free and you could use it, and we did a bunch of optimizing for different groups of people that would be, okay, well, do we want more experienced people? Do we want more new people? We want people from this area or this area. And that gave us a bunch of really good stats. So we were able to learn that, for instance, speed is the only thing that matters. Yeah, there's something crazy thing. Like every 10 milliseconds is 1% fewer completions that people would do. That adds up. 10 milliseconds is pretty fast. We learned that because somewhere in our first few months of public release, we noticed that Indian completions were really low. Like for whatever reason, they were just significantly lower than Europe.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  21. A little complicated. I guess we were pretty much a skunk works project. No one knew about us. So we would go to like the, we'd go to VS Code people, be like, hey, we need you to go implement this very complex feature. We're like, I don't even know who you are. Like, what are you talking about? There was definitely some politicking that happened to get the VS Code people 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 launch.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  22. DSCO didn't support this, so I tried to hack it in and finally came up with a way to hack it in, enough to make a demo, like a little demo video.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  23. Yeah, none of them really worked. I think lists were maybe you'd get one generation per person per day. And this was just a small sample. It's just like a few people that were interested in GitHub, language nerds or people that have written tests for us and open AI people. Yeah, so very early on I had this idea that it should work like a Gmail graytext autocomplete, which was like enamored with that product. It's like it was the first quote unquote large language model deployment in the wild. It was fast. It was cool. Like the paper's great. They give you all sorts of details on how they do it. All the workarounds they had to do. So that was always in the back of my head, you know. It was bad also. It was like those completions are not good. But it seemed like the right thing. Anyway, somewhere along the way after we tried all the UI, you know, sort of come up with some idea for.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  24. It would show this little pop up box like Autocomplete does, and you could pick some strings. And so that format actually, you know, the usage was fine. It wasn't the right metaphor exactly, right? But you've got like this code generated and mixed in with the specific terms that are in the code. And it's a little, it's not exactly the same thing. We tried things like adding a little button over top of empty functions. It would go generate them. Or you could hit a control key and it would create a big list on the side you can choose from or there's a little pop-up thing. So basically trying every single UI we could think of in VS Code.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  25. The first iteration was just like an internal tool that helped people write these tests. And then we wanted to see if maybe we could turn that into some UI that people would use. If there was some way to cover up the fact that one in 10 things pass, right? So we've tried a few UI things there. And then it was actually OpenAI that was like, it would be nice if we could, we're testing these model fine tunes. It'd be nice if we could test them more quickly. What about doing a VS Code extension? Just do autocomplete. All right, sure, why not? And yeah, so we did autocomplete at first, and that was kind of, that was a big jump, you know, because there were still thinking in terms of like stack overflow, you know. But this was, it's like, you know, I didn't have any ideas basically. I didn't know how to beat stack overflow with this thing. But we could play with some stuff in VS Code that was maybe close to the code. First we did autocomplete and that was kind of fun. It was useful.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  26. Yeah, yeah, yeah, yeah. That was more like if you made something compete with Stack Overflow because we have all this code, wouldn't it be nice to leverage it? Yeah. And so we made some UIs, but early on, you know, it was like early on is bad. So it would be like you'd watch it and it would run and most of them would be bad. It'd be like 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.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  27. So that's like one in two tests. It can just generate code for, which is insane, right? Somewhere along the way, you know, there was like 10% to 20% to 35% to 45%, you know, these kind of like improvements along the way, somewhere along the way. We did more prompting work so that the prompts got better. Somewhere along the way, they used all the versions of the code as opposed to just the most recent version. They used diffs so that it could understand small changes. Yeah, just it got better. But when we first started, we were just, we didn't know what we had. We were just trying to figure it out. At the time, they were thinking in terms of like, maybe you can replace that overflow or something, you know, do a stack overflow competitor.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  28. Dimensions are kind of like how many chances do you give it to solve something? And then how do you test whether it's worked or not, right? So for the standalone tests, that was, we had people write test functions and then we would try to generate the body. And if the test passed, then you know it works. And in the wild test harness, we would download a repository, run all the tests, look at the ones that passed, find the functions that they called, make sure that they weren't trivial, generate the bodies for them, rerun the test, see what it passed, see it, and you get your percentage. Yeah, I mean, it was something like some very, very low percentage up front, but we knew that there was kind of a lot more juice to squeeze. So like getting all of GitHub's code into the model, and then a bunch of other tricks that we hadn't, you know, we hadn't even thought of at that time. Yeah, and eventually, you know, it went from less than 10% on in the wild test to over 60%.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  29. Something. It was only Python at that time. Here it is, you know, generating something useful. We didn't really understand anything. So that was enough to like, okay, well, go fetch a couple of people and start working, see if there's anything there. We didn't really know what we had. So the first task was to go test it out, see what it did. We crowdsourced a bunch of Python problems in-house, stuff that we knew wouldn't be in the training set. And then we started work on fetching repositories and finding the tests in them so that we could basically generate functions that were being tested and see if the tests still pass. There had been like a brand new pie test feature introduced recently that allowed you to see which functions were called by the py test. So you'll find that function zero body ask the model to generate it and then rerun the test and see if it passed. And I think it was less, I don't know, 10%, something like that of those guys.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  30. I have to remember now. I think this is before I knew very much. So it was definitely not a DaVinci size model, it's for sure. I don't know what size it was. Yeah. And so it was just like, I learned later that this was basically a training artifact. So they had wanted to see what introducing code into their base models would do. I think it had positive effects on chain of thought reasoning. Code is kind of linear. you can imagine that you know you kind of do stuff one after another and the things before have an impact And yeah, I was not that good. It was very bad. It was, I think, just, like I said, just an artifact and a small sample of GitHub data that they had crawled. And this was before actually I joined me and this guy Albert Ziegler were the first two after Uge. Uge got a hold of this model and started playing with it. And he was able to say like, oh, you know, like it doesn't work most of the time, but here it is doing.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  31. So, I don't know the exact beginnings. I know that OpenAI and Microsoft were working on a deal for supercomputers. So we 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 Bang probably. And GitHub was like, oh, well, okay, well, maybe there's something GitHub can do here. Think OpenAI threw a small fine-tune over and was like, here's a small model trained on some code, see if this is interesting. So we played around with it.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  32. To build GitHub, which is kind of fun. They weren't, yeah. I think people still use code spaces now to build GitHub, which is pretty cool. But yeah, then this kind of opportunity to work with OpenAI came up. And because I had been tracking AI in the past and was pretty aware of what was going on, I jumped on it.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  33. While I was working on mobilecoin, my dad's kidneys failed and I tried to donate a kidney, they found a lump in my chest as part of the scans they do. And I had to have my most of my right lung removed in 2018. And so that was a big deal. And so took some time. It's weird healing from internal injuries takes a lot longer than you think. Anyway, happy story is that I don't cancer now for over four years and in my dad's kidney's got a transplant also, so things are good. And so after, I don't know. I guess I was recovering for quite a while. And then I went and begged my friend for a job. I figured I should start working again. That was the transition, I guess. So I worked on some random stuff at first. I converted GitHub to using their own product.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  34. Yeah, I think it's interesting. I guess I would say it's not somewhere in the middle. It's like imagine there's, North Korea has been trying to do this to us for a long time, right? Now there's a North Korea that has more resources or is more distributed or whatever. We have some mitigations. We need more. We need to be thinking about it a lot more.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  35. Yeah, it's a great way to look at it. It's not as bad as it could be, right? If you think about it, most of the things that you want to spam either have a spam blocker or are somewhat difficult to create an account on. So doing a better job of SockPuppet account filtering is going to be really important going forward. I like what Cloudflare is doing with their kind of fingerprinting instead of visual captures, which are not good enough anymore. One thing that is kind of a saving grace here is that many of the things that you would want to do cost money. So calling everybody costs money, texting everyone should be hopefully illegal soon, but also costs money. Maybe not enough money to prevent these things.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  36. It's a good question. The honest answer is I think we're going to go through a many year period of extreme discomfort where AIs pretend to be things or confuse people or extract money from your grandparents or drain people's life savings in ways that are scary. And OpenAI is trying to do their best, but for some reason the focus has been on open AI doing everything. And instead of like we should go build the systems that prevent that, we should go pass the legislation that drops the hammer on people doing that stuff. We should go all this kind of stuff that is unfortunately it seems like we're going to need some really bad things to happen before we align correctly. I'm not really scared about AI's killing us, although I'm very grateful that there are people that are thinking about it. I'm more worried about bad people using new technology to hurt us.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  37. Oh, yeah, there's a bunch of other stuff along with it. So after that, I got into crypto. My friend was doing HCAPCHA, which was sort of a capture marketplace, which is now something like the number one or number two Capscha service in the world, which is crazy. So kind of launched that. That was fun. Annoyed people the world over for many, many man hours in aggregate. And then left that to work with Moxie on a cryptocurrency for Signal. So that was really fun, complicated, and it all worked in a few seconds. We were shooting for Venmo quality.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  38. The operators. And yeah, we would measure how much time they spent typing with it and without it. across 100 people per day across an eight hour shift. So yeah, that was like my first shipping AI product.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  39. What we were able to do with magic as an aside there, you know, I started working there because I wanted to work on the AI part. I think somewhere in there, Facebook M started as well. And it was just a fun place to try and learn everything I could about solving those problems. So yeah, before Transformers, there was a sequence to sequence was kind of the previous iteration. We were able to like take all the histories of the chats between assistants and people. Little by today's metrics and run it, and it would show some gray text in the little text bar and people could edit it and hit enter.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  40. 99 mark and then change the goal entirely. Yeah, so it's complicated, it's hard to understand what people want. It's hard to understand the complexity involved, especially when you're dealing with the real world. Flights get delayed. Passwords get lost.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  41. Yeah, yeah, yeah. No, yeah. I haven't seen a demo yet, but it seems like they're doing the right thing. There's a few people doing that kind of whole repository changes. So it seems like a great direction. It was all ops-based. It was super heavy op space. So, you know, they had teams of people and it was 24 hours and they would cycle in and they would lose context. And like they were all busy because they're trying to deal with lots of people with lots of requests all the time. And so really it was like a crash course in like human behavior, right? Like what do people do under stress? How do they act? What do they say? What can you train? What can't you train? Like can you bucket stuff? And the answer is no. Like humans are complicated, especially in text one. The beauty of the web and like traditional UIs, right, is that you fill them in. And like if it doesn't do what you want, then you make the decision to either go forward or not go forward, right? Text has this annoying property of you can be all the way at the

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  42. Spent the next few years kind of poking around at stuff. I knew that I wanted to make a robot that does stuff for you. So there's a company called Magic. So I went and worked at this company called Magic. They were doing this text-based personal assistance.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  43. Oh, yeah, it was a real time text editor, kind of like Google Docs. Google Docs is the only other one that did that at that time. It was kind of nice because it would highlight who said what. So you could go track down if somebody had a contribution, be like, oh, what did you mean? Or I heard you say something about this. So that's very useful in large scale anonymous pseudo-anonymous groups where you don't really know who has ownership over what like Burning Man camps. And let's see. And then we did YC and then we got a bunch almost many of those people did it at my like my hack was to go do YC and try and get all the companies doing YC to use my product which many of them did. I also took like very extensive notes of all the YC presentations using the product that everyone would then like look at and we were able to get Stripe and Stripe used us for many years actually. They built for the I think we were their first knowledge base, they used it for a long time.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  44. It's like a rite of passage. Yeah. So I spent, I don't know, nine months working on that. Turns out education is very hard. So after nine months, I was like, all right, this isn't going anywhere. I don't know if there's a value prop here. I mean, that was the value is that I learned that you have to make something that is both achievable and that people want to pay for or spend their time on. So yeah, then I was just kind of fishing around. I was living in like a warehouse in San Francisco, a bunch of Burning Man people. And we were having trouble organizing large-scale Burning Man projects. And so I forked Etherpad and started hacking on it, recruited a friend in the community to start working out with me. And yeah, just grew from there. Before we did YC, we had many of the large Burning Man camps using it to organize their builds.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  45. Oh, Hackpad. Yeah. So I had just finished like four or five years at VMware. And I wanted to get into startups. I knew that. And then so I left VMware and I started working on an education startup like many of us do. Many, many founders start with like the idea of an education startup

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  46. Tech was earlier. I started, you know, really young, and I got really into Linux when I was 14 or so. It was right around the time when the web was like a new thing and you had to work to kind of get on the web. The idea of helping in the open and making it freely available so other people could learn from things. Like I was learning from things seemed great. So I went and spent many years just working on open source stuff. Yeah, spent many hours compiling kernels and hacking on stuff. And yeah

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source

  47. The most fun stuff was people that would pop up and be like, I don't program, but I just learned how to write this 100-line script that does this thing that I need. It's like, oh my God.

    2023-03-30 · No Priors · What’s Beyond GitHub Copilot? With Copilot's Chief Architect and founder of Minion.AI Alex Graveley · IDENTIFIED FROM THE TRANSCRIPT · source