Transcript: What I just spoke about is effectively an aspiration. I was writing in my journal earlier about what communities do I want to be part of, and I guess that is one of the ones that I want to be part of. And being able to participate in that space as deeply as I can, I guess that's something that I'm very interested in at the moment, and I'm willing to push forward and potentially take a job doing that as well, because I think it's important. And I think building great tools for individuals and empowering individuals to play and explore their data and bring it back to themselves is something very much worth doing, because I think it's worth it for myself. I don't know what I am yet to discover, but I am sure I am going to discover something. And to aid in more people's discoveries, that excites me. It excites me in the same way that I'm excited to ask questions over my data, and even these things that I'm saying, it seems like with the power of the large language model and these little modules and plugins and making good ones for people by default, I just suspect that it's going to be really useful. And I could be entirely wrong, but I need to build the mini playground and try to make it happen and see what's possible from there. And I think that's kind of the guiding principle now, more or less, which is, well, start getting some of this recorded data in, see what we can switch off of OpenAI, see what models perform like what. And yeah, I mean, more or less, I think that's kind of the way. So yeah, I mean, we'll just take a run at it and kind of see how it goes. And as long as I can build tooling for myself to make it easy, you know, that's where we'll get to. But I think getting that web page up and literally just having a piece of data and some metadata in front of me and being able to work with it and being able to do some of that directly on the page, it doesn't even need to be saved to the file, being able to just work with it and manipulate it on the page, I suspect is going to be extremely useful. Again, how all of this is stored and logged and everything, I don't know yet. But I think that's more or less the direction for tomorrow is, well, really the rest of the week is just getting this onto a page and probably doing it from a third party application. I don't know yet. All I know is I'm probably going to hit the limit with BUN in terms of statically rendering things. So I want to move to a more reactive front end. And because of that, I will probably end up using Next.js and React to do that and a bunch of client components. I'll keep as much as I can on the server and keep it really simple. I'm going to keep it really, really simple and use BUN to run it, but that's going to be the goal. And yeah, just make a little tiny playground for myself. Probably a feed to begin with. I mean, we'll see. We'll see how much I can get away with. I don't know how this is going to work yet. I want to query it ideally all by natural language. So we will see what we can get out of it as a result of that. Don't know how much GPT this is going to need, or maybe I can just run something with JSON grammar and have it output me exactly what I want. But if we get there by the end of the week, that'll be a pretty satisfying end point. I think the pipeline is in good enough shape. We have pretty good audio going in. I think we need to make sure embeddings are making their way into the embedding space. But really, it's just going to be about getting the data in and then starting to play with it in one way or the other. That's going to be, yeah, I think playing with it is going to be the next step. Building. Building the playground. We have, we have the sand. Now let's build the playground. That's what needs to be done. Setting up the first set of monkey bars. And seeing how it is, it's probably going to be janky and rusty and crappy, but, you know, it'll be fun until it hurts someone. And we'll learn from that mistake and make it better. And, I guess, hopefully it doesn't hurt someone. That's the goal. Oh boy, here we go. Time to go to sleep.
89.78% similar
I'm making good progress on the AI grant application, with both the longer description and one-sentence summary feeling satisfactorily crafted. Despite some reservations, the video I've made is likely sufficient, and with most steps completed, I'm now moving onto the demo, aiming to showcase everything in a concise three-minute presentation. This will highlight one personal frame through which to view data, particularly emphasizing social connections and convenience in planning. My ultimate goal is to demonstrate the simplicity of asking a question to retrieve information and to focus on the two key APIs, store and query, to power the application. Focus around these two queries, as with them, essentially any application can be constructed.
89.48% similar
The speaker is excited about tomorrow but acknowledges that as a developer facing new challenges, the work is not trivial, especially given the lack of extensive documentation and the solitary nature of their current work process. They express a desire to share their learnings, possibly by writing them down, and emphasize the importance of collaboration, suggesting that "if we do this together, it will be a better world." The speaker is tired of creating misleadingly impressive demos and aims to write code and interact with large language models in a more genuine and transparent way. Lastly, they recognize the complexity of building an effective agential system, admitting their current limitations while believing in its importance, and they present open questions about processing and connecting large amounts of data to better understand who we are.
I've successfully published my work, which was an arduous yet rewarding process. On reflection, I realize I want to express myself authentically in my own voice, while also considering the need to help others understand my perspective. Looking ahead, I plan to maintain a regular output, potentially alternating days, to keep the stream of content going. In parallel, I'm excited to start developing new projects, including making my work easily accessible to others and laying the groundwork for a decentralized social network that supports various types of media.
The realization of the value in this application lies in its ability to perform searches quickly, efficiently, and accurately. There are multiple approaches to enhance its functionality, with a focus on both data storage and the improvement of search capabilities, which is currently the most critical yet challenging aspect. Concerns exist about the app's method of aggregating all processed data, which feels inherently flawed, though it's being temporarily accepted for the valuable data it provides. This tension between a recognized need for development against the reluctance to proceed with an imperfect solution underscores the complexity of the problem at hand.
Feeling exhausted but content, the speaker reflects on their constant work and aspirations to improve processes, like making John's burrito preparation faster. They acknowledge that their current project may have flaws, but see potential for it to be a dynamic back-end platform with multiple uses. The speaker expresses a desire to create something novel and valuable, while also fostering a space for both public and private sharing. Amidst these professional goals, they cherish personal connections, such as a satisfying morning of surfing with friends.