Transcript: So I had a morning of watching Andrej Karpathy's videos on neural nets and just trying to get a better understanding of how they work, how backprop works in code, as well as how do you implement transformer-based neural networks. Still don't have a fantastic idea. I will need to spend more time specifically on his transformer video. I started skipping through it halfway. I have some conceptual understanding, I think, but it's still quite bad. So that's how I spent my morning. I did not eat breakfast. I did have coffee. And I am going to go to Costco now. And I also had a call with Austin, which was really nice, and he was checking in on me on the project. I really, really appreciate that. So I think I'm going to go to Costco and probably go get lunch somewhere. I don't know where yet, but yeah, that's kind of my plan. Dinner, I think I have salmon that I'll probably have today. Or I'll cook a steak. Not sure. But we'll kind of take that as it comes, I guess, and go from there.
Today involved watching the Super Bowl, feeling disappointed about the 49ers' loss, and preparing meals including steak for dinner with more food like ramen and salmon for the coming days. Personal achievements included some work on a spreadsheet project and watching educational videos by Andrej Karpathy. Despite also updating the main burrito.place website, feelings of underachievement persist due to slow progress on a project and unresolved uncertainties. Plans for tomorrow include surfing at Swammy's and confronting the aforementioned uncertainties.
Today has been a challenging day, with the speaker feeling overwhelmed by logistical tasks like taxes and job inquiries. They had a productive conversation with Danny but were left feeling aware of the amount of work ahead. They are also pondering ways to make money and considering the potential of experimenting with data and language models. The speaker is interested in the concept of "brain twin" and is curious about using it in a group setting with others, possibly collaborating with someone named John.
Today was eventful with a pleasant dinner party I hosted for Caroline, Patrick, and Kyle, reuniting this group for the first time in two years. The evening was filled with meaningful conversations, vulnerability, and appreciation for the company. I also visited Nick to help with their business spreadsheets, exploring potential additional income. Tomorrow's plans include a bike ride to Mnemonic to spend time writing and reflecting on recent discussions, fueled by energy and an espresso.
I have a busy day planned, including sending off a package to the AI grant and hoping to meditate, write, and position my work effectively by the afternoon. Although I'm feeling very tired now, my plan includes getting up at 6:30 am, having breakfast and coffee, and possibly slacklining in the mid-afternoon. I'm still determining the right direction for the AI grant, as I'm trying to build a platform that needs killer apps to succeed. I'll explore positioning it as software tooling and developer tooling in open source to find a resonant and useful framing.
The text is too short to summarize.
The speaker did not complete their weekly review, which usually provides clarity and insights for the upcoming week. Despite this, they have many projects, personal life commitments, and community efforts to attend to, not to mention taxes. They plan to set week intentions using voice instead of writing, including the exploration of websites for the Diagram Website Explorers Club and developing a Canvas element-based editor for Daily Jam. The technical aspects of this project involve real-time data updates, efficient pixel manipulation, and secure user authentication through tokenization. A function is set to run every five seconds to update the canvas with the latest pixel data, ensuring all viewers see a consistent image while minimizing performance impacts. Other tasks include preparing tax paperwork, organizing Boulder events for systems and AI, and sketching ideas for a project called "co-net." The intention is to spend more time outdoors in the nice weather and to schedule the next "Site Craft Hang," while thinking about potential content for the "Explorers Club" website. Overall, it's a productive Monday morning with good weather contributing to a positive start to the week.
After a hike, I encountered Steph, leading to ongoing communication about hosting events. We discussed her co-organized salon on the AI alignment problem in March and my interest in hosting a website-building event during startup week, potentially in April or May. We also contemplated a tool for managing our projects and events, like a specialized project management software. Further, we talked about the connection between online communities and the physical gatherings they can inspire, emphasizing the cyclical relationship between the two.
The speaker describes their experience of partially understanding a podcast, particularly a term "Socratic search space," while on a walk and expresses a desire to delve deeper into its meaning. They prefer an interactive approach where they can ask a device to provide references and contextual explanations, as opposed to receiving a summary generated by an AI model like GPT, which might lack the most recent uses of the term. They are skeptical about the capability of language models to provide a comprehensive understanding, given that they might not recognize terms with minimal occurrences in training data. The speaker envisions a system that could compile and present relevant information in a coherent way, enhancing their grasp of the podcast's content and making the learning process more meaningful.
The speaker is reflecting on their experience with making audio burrito posts, noting that it often requires multiple attempts to get into the correct mindset—similar to drafting written posts. They're grappling with the challenge of monologuing without a clear understanding of the audience, as they are aware that at least John and CJ will hear it, but uncertainty about the wider audience affects their ability to communicate effectively. This creates a 'contextual membrane shakiness' as the speaker finds the lack of audience boundaries difficult to navigate, which they recognize may vary among different people. The speaker concludes by deciding to end the current note and start a new one.
The speaker reflects on the idea of returning to school and studying cognitive science, an interdisciplinary field that blends various subjects like philosophy, neuroscience, and computer science, which they discovered through a coworker. They had initially studied science at the community college level, pursuing general education before dropping out and working in software, where they learned skills not directly relevant to web app development. Although not currently planning to go back to school, they find the concept of cognitive science fascinating due to its relevance to understanding the human brain and AI, with potential implications for the future. If circumstances allowed, such as affordable tuition and the ability to learn without financial pressure, the speaker would be excited to pursue cognitive science for its practical and forward-looking applications in technology and understanding human cognition. The speaker is explaining how certain things influence their approach to designing systems and living their life, especially in relation to interacting with artificial intelligence. These influences are significant enough to capture their attention, hence the phrase "that's why that calls my name." They imply a deep connection or interest in the impact of these factors on their work and personal life. This perspective helps to inform their design decisions and overall interaction with AI technology.