Transcript: I'm just using about what burrito place or whatever this thing is might, how it might show up in a daily context. So maybe this is kind of like a design fiction if we were to tag this entry with something. But anyway, I just picked up a podcast interview from my YouTube queue and I'm going through watching it, listening to it mostly since I'm on a walk and it's, it's good. Like there's, there's good stuff being said, but I feel like I'm only grasping maybe 40% of the stuff that I'm hearing like Socratic search space, like, well, what does that mean? I want to understand that better. I want to understand, and this is a genre of APM, I think Daniel, no, um, yeah, I'm thinking, yeah, so forget the last name. Anyway. One approach here would be to pause the podcast and say to a magical device, a magical microphone, if you will, what other, what other references are there to this term? Can you help me understand how these people are saying it? What they mean by it when they say it with ideally, ideally like a fair bit of quoted material. I don't, that's maybe one realization I'm recognizing here. I don't really care for a perfectly summarized blob that was created by the like raw output of the most powerful LLM. That's actually less interesting to me because I know for a fact that probably the past and references of this term were recorded and published after the cutoff date of the training data. So, and I guess it would be three occurrences in training data, which my understanding might not even make a blip. I'm not sure. I don't know how LLMs work. The point is given the choice between asking GPT this in a perfectly easy way and asking more or less a pipeline that just ingests a bunch of their raw transcripts, finds these terms, puts them into something appearing like a coherent order and just reads them out to me or shows them to me on the screen is a lot more interesting because I know it's going to be grounded in something that has actually been said, not something that we trained the model to say, which is weird because those are kind of the same thing. But yeah, so that's just one, one design fiction is me being able to ask a query of what does a Socratic search space, descending into a Socratic search space mean? Oh, how are they explaining this in other contexts? And then really just be able to like resume a listening of this podcast with that context now kind of associated together, baked in somehow, because there's a chance that I might, it'd be really interesting to see that as a little step that I took along the route that helped me understand how I was understanding this piece of media. So there we have it.
The text discusses the concept of using screen recording to capture and organize thoughts, particularly when mapping them out with supportive graphics or diagrams, enhancing the process with features like rich audio and linking possibilities. The author suggests that a system similar to rewind.ai's capture format could be utilized, allowing for full-text search and leveraging metadata from shared Figma files to extract links and possibly map these as concept maps. This method aims to enhance the searchability, filtering, and querying of content, integrating into a platform the author refers to as "burrito dot place." The author contemplates the addition of robust social context to screen recordings, considering them as potential raw input for content understanding, akin to the role of audio, and builds upon themes previously explored in R-Log.
The author is reflecting on the challenges of effectively showcasing their work on the internet, particularly in relation to portfolios and resumes. They express frustration with the limitations of resumes in capturing the depth of their experience and contributions. Additionally, they discuss the ongoing financial and practical challenges of maintaining online projects and the importance of preserving past work for the benefit of future creators. The author considers using archive.org as a potential solution but expresses reservations about outsourcing this responsibility to a non-profit organization. They ultimately prioritize the use of such resources for preserving knowledge that benefits the broader community rather than their own personal or professional work. The speaker is exploring the idea of preserving their work and experiences in a meaningful and sustainable way. They express concerns about relying on external platforms like archive.org and consider alternatives such as hosting their own content and encoding it into a lower fidelity medium. They also discuss the concept of creating their own encapsulation and representation of their work, which they hope will be more long-term sustainable. The text discusses the idea of creating a collaborative storytelling and writing platform that acts as a memory time capsule by archiving and snapshotting links. It addresses the challenge of link rot and suggests that decentralized hosting and a network of machines could potentially help in the future. The text discusses the concept of a scoped IPFS that functions similar to RAID, where each file is known only once but stored multiple times based on its significance. It also touches on the importance of data permanence on the internet, addressing concerns about archiving family photos and trusting companies like iCloud to maintain data indefinitely. The author questions if they should trust these companies and expresses uncertainty about the longevity of their data stored on such platforms.
A shared 'brain' is being discussed as a platform for asynchronous voice note conversations where metadata could enhance understanding and visualization of conversational threads. The speaker suggests a focus on DEMO rather than DEC as a fork in the road, believing it better suits the work they've been doing with building prototypes. A group experiment is proposed with four members to delve into how these voice notes can overlap and interconnect, with the idea of marking chapters within responses to clarify dialogue. The concept also touches on the nuances of information retrieval, preferring vector databases over direct text searches, hinting at a similarity to the speaker's initial voice note exchanges with Savannah after meeting on a dating app. Voice communication offers significant advantages as a medium, and there's an idea presented here that its power should extend beyond just live conversations. Current messaging apps are filled with voice notes that are often difficult to search, filter, or respond to, though iMessage now has transcripts, which are generally reliable and useful once you've listened to the original voice note. The ability to refer back to transcribed voice notes can aid in crafting thoughtful responses and engaging in more meaningful discussions. The sender of the message suggests that by embracing this approach to communication, we could enhance our conversations and is curious to see how it will develop.
82.87% similar
The speaker is considering how to categorize inputs for a burrito-like system, focusing on what constitutes a minimum ingredient for a filling, using metadata like voice notes, images, and GPS tags. They ponder the need to explicitly connect related inputs, such as a photo and a voice note about the same subject, or whether temporal and spatial proximity should implicitly link them. The speaker also reflects on the holistic context influencing inputs, including mood and environment, questioning how far explicit bundling should go. Ultimately, they imply that inputs with similar timing and location could be considered related without the need for explicit connection, likening this to lab notes.
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.
86.88% similar
The speaker is considering the research question of how to achieve distributed compute, particularly the need for parallelism in executing pipelines and AI agents. They question the potential for building a Directed Acyclic Graph (DAG) that allows for agents to dynamically contribute to it and execute in parallel, emphasizing the need for pipeline development to accommodate this level of complexity. The discussion also touches on the scalability and parallel execution potential of the mixture of experts model, such as GPT-4, and the potential for hierarchical or vector space implementation. The speaker is keen on exploring the level of parallelism achievable through mixture of experts but acknowledges the limited understanding of its full capabilities at this point. They also express curiosity about fine-tuning experts for personal data. The speaker is discussing the data they are generating and the value of the training data for their system, particularly emphasizing the importance of transforming the data to suit their context and actions. They mention meditating and recording their thoughts, which they intend to transform into a bullet point list using an AI model after running it through a pipeline. The individual also discusses making their data publicly accessible and considering using GPT (possibly GPT-3) to post summaries of their thoughts on Twitter. They also ponder the potential of using machine learning models to create a personal Google-like system for individual data. The text discusses using data chunking as a method for generating backlinks and implementing PageRank in an agent system. It mentions steep space models and the continuous updating of internal state during training. It also compares the level of context in transformer models and discusses the idea of transformer as a compression of knowledge in a language. The speaker expresses interest in understanding the concept of decay in relation to memory and its impact on the storage and retrieval of information. They draw parallels between the processing of information in their mind and the functioning of a transformer model, with the long-term memory being likened to a transformer and short-term memory to online processing. They speculate on the potential of augmenting the transformer model with synthetic training data to improve long-term context retention and recall. Additionally, they mention a desire to leverage a state space model to compile a list of movies recommended by friends and contemplate the symbiotic relationship between technology and human sensory inputs in the future. In this passage, the speaker reflects on the relationship between humans and computers, suggesting that a form of symbiosis already exists between the two. They acknowledge the reliance on technology and the interconnectedness of biological and computational intelligence, viewing them as mutually beneficial and likening the relationship to symbiosis in nature. They express a preference for living at the juxtaposition of humans and computers, while acknowledging the potential challenges and the need to address potential risks. Additionally, they mention that their thoughts on this topic have been influenced by their experiences with psychedelics. The speaker discusses the potential increase in computing power over the next five years, mentioning the impact of Moore's Law and advancements in lithography and semiconductors. They refer to the semiconductor roadmap up to 2034, highlighting the shift towards smaller measurements, such as angstroms, for increased transistor density. They emphasize that the nanometer measurements are based on nomenclature rather than actual transistor size, and the challenges in increasing density due to size limitations and cost constraints. The conversation touches on different companies' approaches to transistor density and the role of ASML in pushing lithography boundaries, before concluding with a reference to the high cost and potential decline in revenue for semiconductor production. The speaker discusses the importance of semiconductor manufacturing in the U.S. and China's significant focus in this area. They mention watching videos and reading sub stacks related to semiconductor technology, specifically referencing industry analysts and experts in the field. The speaker expresses enthusiasm for staying updated on developments and offers to share information with the listener. The conversation concludes with a friendly farewell and the possibility of future discussions.
85.67% similar
I had a profound two-hour call with Jordan at 9 a.m., discussing a range of topics including the exciting potential of language models, which he called "word calculators." Jordan and I agreed on the importance of solidifying a good intention to create a compelling demo that deeply explores the vision of our project. We also touched on self-expression and the value of using the platform as a "playground" to honestly express oneself without worrying about the audience. Lastly, we delved into the dynamic nature of intentions and how they evolve over time, along with the idea that AI could support individuals by acting as an executive function override during moments of weakness.
85.27% similar
The individual has discovered that working backward from a desired result with a large language model is surprisingly effective, especially when detailing the problem forward seems challenging. This backward approach has simplified the problem and resulted in the use of GPT-4 for data transformation within the context window, improving the process. An automatic metadata generation pipeline is emerging, where data transformations are added as needed, potentially storing transformations for future use based on query relevance. This system will generate an extensive amount of synthetic data, allowing for the extraction of relevant information through queries fed into the model at later stages, rather than having to pre-determine all questions.
85.03% similar
The speaker aspires to be part of communities that empower individuals to explore their data and bring value back to themselves. They are willing to take a job in such a space and believe it's worth doing. The goal is to build tools that make it easy for the individual to work with their data directly on a web page. They plan to move to a more reactive front end using Next.js and React, designing a feed and query system possibly using natural language. The speaker also mentions working on embedding audio and ensuring embeddings are accessible. The text discusses the process of obtaining and manipulating data and emphasizes the importance of experimentation and innovation. It uses the metaphor of building a playground to illustrate the iterative nature of the process, acknowledging that initial attempts may be imperfect but can be improved upon through learning from mistakes. The writer anticipates challenges but expresses a hope to avoid negative consequences and eventually achieve success. Finally, the text concludes with a lighthearted remark and a reference to going to sleep.
84.95% similar
The article discusses the concept of excess energy and its potential for useful work, particularly in the context of desalinization. It raises questions about the economic viability of various forms of useful work and their relationship to industry operations. The author ponders how to accommodate fluctuating energy demand and considers alternative forms of useful work that can be easily adjusted. Additionally, the article delves into the rising energy prices and their implications, noting the impact on inflation and the broader economy. It ultimately questions whether energy prices should be decreasing considering the growing energy supply and highlights the ongoing challenge of balancing energy demand. The author contemplates the impact of a hypothetical surplus of 100 terawatts of power, wondering how it would be utilized in practical applications as well as its potential effect on energy prices. They reflect on the potential implications for the efficiency of semiconductor manufacturing processes and the unit economics of power consumption in relation to chip production. Additionally, they consider the impact on the cost of energy and the potential influence on technological advancements, such as mobile devices and large-language models, while pondering the likelihood of significant developments in battery capacity or power grid capacity in the future. Ultimately, the author grapples with the complex interplay between energy availability, technology development, and economic factors. The text discusses the impact of luck and timing on the future, emphasizing the significance of being in the right place at the right time in an evolving world. The questions revolve around the potential of using increased computing power and its implications for various industries. The author ponders the feasibility of building and networking advanced computational systems, as well as seeking funding opportunities by approaching venture capitalists in Silicon Valley. The text also expresses uncertainty about the timing and feasibility of pursuing these ideas, acknowledging the complexity and challenges involved. The speaker is focused on securing funding for their project and contemplating the core question they are trying to answer. They express a concern about the difficulty of the problem as it exists across various future scenarios and emphasize the need for a computer to understand their context without losing the complexity and emotion of human communication. They mention existing products like Rewind and Tab, but express skepticism about the ease of solving their problem through technology, stating a reluctance to change their behavior to fit a machine's requirements and feeling overwhelmed by the complexity of the task. Despite their doubts, they express a desire to fully realize their vision through a website. The speaker plans to create a new app that will generate a JSON output based on their questions. They believe that having this functionality will enable them to build any app they want. The speaker ends the voice memo with the intention of utilizing the recording for a future project they are working on and suggests that they'll use it to engage in questioning and exploration.