Transcript: So the thing that initially made me pause and take that previous audio note was listening to Jan Lecun from, I believe, Facebook research. I believe FAIR. I'm assuming it stands for Facebook AI research. But I don't know. Maybe France AI research. Anyway, I'll have to look this one up later. But, I mean, even something like that going into the voice note would be amazing to just like pull up for the large language model to understand and infer that's something that I want to come up and be in my viewport. So regardless, I'm taking a note about this podcast and they're talking about hierarchical planning. And all of the little tiny steps. To get to you going to Paris, for example. And, yeah, it is an immense amount of sub steps. And this is the whole context thing. And I think a lot of it is, I mean, there's two things. One is we could like build this from scratch and just hope that we can make an AGI navigate the world in that way. Or, I mean, we can start generating that data and making it easier to train models to understand context. And the plans that we have. And the things that we do make based on our actions in the world. So, yeah, I mean, that's my thing on this. But more or less, like, I think, like, he makes an excellent point. And I'm mostly right at, like, putting this down just because, like, it's probably something to refer back to because he's obviously extremely intelligent and knows way more about machine learning than me. So I'm just excited. And I wanted to put a pin on the hierarchy. And I'm just excited to put a pin on the hierarchical planning section of Jan LeCun's podcast with Lex Friedman. Or rather the other way around.
82.80% similar
The author emphasizes the need for personal AI to be holistic and know a fair bit about the user to answer complex questions. They express skepticism about current devices like Tab and Rewind catching on but foresee their eventual adoption. They ponder the societal implications of pervasive surveillance and advocate for thoughtful consideration. The author envisions using an AI system to capture and analyze their conversations at home to elucidate thinking patterns and make them accessible. Additionally, they discuss the limitations of vector algorithms in representing complex questions and suggest the need for a new approach. The speaker suggests that while their idea is a starting point, further exploration is necessary to determine its relevance and significance. They reflect on the process of developing a deeper understanding and consider the practical aspects of implementing their thoughts about how the brain is constructed.
I was really struck by Jan Le Koon's discussion on Lex Friedman's podcast about the importance of sensory input compared to language. He pointed out that language represents just a tiny fraction of the data we process, whereas our sensory intake is massively more extensive. He illustrated this by saying that all of human text would take 170,000 years to read, but that's still two orders of magnitude less than the information a four-year-old has absorbed in their life. This insight made me enthusiastic about further exploring sensory data processing.
82.64% similar
The user is expressing their strong passion for personal data and their desire to make it more accessible to people. They believe that AI will enable easy access to personal data through natural language, particularly as part of augmented reality (AR). They are interested in Mind Palace and hope to contribute to the project if there is a good fit. The user has a diverse technological background and is unafraid to take risks in exploring new technologies. They are driven by their love for exploring and sharing experiences and knowledge, and they want to make personal data sharing easier and more discoverable for themselves and others.
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.
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.
77.84% similar
The author contemplates the process of converting an audio note into a transcript, then summarizing it on their "burrito" page. They express a desire to adjust the summarization voice to better represent themselves on the page. Recognizing that this feature may not have widespread appeal, the author nonetheless sees value in providing users with controls to personalize their "burrito." The concept of allowing users to fine-tune their experience is seen as an intriguing possibility.
77.66% similar
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.
76.78% similar
The speaker conveys their frustration with a difficult fundraising experience, describing a particularly unsatisfactory video call with a fund representative. The caller was in a bad mood, hadn't reviewed the provided materials, and hesitated to engage with the product's features. This led to a tense exchange where the speaker challenged the representative's commitment to valuing founders versus purely focusing on financial metrics. Feeling disillusioned, the speaker is left with a distaste for these disengaged "NPCs" and remains focused on their vision of fostering creative and engaging spaces.