Lucasxp64

Money is just power, and it can be used for good and evil. I don't think people with good intentions should refrain from being greedy as heck to amassing as much as possible within ethical limits to keep having more voice in society. Power by itself is not evil.

I had an "ah-ha" moment now. I noticed as the money kept pilling up on the table in his exercise, the more emotional I began to get, thinking about how it would help me in my survival. The whole point is, to be using money as a means beyond my personal survival and use, in business, in investing, etc. I need to start seeing it less emotionally. It also definitely helps keep someone sane once they achieve fast amounts of wealth. Have you noticed that oftentimes large sums of money for personal use tends to make a lot of people just want to go balls to the wall with using material stuff to achieve happiness? But also at the same time when I see anything above 10-50 Million, I can't personally see myself having personal use for all of that in my lifetime perhaps excluding some ultra expensive medical expenses (Even those are limited, after a certain point it gets ridiculous). It starts to become the kind of money I'd see someone might build a large business that does something really useful, or perhaps it could be used for immense evil as well, like a coup d'état, etc.

For example, I asked the AI to list every objection that Leo has answered, and from there I could just ask further clarification:

It's actually useful as heck for specific practical questions because Leo spoke about that kind of stuff a lot, but his insights are often spread across many videos, and this AI combines them all, like it did for my journal, audio notes and other sources, like when someone wants a quick answer for something. Much better than the answers I get from a generic LLM. But I'll checkout those reasoning models as well. I had done one NotebookLM where I combined other books and authors, including my personal diary, and it's amazing. It does combine multiple perspectives. The podcast generator is kinda lame. I only liked it for helping me with some emotional crap I was going through, and I had been doing audio journaling for the whole month on it and telling myself insights and perspectives I should hold, but due to its unstructured nature, it's insufferable for me to listen to those hours of my own recordings, I ramble a lot and repeat myself. This AI cuts through lack of clarity and repetition in large amounts of text. It's meant to be used as a cleaning, summarization and search tool inside for large bodies of information. This one is not meant to be doing heavy reasoning. It's as good as the text sources. There are some YouTube channels like "Alex Hormozi" that he speaks for hours and hours, or podcasts. I wanna just feed a ton of all different podcasts, and ask questions, and it seeks through all of those hundreds of hours of content the parts relevant to my question based on perspective from people that I find good. As opposed to the generic crap those LLMs will give, it's supposed to BE BIASED, supposed to be SPECIFIC this way.

Leo AI answer:

I won't give technical details unless Leo allows it. I won't make more posts with AI generated content like this. This is just a tech sample. This is the future of search engines. "What happens when someone claps, but there is nobody to hear?" "Do AIs have consciousness?" This one is a hard one, the question: The answer: List all models that leo gura uses to make sense of things Meaning of life:

I used a script that concatenates all my markdown files from my Obsidian vault into a single .txt file. If it's a handwritten notebook, well, I guess you could scan and feed some other AI with the best quality OCR you can get, and feed the AI the outputs. Perhaps it can already OCR if you upload it as PDF? Someone can confirm this? Also, I saw that it actually accepts audio files as well, so I can just upload my voice notes too. But I might hit the upload limit and I might need to circumvent it by transcribing the audios with Whisper, and concatenating the output text as a single file. Or concatenating the audiofiles into a single file using FFMpeg. There must be a setting to do that without re-encoding so it would be fast. Right now, It has a limit of 50 files, and "Each source can contain up to 500,000 words, or up to 200MB for uploaded files." https://support.google.com/notebooklm/answer/14276468?hl=en With OneNote, I tried to export my old Notebooks as PDF, but it glitched. I might try again with some other exporter format or software. As long as I can get the raw text extracted from there. Should be similar for any journaling software, some exporter. Choose to export to MARKDOWN format if possible, that's the native format all LLMs use, but it's not that important, they can make sense of garbled formatting. To upload your "EPUB" files of books, you I used Calibri to convet them to .TXT files. It would be trivial to make a script that takes even a whole folder of files and concatenate/Splits them as needed for importing there. (If it goes past limits of 500k words, or limit per file, etc)

Try to write the "Custom" prompt for the podcast. But yeah, they keep getting sidetracked and are ADHD, the results vary a lot depending on the prompt, but that's what I wanted, I wanted them to be spit-balling based on my journal. Improve your prompt if they are getting too sidetracked. For extremely specific answers, you should not use the podcast. The podcast is not an instruction model. I tried to give specific instructions, they don't follow them. You should use the CHAT for specific/technical answers and questions, it even provides the sources/specific locations in the files. I'd be careful with uploading PDF formats of Mathematics, Chemistry, etc, anything with a lot of notations or complex syntax. Unless they are in something like LaTeX already, like all other models out there. Maybe it's good at parsing them?

notebooklm.google.com I used the podcast generator from this Google AI tool, I extracted all of my notes from my Obsidian vault into a single .txt file, and I feed the AI it as a source, alongside some of my favorite books, and I prompted the podcast to be about speaking my personal struggles from the perspective from the books, and the whole podcast got fine-tuned to reading my notes based on those books mindsets. This is a completely new step above merely chatting with an AI. I always dreamed of being able to actually feed my content into it and getting insights beyond just surface level garbage done with simple vector based techniques. It's completely worth it. Although, you should mind your privacy if you're concerned. It's incredible, I can now relate knowledge of books with my own personal struggles, ways of thinking and biases, it has massive context about me. Now I should also automatically transcribe the dozens of audio journaling audio recordings I had as well. Those are really hard to go through. If I feed them into the AI it will be wonderful to extract insights and common patterns from them.

lol a lot of argument is just because people didn't do the work to realize that their perspectives are pretty close to each other, and they are just rephrasing the same stuff differently.

I ask Mixtral or LLama (From Meta) to: "Please answer this like a Machiavellian" and it proceeds to answer quite differently. You may want to try it, it gets much more objective oriented, and if you ask it "Please answer this like a Machiavellian. Given my goal, yada yada, do you think I'm shooting myself in the feet?" But those models are not as intelligent as ChatGPT4-O, but they are less censored. I like that they give different answers, although pretty dumb sometimes. But that probably will make you more narcissistic if you misuse them like that. I'll try that prompt that Leo quoted above. You can use it at Duck.ai for free