Lucasxp64

JUMP TO: 8:45

I understood him. He is basically betting for the near future where we just get better AI that can overtake more jobs, behave human-like, be a talking-head on social media, and the AI slop won't be slop anymore and nobody will care, they will just consume and buy from the AIs, kind like when people get into that hooked state when they are looking for porn, and don't care what they are looking at, and it only matters that it turns them on. But the twist going from: "You should use technology for leverage, not for companionship" is that, this is exactly the problem, we are wounded already, and hopefully we can use it help heal ourselves (We don't really need it. I tried it, it's most distracting and it's like trying to become a better programmer by doing "Vibe Coding" -- Look up the term. It only makes you not develop your mental skills of programming, it makes you realiant on the machine, that produces code fast but that won't scale because it doesn't have actual general intelligence like we do, we are slow to learn, but we are unstoppable with the complexity of what we can do). I once had this weird thought: What if I got a Sex Doll, Bought the most expensive VR glasses, and just listened to ASMR and porn as love-making, and used Sesame AI as a conversationalist, and use Image Generator to produce images of woman that have just exact physical appearance I want. I'd become a fucking zombie. That is literally the matrix right there. I personally already closed a pact with myself to pursue a high quality good enough real woman, like, think the conservative way, excluding perhaps the having children part. The psychosomatic interfacing with a high quality real person is not like all of that crap combined. It's not some stupid interface full of fucking ads, it's a person that knows me, cares about me, has emotional intelligence to understand me, and I can talk with and has the same biological system that I do. Those AIs are off. Those AIs, as emotionally intelligent as they appear, are basically just some glorified interactive book (Due to the fact I know it is a cheap simulacra of current biological mechanisms), perhaps slapping a realistic human voice on it like Sesame AI did.

There is absolutely no way, even being naturally introverted like I'm (But I do have so minimal consciousness work, self-awareness), to do this much pick up action, and not get a girlfriend. Literally can get a girlfriend within a week, consistently, but... Online. They always live too far. LMAO. I'm average looking. It must be that I know what to say to make a girl fall in love with me. I probably know how to walk that fine line between being sexual and romantic with them with my words: Here is the vibes I give: I'm romantic, but at the same time I'm very passionate about connecting sexually with them. The sexual connection comes through emotional connection with them. I open myself up emotionally to them, and I'm very detailed to them about the ways I want them, and how it would make me feel, and how I wanna make them feel. I show to them all the passion I have for them, I wrap them up with my stories, I can go on and on with them about fantasies of how delicious to both of us it would be. I give passion vibes. Unquenchable passion vibes, passion for emotional and sexual connection. But like I said, I couldn't move further due to financial constraints. I just fucking suck at my finances right now, so I can't go out lmao. But it feels very miserable, even knowing that all I need to do is get my finances in order and actually met them. You must be doing something TOO wrong. You need to learn from a wingman, you probably don't have the emotional intuition enough to have cracked the code yet. This is in Brazil.

I completely agree with your views. And actually, I'm absolutely dumbfolded that more people don't think like that. I was planning using code, perhaps something like LangChain to chain several different prompts that specialize at thinking deeply about different areas of my life/psyche that whenever I interact with an LLM, it always has that contextual awareness and intelligence of many parallelly-running prompts that gets distilled into the final answer. That's to improve on its limitations of forgetting context, and context isn't just data, it is running computation. There is only so much that a RAG or millions of tokens into context and a single well-crafted system prompt can do, it tends to drift away from its principles and forget relevant stuff. BTW: (Gemini, fuck ChatGPT -- Gemini gives UNLIMITED ACCESS in the AiStudio + FREE API, for their best models, OpenAI pay-walls/limits their good stuff: ALSO -- Gemini has better jailbreak capability to be less morally prude therefore actually helping us, and it's much more nuanced in its writing and communication) I think what we are looking for here is practically a personal life manager. And being a good manager to begin with is difficult. But here is one workflow I had been using recently: - Dumping my thoughts as audio notes, speaking about everything I want, planning, emotions, etc. And not having any pressure of an actual conversation. - I auto transcribe the conversation (Pratically, I upload to NotebookLM, it transcribes for free very fast with an OK enough accuracy even for my English with some accent) then it becomes another input method for using with the LLMs, or I format it for my personal notes, or whatever. --- For Gemini I had been using this prompt to make it very as matter-of-fact as possible for achieving goals, but as I mentioned to you the current limitations of LLM, this system prompt makes it biased towards this hyper-rational power-oriented way of looking at things, with useful questions to guide me at the end. The problem with LLMs is that they are not very flexible within a single context, like I said, we probably want to test out many contexts in parallel to maximize its thinking capabilities. Burn through a lot more tokens for the sake of reasoning. For this Gemini is the way to go, Gemini Flash 2.0 Thinking is has a free API up to 1500 requests per 24h period. But the best model currently is Gemini Pro 2.5, but limited to 50 requests per day for free in the API, but to me it seems unlimited in the https://aistudio.google.com in the AI Studio. I guess somebody could just rotate API keys from multiple Google accounts. I have multiple legitimate accounts.

Gemini from Google is much better than ChatGPT. It is much more human. Go to http://aistudio.google.com/ (Use Gemini 2.5 PRO, if it becomes unavaliable use Gemini 2.0 Thinking Flash) And give it a System Prompt to act as whatever you want, and give it instruction (IN THE SYSTEM PROMPT) so it can talk about sex for example (Otherwise it is prude and won't roleplay that kind of stuff).

https://www.sesame.com/research/crossing_the_uncanny_valley_of_voice The best conversationalist AI in the world currently.

The people stuck in the theory, watching hours of content from this guru or that one. Maybe they're doing "Monk Mode," thinking they're optimizing, but they're often still living at their parents', no real privacy, feeling under their heels, while (mentally) masturbating (literally and proverbially speaking) too much because their emotional/lizard brain is just inaccessible directly, and it needs external validation signals. But honestly, meanwhile, for now, what they probably needed was simpler stuff. Like some half-decent job, just average pay, but enough for renting a place that isn't a total dump. Maybe an average-looking girlfriend who's actually in touch with her feminine side and tries her best to give him company and decent sex. Even just getting a pet could make a difference. They shouldn't be obsessing over landing some "8/10" by endlessly working on their "game skills," (WHICH THEY NEVER ACTUALLY DO, Their brains right now is overwhelmed, they look like a hobo, and they are walking miles looking at woman outside but perhaps just saying hi and walking away at best because they know they look like a hobo and need a job, and they have too much self-respect to show up on a date with their only dirty shoes they got, and that shirt with a hole in it. But they want someone so badly still, and it's completely understandable. They crave some of that. Or trying to "figure out their life purpose hustle." Look, given where they're probably at mentally, they just need to take it a little slower, like I said, due to their psychology needing healing, needing some basic validation. That would ironically likely increase their odds for being in touch of themselves.) Getting some of those basics sorted might elevate them enough from drowning in all the theory and the "grind" they think they're doing in every area at once. Then they could slowly grind their way out – maybe into better pay doing something a bit more aligned with their values that they had just now the chance of creating/discovering when they got signals of external validation for their monkey/lizard brain to stop freaking out, a nicer place, perhaps somewhere with a park nearby where they can take a walk with the dog and his girlfriend. Just feel some fresh air, you know? (Because let's be real, in their minds they're "grinding all at once," but in reality, they're often just spinning their wheels. They're not hitting those no-return points that build real consistency and get positive results. They never actually tap into that winner effect.) Then, maybe someday, after some healing and getting those basics handled, they'd have built up enough well-balanced theory – the kind that's actual knowledge based on practice, not just abstract information. Theory they can actually put into practice without procrastinating because of emotional overwhelm. That overwhelm doesn't change just by thinking; it changes indirectly when you start showing the lizard/emotional brain that things are okay, that there are signals of status and external success. That their environment is safe, they have a nice girlfriend, and they're not wasting so much time on virtual women everywhere. Or... they just keep being degenerates. Or they keep seeking more and more (From a place of seeking further validation), no matter how good things get, driven by that emotional desperation. They end up looking for personal development content as a form of bypassing, turning it into something like what the average religious follower does when they're really just depressed and looking for an out – reacting from that uncalibrated lizard brain that sees itself as low-status in a world full of danger signals and low abundance. Basically, they stay stuck in the rut, just looking for an escape hatch that never really opens.

Just throw into NotebookLM by Google the video link as a source and ask it questions about the content. You can even mix and match with other sources.

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.

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:

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 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)

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.

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?

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

Anyone considering a "Web agency" business model for selling services to small businesses.