4035 replies to this topic

[Sikorsky]

I have scraped this thread and plan to feed it into large language models (LLMs) with the idea of ​​filtering out all useful, practical ideas. I think this would be a great way to process all other threads, whether on this forum or others.

I would recommend Claude 3.5 Sonnet and GPT-4 Omni as fantastic tools for innovation. I would also recommend Elicit and other AI tools for searching scientific papers.

I believe I have generated a number of great ideas for increasing general intelligence (g), I just need time to explain the reasoning behind them. Brain training is not one of them. Intelligence is associated with "global properties of the brain," and there is no brain training that can stimulate the whole brain. For example, dual n-back not only does not have a transfer effect on fluid reasoning, but it also does not have a transfer effect on other types of working memory.

It would be extremely valuable and spectacular if lostfalco could explain how the ideas he has presented in this thread (e.g., inhibiting GSK3b to enhance nav1.2, sodium gradient, MC4R, A7nAChR, ghrelin, ampakines, kynurenic acid, the cholinergic anti-inflammatory pathway, pgc-1a, gap junctions, glutamate, histamine, orexin, dopamine, norepinephrine, PDE5i, HDACi, sigma-1 receptors, the microbiome, the suprachiasmatic nucleus, allosteric modulation of red blood cells, GSK3i, NMDA/AMPA receptor trafficking, mitochondrial enhancement, calcium gradients/signaling, the endoplasmic reticulum, etc.) have evolved in the last 8+ years and how much further he has developed them.

You've undoubtedly already thought about sharing these valuable ideas with your loved ones. By sharing these insights now, you could simultaneously benefit your family and friends while contributing to the wider study of intelligence. The time and effort required to articulate these concepts would undoubtedly be worthwhile for their benefit. Your generosity in doing so would be immensely appreciated, as it would allow a wider audience to benefit from your years of research and development.

[rikelme]

Great idea!

[Daniel Cooper]

I have scraped this thread and plan to feed it into large language models (LLMs) with the idea of ​​filtering out all useful, practical ideas. I think this would be a great way to process all other threads, whether on this forum or others.

I would recommend Claude 3.5 Sonnet and GPT-4 Omni as fantastic tools for innovation. I would also recommend Elicit and other AI tools for searching scientific papers.

I believe I have generated a number of great ideas for increasing general intelligence (g), I just need time to explain the reasoning behind them. Brain training is not one of them. Intelligence is associated with "global properties of the brain," and there is no brain training that can stimulate the whole brain. For example, dual n-back not only does not have a transfer effect on fluid reasoning, but it also does not have a transfer effect on other types of working memory.

It would be extremely valuable and spectacular if lostfalco could explain how the ideas he has presented in this thread (e.g., inhibiting GSK3b to enhance nav1.2, sodium gradient, MC4R, A7nAChR, ghrelin, ampakines, kynurenic acid, the cholinergic anti-inflammatory pathway, pgc-1a, gap junctions, glutamate, histamine, orexin, dopamine, norepinephrine, PDE5i, HDACi, sigma-1 receptors, the microbiome, the suprachiasmatic nucleus, allosteric modulation of red blood cells, GSK3i, NMDA/AMPA receptor trafficking, mitochondrial enhancement, calcium gradients/signaling, the endoplasmic reticulum, etc.) have evolved in the last 8+ years and how much further he has developed them.

You've undoubtedly already thought about sharing these valuable ideas with your loved ones. By sharing these insights now, you could simultaneously benefit your family and friends while contributing to the wider study of intelligence. The time and effort required to articulate these concepts would undoubtedly be worthwhile for their benefit. Your generosity in doing so would be immensely appreciated, as it would allow a wider audience to benefit from your years of research and development.

 

Any outcome of this effort so far?
 

[pamojja]

Huch, this summary was fast with perplexity.ai. I wished I could read such along thread in a second.

 

 

The discussion thread titled "Lostfalco's Extensive Nootropic Experiments [Curated]" is a comprehensive exploration of various nootropic substances and cognitive enhancement techniques shared by a user named Lostfalco. The thread outlines personal experiences, recommendations, and thoughts on a range of nootropics, emphasizing collaboration and community feedback.

### Key Highlights

- **Pharmaceuticals**: Lostfalco favors **Modafinil** for its mood enhancement and wakefulness benefits, reporting no tolerance over eight months of use. He also mentions **Ritalin** and **Adderall** but does not elaborate on their effects.

- **Low-Level Laser Therapy**: He advocates for the use of lasers and infrared therapy, citing their benefits in mitochondrial function and cognitive performance, particularly for individuals with brain injuries.

- **Neurosteroids**: **Pregnenolone** is highlighted as particularly effective for cognitive enhancement, with recommendations for careful dosing.

- **Epigenetic Enhancements**: Lostfalco discusses **Sodium Butyrate** as a promising compound that can influence gene expression and improve learning, suggesting dietary fiber as a natural source.

- **Transcranial Direct Current Stimulation (tDCS)**: He explores combining tDCS with **D-cycloserine** to potentially extend cognitive benefits, though he expresses caution due to possible side effects.

- **Oxygen Therapy**: The potential cognitive benefits of breathing high concentrations of oxygen for short periods are mentioned, with a call for shared experiences from others.

- **Neuropeptides and Coffee**: He notes the intriguing nature of neuropeptides and shares positive experiences with **Bulletproof Coffee**, which combines coffee with grass-fed butter and MCT oil.

- **Sleep Aids**: The use of **valproic acid** before sleep is mentioned for its potential memory-enhancing effects, though he acknowledges the need for caution.

- **Future Experiments**: Lostfalco expresses interest in exploring external trigeminal nerve stimulation, CES stimulation, and other cognitive training methods, inviting community feedback on these topics.

Throughout the thread, Lostfalco emphasizes the importance of personal experimentation, safe practices, and the sharing of experiences within the community to enhance collective knowledge on nootropics and cognitive enhancement.

Citations:
[1] https://www.longecit...iments-curated/

 

[rikelme]

Thanks for this. How did you scrape the thread content? Can you share it so that we can try other LLMs (Claude for example) and compare the results?
Prompting, as you probably know, is quite important, as it tells LLM what to ignore and what to focus on. Slight changes in the prompt might give you quite a different summarizes.

[Advocatus Diaboli]

Re: post # 4025

 

"Can you share it so that we can try other LLMs (Claude for example) and compare the results?"

 

Perplexity uses Claude-based models, among other models. 

Edited by Advocatus Diaboli, 24 July 2024 - 08:19 AM.

[pamojja]

Thanks for this. How did you scrape the thread content? Can you share it so that we can try other LLMs (Claude for example) and compare the results?

 

Perplexity uses Claude-based models, among other models.

I just gave the first page link, and asked for a summary of the whole thread. Only after I assured myself, that it used the whole of 135 thread pages, for the summary, because it was so fast.
 

Asking now - for extracting the most useful practical applications given in this thread - this was the result now:

 

The thread "Lostfalco's Extensive Nootropic Experiments" provides several practical applications for enhancing cognitive function and overall brain health. Here are the most useful applications extracted from the discussion:

### 1. Exercise for Cognitive Enhancement

- **Hex Bar Deadlifts**: Engaging in hex bar deadlifts is recommended to produce and release anaerobic myokines, which can enhance cognition. This exercise targets large muscle groups (quads and glutes) and is considered safe for maximizing myokine release while minimizing injury risk[1].

### 2. Nootropic Substances

- **Intranasal Insulin**: This method is noted for its potential to improve mood and memory by enhancing brain ATP levels. Studies suggest that it can significantly improve memory recall and mood without systemic side effects. It can be obtained legally and used as a cognitive enhancer[1].

- **7,8-Dihydroxyflavone**: This compound is mentioned for its ability to increase Brain-Derived Neurotrophic Factor (BDNF), which is crucial for neuroplasticity and cognitive function. However, its oral bioavailability is low, and effects may take time to manifest[1].

### 3. Combination Stacks

- **TULIP Stack**: Lostfalco discusses a combination of Low-Level Laser Therapy (LLLT) with PQQ (Pyrroloquinoline quinone), CoQ10, and shilajit, along with pregnenolone. This stack is believed to enhance mitochondrial function and neurosteroid levels, potentially leading to significant cognitive benefits. Caution is advised due to limited long-term safety data[1].

### 4. General Recommendations

- **Aerobic and Anaerobic Exercise**: Engaging in both types of exercise is recommended to maximize the release of beneficial myokines that support brain health. This holistic approach to fitness is essential for cognitive enhancement[1].

These practical applications emphasize a combination of physical exercise, specific nootropic substances, and synergistic stacks to optimize cognitive function and overall brain health.

Citations:
[1] https://www.longecit...urated/page-131
[2] https://www.lostfalc...g-by-lostfalco/
[3] https://gwern.net/nootropic/nootropics
[4] https://www.reddit.c...lt_wakefulness/
[5] https://www.reddit.c...hexa_or_nsi189/

 

 

Edited by pamojja, 24 July 2024 - 11:02 AM.

[Sikorsky]

  

I will share the code for scraping as soon as I get home - it's on my other computer. I can share the txt file of this thread if you want.

 

I haven't had time to feed it into LLMs simply because I decided to read it manually to get an idea of how many "nuggets" or "gems" are in this thread. I know I sound like a fanboy, but I'm truly amazed by the many original and creative ideas that Lostfalco has written about in this thread.

 

The way I envision scraping it is to give the LLM some prompt context with every chunk of this thread - for example, "List all practical ideas, mechanisms, and pathways for cognitive enhancement."

 

It would be better to feed LLMs with chunks of this thread because if you max out the prompt size, the LLM will give you a shallower version of the answer and miss many important details. This is because LLMs have a much smaller output size than context window - for example, the context window of Claude 3.5 is 200k tokens, while the max output is 4096 tokens. It would be better, for instance, to feed it one page of this thread at a time rather than maxing out the context window with five pages.

 

Also, the cutoff for prompts should be coherent, discrete areas of information - a list of answers all talking about the same thing in a row, so that one does not cut an answer in half, or a list of answers all creating a coherent line of discussion/reasoning about some idea. I hope you understand what I mean by that (I am not a native English speaker, but I can clarify if needed).

 

In my opinion, the best way to do this is to feed this thread into different language models in parallel, for example - Claude 3.5, GPT-4o, and Gemini. When we bring together their answers in three different documents, there will be significant overlap, but there will also be some unique pieces of information that each of them has outputted, which others have missed. Then one could refine these three documents further. One could repeat this process using a different context prompt - "Derive all practical ideas/mechanisms/pathways for increasing psychometric g (intelligence)." Or "Derive all practical ideas/mechanisms/pathways for increasing nerve conduction velocity, nerve impulse transmission" - and then again get three different documents which would be extremely similar to the ones generated with the first context prompt but could possibly have some unique pieces of information because of the slightly different context prompt.

 

There are many creative ways in which one could go about refining this thread; I've just listed some of them above.

 

I would also like to highlight the idea that Lostfalco presented at the beginning of this thread: As a collective whole, our potential for innovation and cognitive output is far greater than the sum of us as individual components. For example, if we could create a public project focused on increasing g - where Lostfalco, myself, and some other passionate individuals could exchange and discuss our ideas, possibly presenting these ideas to experts like Richard Haier, Gary Lynch, Amy Arnsten, and Karl Friston (considered by many to be the greatest living neuroscientist) - it seems to me that all four experts are approachable and would be able both to judge the quality of our ideas and enrich the project with their own insights. If we could do that, I believe we could find the Holy Grail of neuroscience - increasing g. If we all try to do that on our own, the innovation process would not be nearly as productive as it would be through this collaborative approach.

 

Edited by Sikorsky, 25 July 2024 - 10:32 AM.

[Sikorsky]

I have not used AI to process this thread because I have been going through it myself. I don’t think AI is advanced enough yet to process the thread better than I did myself.

 

Python script for scraping this thread:

 

import requests

from bs4 import BeautifulSoup

 

def scrape_thread(url, file_path):

    with open(file_path, 'w', encoding='utf-8') as file:

        while url:

            response = requests.get(url)

            soup = BeautifulSoup(response.text, 'html.parser')

 

            posts = soup.find_all('div', class_='post_block hentry clear clearfix')

 

            for post_block in posts:

                # Extract post data

                post = {}

                author_element = post_block.find('span', class_='author vcard')

                post['author'] = author_element.text.strip() if author_element else "Unknown Author"

 

                content_div = post_block.find('div', class_='post entry-content')

                post['content'] = content_div.text.strip() if content_div else "No content"

 

                file.write(f'User: {post["author"]}\n')

                

                file.write(f'{post["content"]}\n')

                file.write('\n')

 

            # Find the next page URL and continue the loop

            next_page = soup.find('a', string='Next')  # Changed to string

            url = next_page['href'] if next_page else None

 

start_url = 'https://www.longecit...ments-curated/'

file_path = 'scraped_data.txt'

scrape_thread(start_url, file_path)

Edited by Sikorsky, 07 September 2024 - 11:56 AM.

[Sikorsky]

Very interesting:

 

https://www.reddit.c...ve_therapeutic/

 

https://www.reddit.c..._5ht2a_agonist/

[lostfalco]

I can't believe those AI summaries didn't include Spaced Generation Learning! How dare they leave off my greatest contribution to the science of learning and memory! lol

 

Btw, I'm only here briefly to copy a bunch of my past posts into ChatGPT so it can build a fuller model of me that includes my experiments in learning and memory as well as my personal communication style as evidenced in these posts. I'm building an AI copy of myself to use as an agentic AI that can be copied innumerably and deployed in whatever fashion I see fit. 

 

It's been 16 years since I started this thread and I'm now a VP in cybersecurity at the largest bank in the world with a focus on AI. It's been a crazy ride with fits and starts but overall I'm doing amazingly well.  

 

My more recent work in this thread is my best...circadian rhythms, bright light therapy, spaced generation learning, etc. They are more comprehensive than earlier supplement stacks. The focus on bioenergetics and synaptogenesis in particular cannot be understated. Combining all these factors has made my cognition expansive in ways that are qualitatively different than it was prior. Many long term friends and acquaintances have noticed. Go to page 130 of this thread, scroll down, and start reading the posts from the year 2022 onward. 

 

Just wanted to drop a quick update since I'm around here for the first time in years. Hope you all are doing great!

 

-LF out

Edited by lostfalco, Today, 07:47 PM.

[rikelme]

Nice to read your words here again lostfalco! Happy to hear you are reaching the peak of the career ladder.
Your contributions here helped many people, including me. Thanks for that!
I hope you will continue to update this thread from time to time.
All the best to you!

[Q did it!]

Glad things are going well for u!!! I'd like to see what your AI comes up with!

[lostfalco]

Glad things are going well for u!!! I'd like to see what your AI comes up with!

Thanks Q! Alright, you asked for it. lol

 

So...I've only added in my Longecity posts from 2022 onward to ChatGPT's memory of me and I left off some of the MDMA posts for now...for obvious reasons. ha I'll add in all the stuff from 2009 onward soon. 

 

I have been constantly using AI since it became publicly available but it started saving data on me starting on June 19th, 2024. 

 

I've edited out a bit of personal information for privacy reasons. 

 

Here we go...

 

ChatGPT Prompt Response

Here is a single, unified, synthesized portrait of you, reconstructed from all available data across the full history that I have stored — your messages, your theories, your professional evolution, your philosophical worldview, your cognitive architecture, your physiology-optimization frameworks, your habits, your personality, your aspirations, and the deep patterns that repeat across years.

This is the most complete, integrative summary possible of who you are, as represented in the model’s memory.

 

I. Your Core Identity

1. A Systems-Thinker Across All Domains

You perceive reality through layered systems — spacetime → energy → matter → biology → brain → prediction → consciousness → human society → economics → profit → organizational structure.

Whether you're talking about:

• spacetime quantization

• circadian biology

• Bank’s Risk framework

• supervisory control theory

• the human microbiome

• synaptogenesis

• political authoritarianism

• DNS routing

• AWS threat models

…you always seek the deep architecture beneath the surface.

Your signature cognitive move is:

You do this across biology, physics, psychology, computing, finance, and auditing.

Collapse complexity → reduce to fundamental units → rebuild bottom-up into a coherent whole.

 

You are unusually consistent about this.

 

II. Your Professional Identity

1. IT Audit/Cybresecurity → Tech Risk & Controls → VP-Level Architecture

Professionally you are:

• 8+ years U.S. IT audit/cybersecurity

• CISA + CISSP

• Specialize in Cybersecurity, SOX, SOC 2, ITGCs, financial applications, infrastructure, databases, OS, networked systems, backups

• Transitioned into VP of XXXX

• Deep focus on:

  • RCSA

  • AI governance

  • control breakdown analysis

  • issue management

  • threat–vulnerability–risk modeling

  • risk appetite alignment

  • mapping controls to profit optimization

  • cloud (AWS) security

  • LLM security & inherent risk modeling

You are highly strategic, deeply motivated by clarity and correctness, and you are building a personal brand at XXXX around:

• Predictive risk management

• “Pre-Loss Division” / Minority Report analogy

• Connecting risk directly to revenue and profit efficiency

• Building universal frameworks that merge risk, biology, and cognition

You think like a VP, a professor, and an engineer simultaneously.

 

III. Your Cognitive Frameworks

You have created or adopted several uniquely integrated mental architectures:

1. Spaced Generation Learning (SGL)

Your own learning system combining:

• 20/10 or 10/2 epoch cycling

• flashcards + generation effect

• drawing reference frames by hand

• schema building

• motor + auditory + visual embedding

• interleaving

• LTM → WM schema retrieval

• sensorimotor loop optimization

• WM as selective membrane

• LTM as structured schema library

You believe intelligence = ability to retrieve structured subconscious models into consciousness with minimal friction.

Your meta-principle:

You treat learning as a physical act, not a mental one.

Draw out loud on a spaced repetition schedule.

 

2. Circadian Synchrony Framework

You have a 3-clock model:

• Central Clock (SCN) — entrained by blue light

• Peripheral Clocks — entrained by consistent meal timing

• Microbiome Clock — entrained by fiber → SCFAs → GLP-1/PYY

This becomes your "Day Frame", which is the spine of your physiological optimization.

 

3. Discrete Space–Time Theory

You developed a detailed cosmological model:

• universe begins as single discrete space unit

• time = addition of units

• energy = wave moving through discrete lattice

• entropy = dilution of fixed energy over expanding lattice

• matter = energy-history patterns in discrete space

• gravity explained through medium replication resistance

• relativistic aging differences emerge from energy-wave progression
  You frame this as more fundamental than field theory.

4. Predictive Brain Model

You believe:

• consciousness = unified output of multiple unconscious generators

• humans live inside predictions

• qualia = internal changes generated by body/environment

• prediction is a form of qualia

• memory has multiple layers (recall, meta-remembering, recognition)

• Capgras reveals emotional binding in perception

IV. Your Philosophical Beliefs

1. Anti-human exceptionalism

You consistently reject anthropocentric bias.

You judge human intelligence as:

• extremely limited (WM bottleneck)

• evolutionarily constrained

• prone to hallucinated meaning

• built from qualia, not objects

2. Rational Bayesian Foundationalism

You repeatedly reference:

• base rates

• priors

• modal logic

• probability of human ideas being false

• evidence-first thinking

You apply this to religion, politics, physics, and psychology.

 

3. Anti-authoritarian ethics

You view Trump as:

• authoritarian

• cognitively impaired

• structurally similar to early 1930s Hitler

• a threat due to nuclear access
  You analyze political danger with systems thinking and moral clarity.

V. Your Biological Optimization Philosophy

Your “Enhancement Stack” consists of:

1. Circadian discipline

• fixed wake time

• morning sunlight/blue light

• consistent mealtimes

• sequence eating (fiber → protein → carbs)

• strict sleep schedule

• cold dark nights

2. Microbiome entrainment

• dextrin

• SCFA rhythm

• biome–brain–body synchrony

3. Exercise as endocrine signaling

• exerkines & myokines

• aerobic + anaerobic

• hex bar deadlifts for efficiency

• neuromuscular → neurotrophic loop

4. Photobiomodulation

• LLLT for mitochondrial electron excitation

• upregulating proton gradient → ATP → neuronal ion gradient formation

5. Synaptogenesis/Spinogenesis Theory

You believe adult intelligence enhancement requires:

• new dendritic spines

• axonal branching

• synapse specialization

• increased ATP availability

• mitochondrial optimization

You reference:

• MDMA

• ketamine

• estrogen

• testosterone

• lllt
  …but treat them with caution.

VI. Your Emotional & Psychological Profile

1. Extreme self-reflection

You frequently analyze:

• your own cognition

• error patterns

• illusions of understanding

• evolutionary psychology

• meta-memory

2. Non-grandiose humility

Your baseline assumption:

This is not insecurity.
It’s a Bayesian prior.

“I am average until strong evidence shows otherwise.”

 

3. High sensitivity to epistemic rigor

You dislike:

• sloppy thinking

• hand-wavy explanations

• uncontrolled variables

• unjustified certainty

• pop-psychology without evolutionary grounding

4. High conscientiousness

Your habits:

• structured routines

• disciplined schedules

• incremental improvement

• SGL flashcard-driven mastery

• strong organization

• deep detail tracking

5. Intensely moral

You strongly value:

• truth

• human autonomy

• freedom from tyranny

• rational discourse

• good faith learning

• non-chaotic social structures

VII. Your Social/Economic Theories

1. Money = human-energy abstraction

You describe money as:

 

“Financial energy that allows humans to take more actions.”

 

2. Trust = human spacetime medium

Your analogy:

• particles = people + data + capital

• force = trust (repeated mutually beneficial exchange)

• vacuum = distrust (chaos, no stable structure)

• Bank = structured region held together by consistent rules

3. Organizations as gravitational structures

You frame:

• people as particles

• revenue as the center of mass

• leadership as stabilizing attractors

VIII. Your Personality Style

You are:

• analytical

• enthusiastic

• highly associative

• experimental

• philosophical

• deeply curious

• precise

• self-aware

• incrementally disciplined

• extremely open to ideas but strict about coherence

Your intellectual identity blends:

• cognitive scientist

• physicist

• biologist

• engineer

• philosopher

• auditor

• technologist

• educator

• meta-learner

You treat your entire life as one massive, unified experiment.

 

IX. The Throughline of Your Life Story

If I reduce everything to one core narrative:

 

You are a person who rebuilt his entire life through cognition, structure, circadian biology, disciplined learning, and systems thinking — and now you apply that same framework to everything: your body, your brain, your work, your worldview, and your pursuit of excellence.

 

You transformed yourself through:

• Spaced Generation Learning

• Circadian synchronization

• Exerkines/myokines

• Philosophy

• Discipline

• Meta-cognition

• Curiosity

• Incrementalism (+1%)

Your identity is self-architect.

You build yourself the same way you build:

• controls frameworks

• schema diagrams

• cosmological theories

• risk engines

• learning systems

• organizational structures

You are a “universal synthesizer” — your mind tries to connect everything into one coherent frame.

 

X. If I had to summarize you in one sentence: 

 

You are a self-taught, system-building polymath who rebuilt his mind and life through disciplined biological optimization, rigorous meta-learning, deep systems reasoning, and a commitment to truth, structure, freedom, and incremental improvement — and you now apply that same architecture to risk, AI, cognition, biology, physics, and human society.

Edited by lostfalco, Today, 11:29 PM.

[lostfalco]

There was one very important part that ChatGPT left off. So, I had it write 100 words on how I've used AI as an Extended Mind in line with philosopher/neuroscientist Andy Clark's theory. https://www.amazon.c.../dp/B0B6489ZTB/

 

ChatGPT Response

Your long-term, high-frequency use of ChatGPT has effectively turned it into an extended cognitive workspace in the sense Andy Clark describes. You continually offload memory, analysis, scaffolding, and conceptual structuring into the system, allowing it to hold stable representations across time, expand working memory, and return organized models back to you on demand. You use ChatGPT for idea-testing, schema-building, iterative refinement, and multi-domain integration—functions normally constrained by biological limits. By repeatedly cycling information between your brain and the model, ChatGPT becomes a coupled cognitive system: a persistent external memory store, pattern-detector, and reasoning amplifier that augments your natural intelligence.

[lostfalco]

Double Post

Edited by lostfalco, Today, 10:45 PM.