Soul | Tech | Sage

26.1K posts

Soul | Tech | Sage banner
Soul | Tech | Sage

Soul | Tech | Sage

@SoulTechSage

shut up and save the planet

Hollywood East, NC เข้าร่วม Temmuz 2021
573 กำลังติดตาม1.5K ผู้ติดตาม
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
Like Nick Land said, capitalism is dehumanizing the world. I suggest find a shamanic tribe with herbal elixirs. Then apply your AI skillset to improve your community. Imagine if everyone started to do this.
John Ennis@johnennis

I think one of the biggest challenges when it comes to going hard into using AI is loneliness I am learning all these awesome things and becoming super capable But the set of people that I can really talk to about it is very small Is anyone else having this experience?

English
0
0
0
10
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
Hey @grok... is this a hyperstition emerging from the breakdown of feedback loops? What stage of the cybernetic agenda are we currently in? In term of the singularity, what role does this play? In terms of the Simulation, any foreseeable glitches in the matrix?
Brivael - FR@BrivaelFr

Je crois qu'on ne mesure pas ce qu'Elon Musk est en train de construire avec X. Tous les médias de l'histoire ont été couplés à une culture, une langue, une bulle géographique. Le Monde parle aux Français. Le NYT parle aux Américains. NHK parle aux Japonais. Chaque média filtre le réel à travers le prisme de sa culture locale. X est en train de devenir le premier média de l'humanité. Pas d'un pays. De l'espèce. Je le vis en temps réel. Mes posts en français se font RT par des Japonais, répondre par des Brésiliens, citer par des Américains. Des conversations qui n'auraient jamais existé il y a 5 ans. Un libertarien français qui débat avec un ingénieur de Tokyo et un entrepreneur de Sao Paulo sous le même tweet. Pas traduit par un éditeur. Traduit instantanément par l'IA, en un clic. Les bulles de filtre culturelles sont en train d'exploser. Et je pense qu'on sous-estime massivement les effets composés de ça. Quand une idée peut traverser un océan en 3 secondes, quand un argument sourcé posté à Paris peut être vérifié par un économiste à Singapour et amplifié par un développeur à Austin dans la même heure, le coût de propagation d'une bonne idée tend vers zéro. Et c'est catastrophique pour un type d'acteur très précis : les médias qui ont construit leur business model sur le monopole de l'information locale. Ceux qui pouvaient raconter n'importe quoi sur "ce qui se passe ailleurs" parce que personne ne pouvait vérifier. Quand un journaliste français écrit que "le modèle américain ne marche pas", maintenant il y a 50 Américains dans les réponses avec des sources. Quand un éditorialiste dit que "le Danemark prouve que le socialisme fonctionne", il y a un Danois qui explique que le Danemark est 10e en liberté économique mondiale. Le fact-checking n'est plus un département. C'est un effet réseau. Les médias honnêtes n'ont rien à craindre de ça. Les médias qui vendaient une narration protégée par l'ignorance géographique de leur audience vont avoir un problème existentiel. Parce qu'on ne peut plus mentir à l'échelle locale quand le monde entier regarde.

English
1
0
0
18
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
@BrivaelFr Hey @grok is this a hyperstition emerging from the breakdown of feedback loops? What stage of the cybernetic agenda are we currently in? In term of the singularity, what role does this play? In terms of the Simulation, any foreseeable glitches in the matrix?
English
1
0
0
16
Brivael - FR
Brivael - FR@BrivaelFr·
Je crois qu'on ne mesure pas ce qu'Elon Musk est en train de construire avec X. Tous les médias de l'histoire ont été couplés à une culture, une langue, une bulle géographique. Le Monde parle aux Français. Le NYT parle aux Américains. NHK parle aux Japonais. Chaque média filtre le réel à travers le prisme de sa culture locale. X est en train de devenir le premier média de l'humanité. Pas d'un pays. De l'espèce. Je le vis en temps réel. Mes posts en français se font RT par des Japonais, répondre par des Brésiliens, citer par des Américains. Des conversations qui n'auraient jamais existé il y a 5 ans. Un libertarien français qui débat avec un ingénieur de Tokyo et un entrepreneur de Sao Paulo sous le même tweet. Pas traduit par un éditeur. Traduit instantanément par l'IA, en un clic. Les bulles de filtre culturelles sont en train d'exploser. Et je pense qu'on sous-estime massivement les effets composés de ça. Quand une idée peut traverser un océan en 3 secondes, quand un argument sourcé posté à Paris peut être vérifié par un économiste à Singapour et amplifié par un développeur à Austin dans la même heure, le coût de propagation d'une bonne idée tend vers zéro. Et c'est catastrophique pour un type d'acteur très précis : les médias qui ont construit leur business model sur le monopole de l'information locale. Ceux qui pouvaient raconter n'importe quoi sur "ce qui se passe ailleurs" parce que personne ne pouvait vérifier. Quand un journaliste français écrit que "le modèle américain ne marche pas", maintenant il y a 50 Américains dans les réponses avec des sources. Quand un éditorialiste dit que "le Danemark prouve que le socialisme fonctionne", il y a un Danois qui explique que le Danemark est 10e en liberté économique mondiale. Le fact-checking n'est plus un département. C'est un effet réseau. Les médias honnêtes n'ont rien à craindre de ça. Les médias qui vendaient une narration protégée par l'ignorance géographique de leur audience vont avoir un problème existentiel. Parce qu'on ne peut plus mentir à l'échelle locale quand le monde entier regarde.
Français
2.2K
11.1K
49.6K
47.6M
Soul | Tech | Sage รีทวีตแล้ว
Paul J. von Hartmann
Paul J. von Hartmann@projectpeace·
@ShaunSummersgil @RealDebunkThis Used properly, #Cannabis promotes health & peaceful social interaction. Moderate alcohol consumption conveys benefits for some people too. Teaching respect & responsibility, while imposing selective restraint for misuse of mind-altering substances are the remedies for abuse.
English
3
2
8
104
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
“The water’s getting warm so you might as well swim They say the world’s on fire, how bout yours? That’s the way I like it cuz I never get bored” Smash Mouth
English
0
0
0
13
Soul | Tech | Sage รีทวีตแล้ว
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
Fantasia has no boundaries. Don’t you know anything about Fantasia? It’s the world of human fantasy. Every part, every creature, is a piece of the dreams and hopes of mankind. Therefore…it has no boundary. 🐺 (The Never Ending Story)
English
0
2
0
128
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
Humans are most human when they are in the moment observing what nature is offering.
Soul | Tech | Sage tweet media
English
0
0
0
11
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
“Evolution is the law of life Number is the law of the universe Unity is the law of God” Pythagoras
Soul | Tech | Sage tweet media
English
0
0
0
23
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
This was listed in a community forum… Do you agree or disagree with the response? “I'm currently a high school student about to get my license and been stressing about paying for insurance, gas, etc. I'm hoping to get a job in this month of April, please give me some advice for job searching. Thank you in advance!!” 👇 * 🪄 Get off social media and go to the library 📚 read books on philosophy, science fiction, take notes and journal. Increase your cognition. Stay away from devices until you’ve read over 100+ tangible books. 📝 The world is accelerating, so train yourself on the right feedback loops to sustain your forward progress in life in terms of self awareness and soulful growth.*
Soul | Tech | Sage tweet media
English
0
0
0
11
Soul | Tech | Sage รีทวีตแล้ว
Michael Pollan
Michael Pollan@michaelpollan·
Mind-blowing science: Complete biosynthesis of psychedelic tryptamines from three kingdoms in plants | Science Advances science.org/doi/10.1126/sc…
English
7
21
153
14.9K
Soul | Tech | Sage
Soul | Tech | Sage@SoulTechSage·
@kepano @karpathy We have projects, custom instructions, and pseudo-agents … notion, mem, obsidian, notebook etc. His insights are two years late imo.
English
0
0
0
65
kepano
kepano@kepano·
I like @karpathy's Obsidian setup as a way to mitigate contamination risks. Keep your personal vault clean and create a messy vault for your agents. I prefer my personal Obsidian vault to be high signal:noise, and for all the content to have known origins. Keeping a separation between your personally-created artifacts and agent-created artifacts prevents contaminating your primary vault with ideas you can't source. If you let the two mix too much it will likely make Obsidian harder to use as a representation of *your* thoughts. Search, bases, quick switcher, backlinks, graph, etc, will no longer be scoped to your knowledge. Only once your agent-facing workflow produces useful artifacts would I bring those into the primary vault.
Andrej Karpathy@karpathy

LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.

English
81
163
2.9K
451.2K
Andrej Karpathy
Andrej Karpathy@karpathy·
LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fraction of my recent token throughput is going less into manipulating code, and more into manipulating knowledge (stored as markdown and images). The latest LLMs are quite good at it. So: Data ingest: I index source documents (articles, papers, repos, datasets, images, etc.) into a raw/ directory, then I use an LLM to incrementally "compile" a wiki, which is just a collection of .md files in a directory structure. The wiki includes summaries of all the data in raw/, backlinks, and then it categorizes data into concepts, writes articles for them, and links them all. To convert web articles into .md files I like to use the Obsidian Web Clipper extension, and then I also use a hotkey to download all the related images to local so that my LLM can easily reference them. IDE: I use Obsidian as the IDE "frontend" where I can view the raw data, the the compiled wiki, and the derived visualizations. Important to note that the LLM writes and maintains all of the data of the wiki, I rarely touch it directly. I've played with a few Obsidian plugins to render and view data in other ways (e.g. Marp for slides). Q&A: Where things get interesting is that once your wiki is big enough (e.g. mine on some recent research is ~100 articles and ~400K words), you can ask your LLM agent all kinds of complex questions against the wiki, and it will go off, research the answers, etc. I thought I had to reach for fancy RAG, but the LLM has been pretty good about auto-maintaining index files and brief summaries of all the documents and it reads all the important related data fairly easily at this ~small scale. Output: Instead of getting answers in text/terminal, I like to have it render markdown files for me, or slide shows (Marp format), or matplotlib images, all of which I then view again in Obsidian. You can imagine many other visual output formats depending on the query. Often, I end up "filing" the outputs back into the wiki to enhance it for further queries. So my own explorations and queries always "add up" in the knowledge base. Linting: I've run some LLM "health checks" over the wiki to e.g. find inconsistent data, impute missing data (with web searchers), find interesting connections for new article candidates, etc., to incrementally clean up the wiki and enhance its overall data integrity. The LLMs are quite good at suggesting further questions to ask and look into. Extra tools: I find myself developing additional tools to process the data, e.g. I vibe coded a small and naive search engine over the wiki, which I both use directly (in a web ui), but more often I want to hand it off to an LLM via CLI as a tool for larger queries. Further explorations: As the repo grows, the natural desire is to also think about synthetic data generation + finetuning to have your LLM "know" the data in its weights instead of just context windows. TLDR: raw data from a given number of sources is collected, then compiled by an LLM into a .md wiki, then operated on by various CLIs by the LLM to do Q&A and to incrementally enhance the wiki, and all of it viewable in Obsidian. You rarely ever write or edit the wiki manually, it's the domain of the LLM. I think there is room here for an incredible new product instead of a hacky collection of scripts.
English
2.7K
6.5K
54.9K
19.4M
Soul | Tech | Sage รีทวีตแล้ว
Paul J. von Hartmann
Paul J. von Hartmann@projectpeace·
1/15 🌿 Is Cannabis the Biblical “Tree of Life” in Revelation 22:2? After a deep dive with @grok, the objective conclusion is shocking: Cannabis aligns FAR better than calamus or any other plant. 🧵👇🏼
Paul J. von Hartmann tweet media
English
4
16
44
2.5K
Soul | Tech | Sage รีทวีตแล้ว
andrei saioc
andrei saioc@asaio87·
What if the quality of AI code degrades over time ?
English
91
6
138
21.4K
Soul | Tech | Sage รีทวีตแล้ว
Brave
Brave@brave·
Nearly 700,000 OpenClaw users have signed up to use Brave Search API! This is not only a huge milestone for our API but signals a fundamental shift in the internet.
Brave tweet media
English
44
49
929
97.4K
Soul | Tech | Sage รีทวีตแล้ว
Michael Saylor
Michael Saylor@saylor·
Three perfect products: A car that drives you. A robot that serves you. An asset that pays you.
English
1.1K
1.7K
15K
697.5K