CyrilXBT's banner
CyrilXBT's profile picture

CyrilXBT

@cyrilXBT • 196,805 subscribers

building https://t.co/4rEItVdcLo AI • Tech • Crypto | Sharing what I see before everyone else does.

Shorts

sharing grok bots just jumped from “one day” to instantly public. i got early access and doom-scrolled 100 shared bot templates. [here are 6 i’d shamelessly steal:] →loops (matt) →master (farzad) →chief of staff (avid) →growth desk (avid) →forge (robert) →grok bot coach (amina) here’s the play to put your own grok bots in front of everyone. yeah, people can clone the bot. but they can’t clone the vault behind it, the handoffs you designed, or the taste you baked into the graph.

sharing grok bots just jumped from “one day” to instantly public. i got early access and doom-scrolled 100 shared bot templates. [here are 6 i’d shamelessly steal:] →loops (matt) →master (farzad) →chief of staff (avid) →growth desk (avid) →forge (robert) →grok bot coach (amina) here’s the play to put your own grok bots in front of everyone. yeah, people can clone the bot. but they can’t clone the vault behind it, the handoffs you designed, or the taste you baked into the graph.

25,463 views

Obsidian plus Vellum = a second brain that never stops thinking. Works while you sleep. Obsidian holds everything you know. Vellum reasons across it continuously. Every idea connected. Every pattern surfaced. Every insight waiting when you wake up. The people who build this tonight will never go back to thinking alone. Read this and Bookmark it now.

Obsidian plus Vellum = a second brain that never stops thinking. Works while you sleep. Obsidian holds everything you know. Vellum reasons across it continuously. Every idea connected. Every pattern surfaced. Every insight waiting when you wake up. The people who build this tonight will never go back to thinking alone. Read this and Bookmark it now.

260,682 views

Obsidian plus Vellum = a second brain that never stops thinking. Works while you sleep. Obsidian holds everything you know. Vellum reasons across it continuously. Every idea connected. Every pattern surfaced. Every insight waiting when you wake up. The people who build this tonight will never go back to thinking alone. Read this and Bookmark it now.

Obsidian plus Vellum = a second brain that never stops thinking. Works while you sleep. Obsidian holds everything you know. Vellum reasons across it continuously. Every idea connected. Every pattern surfaced. Every insight waiting when you wake up. The people who build this tonight will never go back to thinking alone. Read this and Bookmark it now.

35,003 views

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS. No Bloomberg terminal. No analytics desk. No team of analysts. A Mac Mini by the wall. An iPhone in his pocket. One local Obsidian vault. Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault. Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses. Every morning at 6AM, a brief lands in his inbox: - 3 trading ideas with confidence scores - The emerging thesis of the week - Any note that contradicts an active position The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence. Everything else runs without him. The monthly bill: $120 in API costs. The monthly return: approximately $30,000 into the account. Traditional quant funds pay teams of 8 people to produce the same flow of insights. He pays $120 and a Mac Mini. The full system breakdown is in the article below. Bookmark this before you pay for a Bloomberg subscription. Follow CyrilXBT for every solo operator setup that changes what one person can build.

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS. No Bloomberg terminal. No analytics desk. No team of analysts. A Mac Mini by the wall. An iPhone in his pocket. One local Obsidian vault. Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault. Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses. Every morning at 6AM, a brief lands in his inbox: - 3 trading ideas with confidence scores - The emerging thesis of the week - Any note that contradicts an active position The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence. Everything else runs without him. The monthly bill: $120 in API costs. The monthly return: approximately $30,000 into the account. Traditional quant funds pay teams of 8 people to produce the same flow of insights. He pays $120 and a Mac Mini. The full system breakdown is in the article below. Bookmark this before you pay for a Bloomberg subscription. Follow CyrilXBT for every solo operator setup that changes what one person can build.

129,718 views

SOMEONE JUST BUILT A PERSONAL AI DASHBOARD WITH CLAUDE AND IT DOES NOT FEEL LIKE A TOOL. It feels like an operating system for their entire life. One screen. Their calendar. Their tasks. Their goals. Their content pipeline. Their finances. Their health metrics. All connected. All updated in real time. All queryable in plain English. Not ten apps talking past each other. One intelligent surface that knows everything and surfaces what matters. They described what they wanted to Claude Design. Claude built the entire interface. Then they connected it to Opus 4.7 as the reasoning layer. Now instead of opening five apps to answer one question they just ask the dashboard. This is what personal computing looks like when the interface finally understands you. The people building their own AI OS right now will look back at this moment the way the first iPhone users looked back at 2007. You are early.

SOMEONE JUST BUILT A PERSONAL AI DASHBOARD WITH CLAUDE AND IT DOES NOT FEEL LIKE A TOOL. It feels like an operating system for their entire life. One screen. Their calendar. Their tasks. Their goals. Their content pipeline. Their finances. Their health metrics. All connected. All updated in real time. All queryable in plain English. Not ten apps talking past each other. One intelligent surface that knows everything and surfaces what matters. They described what they wanted to Claude Design. Claude built the entire interface. Then they connected it to Opus 4.7 as the reasoning layer. Now instead of opening five apps to answer one question they just ask the dashboard. This is what personal computing looks like when the interface finally understands you. The people building their own AI OS right now will look back at this moment the way the first iPhone users looked back at 2007. You are early.

194,438 views

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS. No Bloomberg terminal. No analytics desk. No team of analysts. A Mac Mini by the wall. An iPhone in his pocket. One local Obsidian vault. Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault. Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses. Every morning at 6AM, a brief lands in his inbox: - 3 trading ideas with confidence scores - The emerging thesis of the week - Any note that contradicts an active position The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence. Everything else runs without him. The monthly bill: $120 in API costs. The monthly return: approximately $30,000 into the account. Traditional quant funds pay teams of 8 people to produce the same flow of insights. He pays $120 and a Mac Mini. The full system breakdown is in the article below. Bookmark this before you pay for a Bloomberg subscription. Follow CyrilXBT for every solo operator setup that changes what one person can build.

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS. No Bloomberg terminal. No analytics desk. No team of analysts. A Mac Mini by the wall. An iPhone in his pocket. One local Obsidian vault. Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault. Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses. Every morning at 6AM, a brief lands in his inbox: - 3 trading ideas with confidence scores - The emerging thesis of the week - Any note that contradicts an active position The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence. Everything else runs without him. The monthly bill: $120 in API costs. The monthly return: approximately $30,000 into the account. Traditional quant funds pay teams of 8 people to produce the same flow of insights. He pays $120 and a Mac Mini. The full system breakdown is in the article below. Bookmark this before you pay for a Bloomberg subscription. Follow CyrilXBT for every solo operator setup that changes what one person can build.

117,631 views

Obsidian notes = raw material. This system = finished output. Five workflows that process every capture into something usable. Decision support. Writing fuel. Conversation material. Action triggers. Every note connected. Every idea surfaced at the right moment. Nothing captured and forgotten. The vault that produces instead of collects. Read this and Bookmark it now.

Obsidian notes = raw material. This system = finished output. Five workflows that process every capture into something usable. Decision support. Writing fuel. Conversation material. Action triggers. Every note connected. Every idea surfaced at the right moment. Nothing captured and forgotten. The vault that produces instead of collects. Read this and Bookmark it now.

92,767 views

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS. No Bloomberg terminal. No analytics desk. No team of analysts. A Mac Mini by the wall. An iPhone in his pocket. One local Obsidian vault. Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault. Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses. Every morning at 6AM, a brief lands in his inbox: - 3 trading ideas with confidence scores - The emerging thesis of the week - Any note that contradicts an active position The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence. Everything else runs without him. The monthly bill: $120 in API costs. The monthly return: approximately $30,000 into the account. Traditional quant funds pay teams of 8 people to produce the same flow of insights. He pays $120 and a Mac Mini. The full system breakdown is in the article below. Bookmark this before you pay for a Bloomberg subscription.

A CHINESE TRADER BUILT A SECOND BRAIN IN OBSIDIAN THAT GENERATES 3 TRADING IDEAS EVERY MORNING AT 6AM AND MADE $180,000 IN 6 MONTHS. No Bloomberg terminal. No analytics desk. No team of analysts. A Mac Mini by the wall. An iPhone in his pocket. One local Obsidian vault. Six N8N pipelines running 24/7, pulling every article he reads, every podcast he listens to, and every voice note he drops into a Telegram bot—directly into the vault. Every night, a neural network reads across 4,000 connected notes and finds the strongest connections between fresh information and old theses. Every morning at 6AM, a brief lands in his inbox: - 3 trading ideas with confidence scores - The emerging thesis of the week - Any note that contradicts an active position The system only wakes him up when a fresh note contradicts his thesis, or when an idea breaks 90% confidence. Everything else runs without him. The monthly bill: $120 in API costs. The monthly return: approximately $30,000 into the account. Traditional quant funds pay teams of 8 people to produce the same flow of insights. He pays $120 and a Mac Mini. The full system breakdown is in the article below. Bookmark this before you pay for a Bloomberg subscription.

46,087 views

Fable 5 dropping again is the biggest AI moment of the year. It’s also a usage limit trap if you don’t know what you’re doing. I just mapped out the full system to run it at 10x lower cost: - 10-80-10 framework - Model routing table - Loop engineering - Codex setup - Context memory - And every mistake that burns your limit in the first hour Don’t open Fable again until you read this.

Fable 5 dropping again is the biggest AI moment of the year. It’s also a usage limit trap if you don’t know what you’re doing. I just mapped out the full system to run it at 10x lower cost: - 10-80-10 framework - Model routing table - Loop engineering - Codex setup - Context memory - And every mistake that burns your limit in the first hour Don’t open Fable again until you read this.

33,834 views

SOMEONE VISUALIZED THEIR SECOND BRAIN AS A COLOR CODED CLUSTER YOU CAN ROTATE every note sized by weight, activity bleeding through in reds and oranges, months of thinking compressed into one shape you can spin around this article runs a different kind of second brain through the same idea, four agents instead of one static map, each one updating its own cluster every six hours as new notes, chats, and code sessions come in the map isn’t just a snapshot here, it keeps redrawing itself while you sleep full breakdown in the article below👇

SOMEONE VISUALIZED THEIR SECOND BRAIN AS A COLOR CODED CLUSTER YOU CAN ROTATE every note sized by weight, activity bleeding through in reds and oranges, months of thinking compressed into one shape you can spin around this article runs a different kind of second brain through the same idea, four agents instead of one static map, each one updating its own cluster every six hours as new notes, chats, and code sessions come in the map isn’t just a snapshot here, it keeps redrawing itself while you sleep full breakdown in the article below👇

29,386 views

BEFORE: $500 a month across six different tools. Switching between apps all day. Context scattered everywhere. AFTER: One Obsidian vault. One Claude subscription. Everything in one place. Same capability. Fraction of the cost. Zero app switching. The full setup is in the article below.

BEFORE: $500 a month across six different tools. Switching between apps all day. Context scattered everywhere. AFTER: One Obsidian vault. One Claude subscription. Everything in one place. Same capability. Fraction of the cost. Zero app switching. The full setup is in the article below.

36,525 views

Nemotron 3 Ultra versus DeepSeek V4 versus MiniMax M3 versus Qwen 3.7 Max. Same two prompts. Four frontier models. One honest comparison. Fast. Genuinely good. More impressive than the benchmarks suggested. Full results below. Bookmark this before your next model decision.

Nemotron 3 Ultra versus DeepSeek V4 versus MiniMax M3 versus Qwen 3.7 Max. Same two prompts. Four frontier models. One honest comparison. Fast. Genuinely good. More impressive than the benchmarks suggested. Full results below. Bookmark this before your next model decision.

30,261 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

this is honestly playing with fire i just watched an 18-year-old calmly explain how he’s pulling in $10k/month with AI while he’s literally asleep, and it hit me that 99% of people are walking past a wide-open door the setup is stupid simple: pick a YouTube channel that posts nonstop. drop the link into one tool. link TikTok, Instagram, YouTube Shorts. close the laptop. from there, the AI does the heavy lifting it monitors every new upload, carves out the strongest clips, adds captions, and blasts them across every platform. > 1M views ≈ $2,000 > no editing, no posting, no stress > 10 minutes to install, then it runs forever you’re not “making content.” you’re operating an automated content factory. the full step-by-step is in the article below exact tools, exact stack, exact moves save it.l
1:14
cyrilXBT's profile picture

this is honestly playing with fire i just watched an 18-year-old calmly explain how he’s pulling in $10k/month with AI while he’s literally asleep, and it hit me that 99% of people are walking past a wide-open door the setup is stupid simple: pick a YouTube channel that posts nonstop. drop the link into one tool. link TikTok, Instagram, YouTube Shorts. close the laptop. from there, the AI does the heavy lifting it monitors every new upload, carves out the strongest clips, adds captions, and blasts them across every platform. > 1M views ≈ $2,000 > no editing, no posting, no stress > 10 minutes to install, then it runs forever you’re not “making content.” you’re operating an automated content factory. the full step-by-step is in the article below exact tools, exact stack, exact moves save it.l

CyrilXBT

126,786 views • 4 days ago

this is insanely dangerous i just watched an 18-year-old calmly break down how he pulls in $10k/month with ai while he sleeps and now i’m convinced 99% of people are completely asleep at the wheel the whole system: find a youtube channel that uploads nonstop. paste the link into one tool. connect your tiktok, instagram, youtube shorts. shut the laptop. after that, ai runs the machine it monitors every new upload, rips out the high-retention moments, adds captions, and fires them out across every platform. > 1m views ≈ $2,000 > no editing, no posting, no hassle > 10 minutes to set up, then it prints on autopilot you’re not “creating content” anymore. you’re running a content assembly line. the full step-by-step is in the article below exact tools, exact stack, exact workflow
1:14
cyrilXBT's profile picture

this is insanely dangerous i just watched an 18-year-old calmly break down how he pulls in $10k/month with ai while he sleeps and now i’m convinced 99% of people are completely asleep at the wheel the whole system: find a youtube channel that uploads nonstop. paste the link into one tool. connect your tiktok, instagram, youtube shorts. shut the laptop. after that, ai runs the machine it monitors every new upload, rips out the high-retention moments, adds captions, and fires them out across every platform. > 1m views ≈ $2,000 > no editing, no posting, no hassle > 10 minutes to set up, then it prints on autopilot you’re not “creating content” anymore. you’re running a content assembly line. the full step-by-step is in the article below exact tools, exact stack, exact workflow

CyrilXBT

25,577 views • 1 day ago

INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 1 hour with this. Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything. The people who watch this tonight will wake up tomorrow with a skill that most people will not have in 2 years. The people who skip it will still be watching Netflix next year wondering why nothing in their life has changed. Your call.
59:51
cyrilXBT's profile picture

INSTEAD OF WATCHING NETFLIX TONIGHT. Spend 1 hour with this. Claude AI FULL COURSE that teaches you how to BUILD and AUTOMATE anything. The people who watch this tonight will wake up tomorrow with a skill that most people will not have in 2 years. The people who skip it will still be watching Netflix next year wondering why nothing in their life has changed. Your call.

CyrilXBT

4,076,973 views • 5 months ago

skip Netflix tonight and spend 44 minutes on this video it’s the sharpest breakdown I’ve found on how to make money with Grok Bot in 2026 I’ve watched $500 courses deliver less value than what’s packed into this one clip bookmark it now before it disappears into the scroll full walkthrough in the article below
44:20
cyrilXBT's profile picture

skip Netflix tonight and spend 44 minutes on this video it’s the sharpest breakdown I’ve found on how to make money with Grok Bot in 2026 I’ve watched $500 courses deliver less value than what’s packed into this one clip bookmark it now before it disappears into the scroll full walkthrough in the article below

CyrilXBT

41,130 views • 4 days ago

my #1 tip for using grok bot: give it an agent passport. an inbox, a calendar, a funded card with hard limits, a wallet, a signing key, a phone number, a domain, an x account. treat it like you're onboarding a real employee, not configuring a chatbot. one important correction before you start: don't give it a gmail account. google is actively disabling gmail accounts created by grok bot. use agentmail instead, it's an official plugin already listed in grok bot's browser, oauth, three minutes, 24 email tools ready. for payments, stripe's mcp server is real and live, letting an agent create customers, issue invoices, and process transactions through natural language, no custom integration required. then write the actual rules before any of this goes live. what can it read. what can it send. what can it spend. what needs your approval. who can shut it down. give it the passport. give it the rules. in that order.
0:20
cyrilXBT's profile picture

my #1 tip for using grok bot: give it an agent passport. an inbox, a calendar, a funded card with hard limits, a wallet, a signing key, a phone number, a domain, an x account. treat it like you're onboarding a real employee, not configuring a chatbot. one important correction before you start: don't give it a gmail account. google is actively disabling gmail accounts created by grok bot. use agentmail instead, it's an official plugin already listed in grok bot's browser, oauth, three minutes, 24 email tools ready. for payments, stripe's mcp server is real and live, letting an agent create customers, issue invoices, and process transactions through natural language, no custom integration required. then write the actual rules before any of this goes live. what can it read. what can it send. what can it spend. what needs your approval. who can shut it down. give it the passport. give it the rules. in that order.

CyrilXBT

24,311 views • 3 days ago

YOU CAN BUILD AN AI SECOND BRAIN IN 15 MINUTES. No coding experience. No $1000 course. Here is the entire setup. Step 1: Download Claude Desktop. Step 2: Download Obsidian. Step 3: Create a new vault and start dropping .MD files into it. Step 4: Tell Claude Code to connect to your vault using Karpathy's prompt: That is it. Your entire knowledge base becomes searchable, connectable, and queryable by the most powerful AI model on earth. Every note you have ever written. Every idea you have ever captured. Every resource you have ever saved. Claude reads all of it, finds connections you missed, and surfaces insights from your own thinking that you FORGOT you had. Most people use Claude as a search engine. The people building second brains use it as an INTELLIGENCE LAYER on top of everything they know. That gap is the gap between asking Google a question and having a research partner who has read everything you have ever written. Bookmark this. Build it tonight. Follow CyrilXBT
1:19
cyrilXBT's profile picture

YOU CAN BUILD AN AI SECOND BRAIN IN 15 MINUTES. No coding experience. No $1000 course. Here is the entire setup. Step 1: Download Claude Desktop. Step 2: Download Obsidian. Step 3: Create a new vault and start dropping .MD files into it. Step 4: Tell Claude Code to connect to your vault using Karpathy's prompt: That is it. Your entire knowledge base becomes searchable, connectable, and queryable by the most powerful AI model on earth. Every note you have ever written. Every idea you have ever captured. Every resource you have ever saved. Claude reads all of it, finds connections you missed, and surfaces insights from your own thinking that you FORGOT you had. Most people use Claude as a search engine. The people building second brains use it as an INTELLIGENCE LAYER on top of everything they know. That gap is the gap between asking Google a question and having a research partner who has read everything you have ever written. Bookmark this. Build it tonight. Follow CyrilXBT

CyrilXBT

260,035 views • 1 month ago

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: Stop using AI to write code. Use it to build a second brain. You point Claude Code at a folder. Drop in any source: an article, a transcript, a PDF. Claude reads it, links it, files it into a living wiki of everything you know. It compounds like interest. The more you feed it, the smarter it gets. Here's the whole thing: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.
1:48
cyrilXBT's profile picture

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: Stop using AI to write code. Use it to build a second brain. You point Claude Code at a folder. Drop in any source: an article, a transcript, a PDF. Claude reads it, links it, files it into a living wiki of everything you know. It compounds like interest. The more you feed it, the smarter it gets. Here's the whole thing: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.

CyrilXBT

323,267 views • 2 months ago

This is F**king dangerous Someone figured out how to get dramatically sharper reasoning out of Opus 4.8 with one setup. Here is how: Ask Claude to write you an "operating manual" for how it should reason through your work Create a new Claude Project and paste that .md into the Project instructions Run Opus 4.8 on High or Max effort Now the model reasons against a real framework instead of improvising every response. Same model. Far better output. And Opus 4.8 already costs a fraction of Fable 5. Save and bookmark this. Follow CyrilXBT
0:41
cyrilXBT's profile picture

This is F**king dangerous Someone figured out how to get dramatically sharper reasoning out of Opus 4.8 with one setup. Here is how: Ask Claude to write you an "operating manual" for how it should reason through your work Create a new Claude Project and paste that .md into the Project instructions Run Opus 4.8 on High or Max effort Now the model reasons against a real framework instead of improvising every response. Same model. Far better output. And Opus 4.8 already costs a fraction of Fable 5. Save and bookmark this. Follow CyrilXBT

CyrilXBT

198,085 views • 1 month ago

INSANE. Qwen 3.8 27B is now running locally on an RTX 4060 with just 8GB VRAM. 64,000 token context window using Unsloth's new IQ4_XS quant, only 14.6GB on disk. Prefill hits 150 tokens/sec, decode at 5 tokens/sec via native MTP. Just 25 GPU layers offloaded to stay inside 8GB - zero spillover. Quantized KV cache crushes the memory footprint. A model that beats Claude Opus 4.6 on several benchmarks. Running on a $300 GPU. Let that sink in. One flag before you post: that "beats Claude Opus 4.6 on several benchmarks" line is a strong, specific claim — if you don't have a source screenshot or benchmark link ready to drop in the replies, it'll get fact-checked fast and could undercut the post. Worth having the receipts on hand.
0:20
cyrilXBT's profile picture

INSANE. Qwen 3.8 27B is now running locally on an RTX 4060 with just 8GB VRAM. 64,000 token context window using Unsloth's new IQ4_XS quant, only 14.6GB on disk. Prefill hits 150 tokens/sec, decode at 5 tokens/sec via native MTP. Just 25 GPU layers offloaded to stay inside 8GB - zero spillover. Quantized KV cache crushes the memory footprint. A model that beats Claude Opus 4.6 on several benchmarks. Running on a $300 GPU. Let that sink in. One flag before you post: that "beats Claude Opus 4.6 on several benchmarks" line is a strong, specific claim — if you don't have a source screenshot or benchmark link ready to drop in the replies, it'll get fact-checked fast and could undercut the post. Worth having the receipts on hand.

CyrilXBT

49,494 views • 14 days ago

Andrew Ng: “AI agents are doing almost 100% of my tasks now - the hype has exceeded my expectations. in 3-6 months, we’ll all be building graphs to orchestrate self-improving agents. No more prompting.” In a 40-minute talk, Andrew Ng explains how to build self-improving agentic systems from scratch. Worth more than a $500 agentic course. Watch this video, then read the article below on how to become a graph architect.
40:37
cyrilXBT's profile picture

Andrew Ng: “AI agents are doing almost 100% of my tasks now - the hype has exceeded my expectations. in 3-6 months, we’ll all be building graphs to orchestrate self-improving agents. No more prompting.” In a 40-minute talk, Andrew Ng explains how to build self-improving agentic systems from scratch. Worth more than a $500 agentic course. Watch this video, then read the article below on how to become a graph architect.

CyrilXBT

99,902 views • 1 month ago

how is this even allowed i dropped my $200/mo claude plan for deepseek harness, it’s basically free the whole thing runs on one simple rule: everything is a plugin [setup takes 3 minutes, here’s the playbook] 1. clone/install the repo called deepseek-harness 2. skim the architecture docs 3. that’s it, you’re live bookmark this and hand it to your agent right now.
1:11
cyrilXBT's profile picture

how is this even allowed i dropped my $200/mo claude plan for deepseek harness, it’s basically free the whole thing runs on one simple rule: everything is a plugin [setup takes 3 minutes, here’s the playbook] 1. clone/install the repo called deepseek-harness 2. skim the architecture docs 3. that’s it, you’re live bookmark this and hand it to your agent right now.

CyrilXBT

42,225 views • 18 days ago

Obsidian trading journal = a system that studies every trade you make. Works while you sleep. Every pattern identified. Every edge validated. Every mistake documented so it never costs you twice. After 30 days it knows your trading better than you do. After 90 days it is preventing losses your past positions already predicted. The people who build this tonight will never trade the same way again. Read this and Bookmark it now.
0:44
cyrilXBT's profile picture

Obsidian trading journal = a system that studies every trade you make. Works while you sleep. Every pattern identified. Every edge validated. Every mistake documented so it never costs you twice. After 30 days it knows your trading better than you do. After 90 days it is preventing losses your past positions already predicted. The people who build this tonight will never trade the same way again. Read this and Bookmark it now.

CyrilXBT

205,737 views • 3 months ago

Obsidian + Claude Code = 24/7 personal operating system. Works while you sleep. The people who build this tonight will never work the same way again. Watch it and Bookmark it now.
14:43
cyrilXBT's profile picture

Obsidian + Claude Code = 24/7 personal operating system. Works while you sleep. The people who build this tonight will never work the same way again. Watch it and Bookmark it now.

CyrilXBT

233,784 views • 3 months ago

What the fuck bro talking about 😭
0:39
cyrilXBT's profile picture

What the fuck bro talking about 😭

CyrilXBT

561,563 views • 10 months ago

Hermes Agent. Zero to full autonomous operation. One complete course. Installation. Skills. Memory. MCP. Scheduler. Multi-agent. Works while you sleep. The people who build this system will never manually operate a content, research, or business workflow again. The compounding starts from the first automated skill that runs. Read this and bookmark it now.
0:38
cyrilXBT's profile picture

Hermes Agent. Zero to full autonomous operation. One complete course. Installation. Skills. Memory. MCP. Scheduler. Multi-agent. Works while you sleep. The people who build this system will never manually operate a content, research, or business workflow again. The compounding starts from the first automated skill that runs. Read this and bookmark it now.

CyrilXBT

176,900 views • 3 months ago

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy one of the clearest minds in AI just released a 2‑hour breakdown of how he actually uses LLMs every day. • 00:00 — LLMs, explained like you’re busy • 22:49 — picking the right model (for real) • 42:00 — the single prompt that powers deep research • 1:13:57 — writing code with LLMs without the chaos • 1:37:04 — turning NotebookLM into a podcast machine If you watch this end to end, you’ll walk away with more practical LLM skill than many “AI engineers” collect over years. Save it. Carve out two hours today—no excuses. Then hit the article below.
2:11:07
cyrilXBT's profile picture

Don't waste 2 years learning to use LLMs like Claude & ChatGPT. Andrej Karpathy one of the clearest minds in AI just released a 2‑hour breakdown of how he actually uses LLMs every day. • 00:00 — LLMs, explained like you’re busy • 22:49 — picking the right model (for real) • 42:00 — the single prompt that powers deep research • 1:13:57 — writing code with LLMs without the chaos • 1:37:04 — turning NotebookLM into a podcast machine If you watch this end to end, you’ll walk away with more practical LLM skill than many “AI engineers” collect over years. Save it. Carve out two hours today—no excuses. Then hit the article below.

CyrilXBT

51,835 views • 26 days ago

Anthropic's CEO: "software engineering will be fully automated in 12 months." two types of people right now: type 1: opens Claude, types something, gets an answer, closes the tab. thinks they're using AI. type 2: knows the hidden features, settings, and shortcuts. runs Claude like a power tool. type 1 gets surprised in 12 months. type 2 built the advantage already. bookmark this. read it today.
0:58
cyrilXBT's profile picture

Anthropic's CEO: "software engineering will be fully automated in 12 months." two types of people right now: type 1: opens Claude, types something, gets an answer, closes the tab. thinks they're using AI. type 2: knows the hidden features, settings, and shortcuts. runs Claude like a power tool. type 1 gets surprised in 12 months. type 2 built the advantage already. bookmark this. read it today.

CyrilXBT

54,895 views • 1 month ago

Six months ago my Obsidian vault had 2,000 notes and I could not find anything. I rebuilt the entire structure in one afternoon using this exact system. I have not lost a single idea since. The people who set this up today will wonder how they ever worked without it.
0:53
cyrilXBT's profile picture

Six months ago my Obsidian vault had 2,000 notes and I could not find anything. I rebuilt the entire structure in one afternoon using this exact system. I have not lost a single idea since. The people who set this up today will wonder how they ever worked without it.

CyrilXBT

155,701 views • 3 months ago

OBSIDIAN PLUS HERMES AGENT IS THE MOST POWERFUL PERSONAL OPERATING SYSTEM AVAILABLE RIGHT NOW AND ALMOST NOBODY HAS BUILT IT YET. Obsidian holds everything you know permanently. Hermes reads it, reasons across it, and runs your most important workflows automatically. Morning briefs generated from your actual vault. Inbox processed every evening without you touching it. Project health monitored every Monday. Weekly synthesis ready every Sunday. One system. Thinks. Remembers. Runs your life. Read this and Bookmark it now.
0:53
cyrilXBT's profile picture

OBSIDIAN PLUS HERMES AGENT IS THE MOST POWERFUL PERSONAL OPERATING SYSTEM AVAILABLE RIGHT NOW AND ALMOST NOBODY HAS BUILT IT YET. Obsidian holds everything you know permanently. Hermes reads it, reasons across it, and runs your most important workflows automatically. Morning briefs generated from your actual vault. Inbox processed every evening without you touching it. Project health monitored every Monday. Weekly synthesis ready every Sunday. One system. Thinks. Remembers. Runs your life. Read this and Bookmark it now.

CyrilXBT

122,498 views • 3 months ago

Holy sh*t this is gold THE FULL GRAPH ENGINEERING PIPELINE, GROUNDED IN REAL, OPEN SOURCE WORK. Representation. Ontology. Entity extraction. Relations. Events. Quality gate. Fusion. Embeddings. Memory your agent can actually traverse. Real repos already cover this end to end. Strwythura walks through the full ontology pipeline with entity resolution and embedding-enhanced GraphRAG. llm2kg covers entity and relationship extraction against an ontology, Neo4j storage with vector embeddings, and a ReAct agent that queries the graph directly. No PhD required. Real, working code you can run against your own data today.
1:03
cyrilXBT's profile picture

Holy sh*t this is gold THE FULL GRAPH ENGINEERING PIPELINE, GROUNDED IN REAL, OPEN SOURCE WORK. Representation. Ontology. Entity extraction. Relations. Events. Quality gate. Fusion. Embeddings. Memory your agent can actually traverse. Real repos already cover this end to end. Strwythura walks through the full ontology pipeline with entity resolution and embedding-enhanced GraphRAG. llm2kg covers entity and relationship extraction against an ontology, Neo4j storage with vector embeddings, and a ReAct agent that queries the graph directly. No PhD required. Real, working code you can run against your own data today.

CyrilXBT

49,462 views • 1 month ago