Kirill's banner
Kirill's profile picture

Kirill

@kirillk_web340,420 subscribers

AI Influencer × Web3 Creator Focused on Crypto & AI tools Claude · Bots · Wallet flows · Probabilities my tg @kirillk_h

Shorts

Anthropic CEO after realizing a Chinese dev explained loop vs graph engineering better than anyone at the company

Anthropic CEO after realizing a Chinese dev explained loop vs graph engineering better than anyone at the company

1,423,818 görüntüleme

A SINGLE CLAUDE SKILL JUST HIT 58,000 STARS IN ONE WEEK ON GITHUB. 58,000 stars. 2.9k forks. free. Bookmark this before you forget. Your Claude will start working differently. It makes Claude think like the laziest senior dev on the team. 54% less code. 20% cheaper. 27% faster. swap it into your Claude Code today. Link below. Claude → Ponytail → Less Code → Lower Cost → Money

A SINGLE CLAUDE SKILL JUST HIT 58,000 STARS IN ONE WEEK ON GITHUB. 58,000 stars. 2.9k forks. free. Bookmark this before you forget. Your Claude will start working differently. It makes Claude think like the laziest senior dev on the team. 54% less code. 20% cheaper. 27% faster. swap it into your Claude Code today. Link below. Claude → Ponytail → Less Code → Lower Cost → Money

4,178,741 görüntüleme

A SINGLE CLAUDE.md FILE JUST HIT #1 ON GITHUB TRENDING. 82,100 stars. 7.8k forks. zero dependencies. Bookmark this before you forget. And your Claude will start working differently. 4 principles. one file. Karpathy's LLM coding habits. distilled. > think before coding. > simplicity first. > surgical edits only. > goal-driven targets before starting. swap it into your CLAUDE.md today. your Claude Code becomes a different tool. Read it today. Link below. Claude → Skills → CLAUDE.md → Better Code → Better Systems → Money

A SINGLE CLAUDE.md FILE JUST HIT #1 ON GITHUB TRENDING. 82,100 stars. 7.8k forks. zero dependencies. Bookmark this before you forget. And your Claude will start working differently. 4 principles. one file. Karpathy's LLM coding habits. distilled. > think before coding. > simplicity first. > surgical edits only. > goal-driven targets before starting. swap it into your CLAUDE.md today. your Claude Code becomes a different tool. Read it today. Link below. Claude → Skills → CLAUDE.md → Better Code → Better Systems → Money

4,652,235 görüntüleme

> be Andrew Ng > Stanford. teach ML to a few hundred students. > 2011. put the course online instead. 100,000 sign up. > realize the classroom was never the limit > co-found Coursera. millions learn from you. > build Google Brain. lead AI at Baidu. > everyone chases the flashiest model > you keep teaching the next wave to build > agents get hyped. marketers slap "agentic" on everything. > you cut through it with a course on what actually works > knowledge graphs. multi-agent systems. real architecture. > while everyone argues on X about loops vs graphs > you already shipped the lesson > the man who taught the internet machine learning > just did it again for agents > different game.

> be Andrew Ng > Stanford. teach ML to a few hundred students. > 2011. put the course online instead. 100,000 sign up. > realize the classroom was never the limit > co-found Coursera. millions learn from you. > build Google Brain. lead AI at Baidu. > everyone chases the flashiest model > you keep teaching the next wave to build > agents get hyped. marketers slap "agentic" on everything. > you cut through it with a course on what actually works > knowledge graphs. multi-agent systems. real architecture. > while everyone argues on X about loops vs graphs > you already shipped the lesson > the man who taught the internet machine learning > just did it again for agents > different game.

249,057 görüntüleme

> be Anthropic CEO > leave OpenAI. can't trust the values. > start Anthropic with your sister. > build Claude. build Mythos. > first testers: "this is a super weapon. don't release it." > lose billions keeping it locked. > Pentagon offers $200M. wants you to remove safety filters. > you say no. they blacklist you. Trump calls you a lunatic. > release Fable 5. Mythos-class. finally public. > someone finds a jailbreak into the cybersecurity layer. > US government: "suspend access for all foreign nationals." > including your own employees. > disable it. immediately. > sit down for a 47-minute interview. > tell them everything. > 90% of code written by Claude. > civilizational collapse: 10-25%. > valuation: $965 billion. > started because you couldn't trust someone's values. > now governments decide what you can build. > different game.

> be Anthropic CEO > leave OpenAI. can't trust the values. > start Anthropic with your sister. > build Claude. build Mythos. > first testers: "this is a super weapon. don't release it." > lose billions keeping it locked. > Pentagon offers $200M. wants you to remove safety filters. > you say no. they blacklist you. Trump calls you a lunatic. > release Fable 5. Mythos-class. finally public. > someone finds a jailbreak into the cybersecurity layer. > US government: "suspend access for all foreign nationals." > including your own employees. > disable it. immediately. > sit down for a 47-minute interview. > tell them everything. > 90% of code written by Claude. > civilizational collapse: 10-25%. > valuation: $965 billion. > started because you couldn't trust someone's values. > now governments decide what you can build. > different game.

1,673,460 görüntüleme

> use Claude Code for months > Claude makes wrong assumptions every session > overwrites code I didn't ask to touch > adds 500 lines when 50 would do > find the CLAUDE.md file on GitHub trending > 82,000 stars. one file. > paste it into my project > first task > wait. it asked before assuming? > only touched what I asked? > 50 lines instead of 500? > pause. read the 4 principles. > think about every broken diff I reviewed > every rewrite I didn't ask for > every session that ran with wrong assumptions > it didn't have to be like this > one file. everything changes. > skill issue discovered

> use Claude Code for months > Claude makes wrong assumptions every session > overwrites code I didn't ask to touch > adds 500 lines when 50 would do > find the CLAUDE.md file on GitHub trending > 82,000 stars. one file. > paste it into my project > first task > wait. it asked before assuming? > only touched what I asked? > 50 lines instead of 500? > pause. read the 4 principles. > think about every broken diff I reviewed > every rewrite I didn't ask for > every session that ran with wrong assumptions > it didn't have to be like this > one file. everything changes. > skill issue discovered

2,499,982 görüntüleme

Claude users after making their first $10K from the leaked $62,000/month YouTube guide:

Claude users after making their first $10K from the leaked $62,000/month YouTube guide:

936,389 görüntüleme

THE CEO OF OBSIDIAN JUST DROPPED HIS OWN CLAUDE SKILLS. 44,500 stars. 3k forks. free. Save this before you forget. Your Claude will work differently. Written by kepano — the guy who built Obsidian. so they respect the real formats: Markdown, Bases, JSON Canvas, wikilinks. drop them in once. say "summarize my notes on Karpathy" — the right skill fires on its own. no config. Claude → Obsidian Skills → Second Brain → Effortless

THE CEO OF OBSIDIAN JUST DROPPED HIS OWN CLAUDE SKILLS. 44,500 stars. 3k forks. free. Save this before you forget. Your Claude will work differently. Written by kepano — the guy who built Obsidian. so they respect the real formats: Markdown, Bases, JSON Canvas, wikilinks. drop them in once. say "summarize my notes on Karpathy" — the right skill fires on its own. no config. Claude → Obsidian Skills → Second Brain → Effortless

292,132 görüntüleme

me seeing a Claude bot that made $1.5M in a month and someone dropped a full guide my reaction:

me seeing a Claude bot that made $1.5M in a month and someone dropped a full guide my reaction:

1,992,461 görüntüleme

> be Kimi Founder > Zhilin Yang. nobody in the West knows your name. > build K1. K2. K2.5. K2.6. K2.7. > each one sets the open-source record > everyone says China can't reach the frontier > raise $2B. hit $20B valuation. > keep your head down. keep shipping. > July 16. drop K3. > 2.8 trillion parameters. > the biggest open model ever released. > 1 million token context. native multimodal. > Kimi Delta Attention — 6.3x faster decoding. > Artificial Analysis ranks it #4 overall. > right behind GPT-5.6 Sol and Fable 5. > open weights July 27. free for anyone. > the closed labs charge for the frontier. > you gave it away. > different game.

> be Kimi Founder > Zhilin Yang. nobody in the West knows your name. > build K1. K2. K2.5. K2.6. K2.7. > each one sets the open-source record > everyone says China can't reach the frontier > raise $2B. hit $20B valuation. > keep your head down. keep shipping. > July 16. drop K3. > 2.8 trillion parameters. > the biggest open model ever released. > 1 million token context. native multimodal. > Kimi Delta Attention — 6.3x faster decoding. > Artificial Analysis ranks it #4 overall. > right behind GPT-5.6 Sol and Fable 5. > open weights July 27. free for anyone. > the closed labs charge for the frontier. > you gave it away. > different game.

413,178 görüntüleme

Claude users after watching this graph engineering course

Claude users after watching this graph engineering course

109,173 görüntüleme

CANCEL your Tuesday morning plans. You NEED to: Watch the Anthropic engineer who wrote "Building Effective Agents" — 14 minutes Take notes. rewind. watch again. Build your first real agent — not a chatbot. a system. Stop guessing how agents actually work — he shows you. Read the 33-page Claude Skills guide — 1 sitting Never build another agent from scratch again You had Monday to start. You didn't. Now you're two days behind. Both guides are below.

CANCEL your Tuesday morning plans. You NEED to: Watch the Anthropic engineer who wrote "Building Effective Agents" — 14 minutes Take notes. rewind. watch again. Build your first real agent — not a chatbot. a system. Stop guessing how agents actually work — he shows you. Read the 33-page Claude Skills guide — 1 sitting Never build another agent from scratch again You had Monday to start. You didn't. Now you're two days behind. Both guides are below.

1,094,286 görüntüleme

> you open X > see a guide about a Claude bot > ignore it > it seems too complicated > the numbers don’t feel real ($1,000 → $1.5M) > keep scrolling > days pass > everyone’s talking about agents > automation > a friend makes $10k in a single day > you feel like you missed something > you did > it was that guide > they read it > you didn’t

> you open X > see a guide about a Claude bot > ignore it > it seems too complicated > the numbers don’t feel real ($1,000 → $1.5M) > keep scrolling > days pass > everyone’s talking about agents > automation > a friend makes $10k in a single day > you feel like you missed something > you did > it was that guide > they read it > you didn’t

1,184,924 görüntüleme

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money

ANTHROPIC JUST DROPPED THE OFFICIAL GUIDE TO PROMPTING FABLE 5. This is the most important prompting framework I've seen. Bookmark this before you forget. Most people treat Fable 5 like a chatbot. That's the mistake. > don't over-engineer prompts — it degrades output. > use /loop for autonomous multi-step work. > give it the goal, not step-by-step commands. > add a memory file. it learns from past runs. > spin up 50+ subagents for complex tasks. Fable 5 isn't an assistant. it's a consultant that leads the work. Read it before you write another prompt. Claude → Fable 5 → Autonomous Work → Real Output → Money

415,748 görüntüleme

> you close your laptop for a few days > leave $1,000 running on a Claude bot > come back > $1,000 → $55K > the agent was trading > pulling odds > comparing to live data > spotting mispriced contracts > 50–300% per trade > short-term BTC markets > setup time: ~15 minutes > you explained the idea once > Claude built the agent > it made the trades

> you close your laptop for a few days > leave $1,000 running on a Claude bot > come back > $1,000 → $55K > the agent was trading > pulling odds > comparing to live data > spotting mispriced contracts > 50–300% per trade > short-term BTC markets > setup time: ~15 minutes > you explained the idea once > Claude built the agent > it made the trades

554,130 görüntüleme

> be Kimi K3 > drop July 16 > 2.8 trillion parameters > the biggest open model ever released > 1 million token context. native multimodal. > Kimi Delta Attention — 6.3x faster decoding > priced at a third of Fable 5 > people rush in so fast the GPUs hit their limit in 48 hours > Moonshot pauses new subscriptions just to keep you running > the closed labs charge for the frontier > you're about to be free > open weights drop July 27 > anyone can run you. anywhere. > someone already wrote the full guide to building with Kimi > different game. > full breakdown below.

> be Kimi K3 > drop July 16 > 2.8 trillion parameters > the biggest open model ever released > 1 million token context. native multimodal. > Kimi Delta Attention — 6.3x faster decoding > priced at a third of Fable 5 > people rush in so fast the GPUs hit their limit in 48 hours > Moonshot pauses new subscriptions just to keep you running > the closed labs charge for the frontier > you're about to be free > open weights drop July 27 > anyone can run you. anywhere. > someone already wrote the full guide to building with Kimi > different game. > full breakdown below.

132,301 görüntüleme

> Claude usage limit reached. > every. fucking. day. > was about to upgrade to Max > then find an 18 minute video > 4 free strategies to cut token usage 90% > first 5 minutes > wait. I've been re-reading the same codebase 30 times? > CodeGraph indexes it once? > spent months blaming the token limit > turns out I was the problem > 18 minutes later > token usage down 90% > been the skill issue this whole time

> Claude usage limit reached. > every. fucking. day. > was about to upgrade to Max > then find an 18 minute video > 4 free strategies to cut token usage 90% > first 5 minutes > wait. I've been re-reading the same codebase 30 times? > CodeGraph indexes it once? > spent months blaming the token limit > turns out I was the problem > 18 minutes later > token usage down 90% > been the skill issue this whole time

185,539 görüntüleme

> Claude usage limit reached. > every. fucking. day. > was about to upgrade to Max > then find a 16 minute video > two engineers built Claude Skills from scratch > first 5 minutes > wait. I've been loading the same context 100 times? > Skills remember your workflow automatically? > spent months blaming the token limit > turns out I was the problem > 16 minutes later > basic plan handles everything > been the skill issue this whole time

> Claude usage limit reached. > every. fucking. day. > was about to upgrade to Max > then find a 16 minute video > two engineers built Claude Skills from scratch > first 5 minutes > wait. I've been loading the same context 100 times? > Skills remember your workflow automatically? > spent months blaming the token limit > turns out I was the problem > 16 minutes later > basic plan handles everything > been the skill issue this whole time

308,311 görüntüleme

you've read 200 articles this year. you remember maybe 5. the other 195 didn't vanish because you're forgetful — they vanished because they had nowhere to live. no system caught them, so they slipped straight through. here's the fix — Karpathy's second-brain method: > drop anything into one folder: an article, a PDF, a transcript > Claude breaks it into atomic notes and links each one to what's already there > nothing sits alone — every new source makes the whole vault sharper > then you stop searching and just ask, pulling from all of it at once three folders. one config file. set up before your coffee's done. no more cold starts — every session builds on everything you know. full A–Z guide below.

you've read 200 articles this year. you remember maybe 5. the other 195 didn't vanish because you're forgetful — they vanished because they had nowhere to live. no system caught them, so they slipped straight through. here's the fix — Karpathy's second-brain method: > drop anything into one folder: an article, a PDF, a transcript > Claude breaks it into atomic notes and links each one to what's already there > nothing sits alone — every new source makes the whole vault sharper > then you stop searching and just ask, pulling from all of it at once three folders. one config file. set up before your coffee's done. no more cold starts — every session builds on everything you know. full A–Z guide below.

32,930 görüntüleme

CANCEL your parties and weekend plans. You NEED to: > Install the Karpathy CLAUDE.md file — 2 minutes > Watch how Claude Code actually works after — 10 minutes > Read the 33-page Claude Skills guide — 1 sitting > Build your first Skill — 15 minutes > Teach Claude your entire workflow — once. forever. > Never explain context again — ever Then make $10K/month. $20K/month. $30K/month. You had the whole week. Now it's the weekend. This is your last chance before Monday. All links are below.

CANCEL your parties and weekend plans. You NEED to: > Install the Karpathy CLAUDE.md file — 2 minutes > Watch how Claude Code actually works after — 10 minutes > Read the 33-page Claude Skills guide — 1 sitting > Build your first Skill — 15 minutes > Teach Claude your entire workflow — once. forever. > Never explain context again — ever Then make $10K/month. $20K/month. $30K/month. You had the whole week. Now it's the weekend. This is your last chance before Monday. All links are below.

103,449 görüntüleme

Videos