Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

> 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 >... show more

Kirill

43,037 subscribers

2,506,937 Aufrufe • vor 6 Monaten •via X (Twitter)

Nachrichten & Politik Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Claude Code Scheduled Tasks is now available... here's a solid idea to connect it with Telegram Save this so you don't forget to set it up! First, ask Claude to add a simple Telegram messaging module to your repo. You can use the Telegram Bot Builder Skill from Link: Install command: npx claude-code-templates@latest --skill enterprise-communication/telegram-bot-builder Once the module is in your project, grab your bot credentials from BotFather and add the bot ID to your .env file That's it! ✅ Now every Scheduled Task you create should end with an instruction for Claude to send the task result to Telegram using that module. Claude will handle the delivery automatically on every task it runs

Daniel San

91,123 Aufrufe • vor 7 Monaten

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.

if you use claude code, this will save you real money. the problem: every time you make an edit, your ai rereads the whole codebase to figure out what changed. tens of thousands of tokens, every turn, for context it already had. this repo fixes it. it’s called code review graph, and it just maps your entire codebase: every file, every function, every connection laid out so you can see the actual shape of your project how to set up (2 min): 1. pip install code-review-graph 2. code-review-graph install - auto-configures Claude Code, Cursor, Codex, Gemini CLI + more 3. code-review-graph build change one function, and it traces exactly what that touches... every caller, every dependent file, every test. your ai only reads what's affected, not the whole repo. and the savings are wild. a task that used to burn ~100,000 tokens (about a dollar) now runs closer to a penny.

Alvaro Cintas

75,596 Aufrufe • vor 2 Monaten

Met my girlfriend's parents for the first time. Her dad shook my hand. "So what do you do?" "Building trading systems." "Like Wall Street?" "No. Open-source. Anyone can audit the code." He laughed. "So you code for free?" "No sir. The code makes money." "Sure it does." I didn't argue. I opened my laptop. One wallet I was tracking made $11,400 in 19 days. Another moved $5.3M in volume. One more had a 74% winrate across 214 trades. Sharpe 2.31. I didn't touch it once. He stopped smiling. "That's... from a script?" Exactly. Then I showed him the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He went quiet for a long time. Then: "How long have you been doing this?" "Eight months." "And you didn't tell my daughter?" I didn't have a good answer. Her mom asked for the links before dessert. Profile: Fathers-in-law don't ask about the money. They ask why you didn't tell their daughter. Then the mom does the rest.

Lunar

20,181 Aufrufe • vor 4 Monaten

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Claude Code Desktop now opens a new window for each session This makes it much easier to visualize multiple Claude Code agents running in parallel My current stack depends on the task: - Ghostty: when starting a project. Bash commands, git, env variables, provider connections. All manual through the terminal with a Claude panel running alongside. - Claude Code Desktop: once everything is configured. GitHub connected, CLAUDE.md, Skills, subagents and Hooks ready. Claude Code runs on its own, no more terminal setup, just panels running and outputs to review. - VSCode: when I need to review code by hand. I use it less and less, but there are moments where I have to confirm Claude got it right. I usually open the Claude extension inside VSCode, but it lacks most of the CLI features so it's limited Solid update. Worth trying once your workflows are already set up 👇

Daniel San

38,806 Aufrufe • vor 5 Monaten

My girlfriend asked me at brunch what I actually do for work. "Building trading systems." "Like Robinhood?" "No. Open-source. Anyone can audit the code." She put her fork down. "So you're just coding all day for free?" "I don't code for free. The code makes money." "Sure it does." I didn't argue. I opened my phone. One wallet I was tracking turned $480 into $6,900 in 19 days. Another moved $5.3M in volume. One more had a 74% winrate across 214 trades. Sharpe 2.31. I didn't touch it once. She stopped mid-sip. "That's... from a script?" Exactly. Then I showed her the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. She went quiet for a long time. Then: "Why didn't you ever tell me?" I didn't have a good answer. Profile: The people closest to you are always the last to know.

Lunar

24,670 Aufrufe • vor 4 Monaten

My dad called Sunday morning. Said he was in the neighborhood. "Did you eat?" "No." "I'll grab bagels." He showed up an hour later. Sat at the kitchen table. Looked around. "So this is what you do all day." "Yeah." "What, you just code?" "Trading systems. Open-source. Anyone can see the code." He took a bite of his bagel. "So you code for free?" "No, dad. The code makes money." "Sure it does." I didn't argue. I opened my laptop. One wallet I was tracking turned $480 into $6,900 in 19 days. Another moved $5.3M in volume. One more had a 74% winrate across 214 trades. Sharpe 2.31. I didn't touch it once. He stopped chewing. "That's... from a script?" Exactly. Then I showed him the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He went quiet for a long time. Then: "How long have you been doing this?" "Eight months." "And you didn't tell me?" I didn't have a good answer. Profile: Fathers don't ask about the money. They ask why you didn't tell them.

Lunar

12,991 Aufrufe • vor 4 Monaten

Had dinner with my dad. He asked what I actually do for a living. "Building trading systems." "Like Wall Street?" "No. Open-source. Anyone can read the code." He nodded slowly. "So... programming for banks?" I didn't correct him. I opened my laptop. One wallet I was tracking turned $480 into $6,900 in 19 days. Another moved $5.3M in volume. One more had a 74% winrate across 214 trades. Hands off. Didn't touch it once. He put down his fork. "That's... from a script?" Exactly. Then I showed him the stack. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free download. Second: Market making bot. Both sides of the book. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He went quiet for a long time. Then he said: "Why didn't you tell me earlier?" I didn't have an answer. Profile: He's been telling his friends at the golf club about it since Monday.

Lunar

36,787 Aufrufe • vor 4 Monaten

My dad was at the stove when I walked in. Haven't seen him in 3 months. He looked older. "You cook now?" "Only on Sundays." "What changed?" "Time makes sense when the code works." He laughed. "What code?" "Trading systems. Open-source. Anyone can audit the code." Copytrade wallet: He cracked an egg. "So you code for free?" "No dad. The code makes money." "Sure it does, son." I didn't argue. I opened my laptop on the counter. One wallet I was tracking cleared $2,800 in a single weekend. Another flipped 156 trades in 48 hours with 78% winrate. One more turned $950 into $14,200 in 17 days. He put the spatula down. "That's... from a script?" Exactly. Then I showed him the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He went quiet for a long time. Then: "How long have you been doing this?" "Nine months." "And you didn't tell me?" I didn't have a good answer. He slid a plate of eggs across the counter. Sat down across from me. "Send me the links. I'm reading them tonight." Then: "And come home more often. Your mom worries." Fathers don't ask about the money. They ask why you didn't tell them. Then they ask you to come home more.

My dad was at the stove when I walked in. Haven't seen him in 3 months. He looked older. "You cook now?" "Only on Sundays." "What changed?" "Time makes sense when the code works." He laughed. "What code?" "Trading systems. Open-source. Anyone can audit the code." Copytrade wallet: He cracked an egg. "So you code for free?" "No dad. The code makes money." "Sure it does, son." I didn't argue. I opened my laptop on the counter. One wallet I was tracking cleared $2,800 in a single weekend. Another flipped 156 trades in 48 hours with 78% winrate. One more turned $950 into $14,200 in 17 days. He put the spatula down. "That's... from a script?" Exactly. Then I showed him the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He went quiet for a long time. Then: "How long have you been doing this?" "Nine months." "And you didn't tell me?" I didn't have a good answer. He slid a plate of eggs across the counter. Sat down across from me. "Send me the links. I'm reading them tonight." Then: "And come home more often. Your mom worries." Fathers don't ask about the money. They ask why you didn't tell them. Then they ask you to come home more.

Lunar

10,443 Aufrufe • vor 4 Monaten

I have a little robot that unlocks my door from the inside (so I don't have to carry a key) The problem was it wouldn't calibrate on my door. It was designed for 90° turns, but my lock only needs 15° In the past, this would've been a showstopper But I asked AI if it could help... At first, it suggested I snoop on the bluetooth connection to figure out the protocol Then it realized that we could probably just decompile the app's SDK and read its source code. That worked! It told me to switch to my mac and run some python for it. Unfortunately, it couldn't run the scripts directly because Claude Code Desktop didn't have bluetooth permissions, but my shell did. Thinking about it now, I probably should've used Claude Code or Codex in the Terminal. Anyways, it took a while, lots of backs and forths, we had some misunderstandings, it was massively overcautious in the beginning, but we finally got the lock calibrated! Feels like magic! I threw the repo up on github in case anyone in the future (ie me) runs into a similar issue – hopefully it can save them some time

I have a little robot that unlocks my door from the inside (so I don't have to carry a key) The problem was it wouldn't calibrate on my door. It was designed for 90° turns, but my lock only needs 15° In the past, this would've been a showstopper But I asked AI if it could help... At first, it suggested I snoop on the bluetooth connection to figure out the protocol Then it realized that we could probably just decompile the app's SDK and read its source code. That worked! It told me to switch to my mac and run some python for it. Unfortunately, it couldn't run the scripts directly because Claude Code Desktop didn't have bluetooth permissions, but my shell did. Thinking about it now, I probably should've used Claude Code or Codex in the Terminal. Anyways, it took a while, lots of backs and forths, we had some misunderstandings, it was massively overcautious in the beginning, but we finally got the lock calibrated! Feels like magic! I threw the repo up on github in case anyone in the future (ie me) runs into a similar issue – hopefully it can save them some time

Steve Krouse

38,720 Aufrufe • vor 2 Monaten

THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of the smartest ways to run Opus three models work on one task and each does only the part it’s cheapest at. start Claude Code like this: claude -> model sonnet -> advisor opus you stop paying Opus prices for work that doesn’t need Opus > Sonnet runs the session and edits the code > Haiku 5.5 searches the repo and docs, at up to 40x less per token than Opus 5.5 > Opus waits as the advisor and reads the whole session, tool calls included Claude usually calls Opus at three points: > before it locks a plan > when the same error comes back > right before it says it’s done Sonnet drives. Haiku scouts. Opus signs off and if you go one step lower, most of an agent’s day is tiny choices like picking a file or a tool, or deciding whether to retry. Jev takes those first, so Sonnet and Opus only see the moments that are really open the whole setup Sonnet runs the main session Explore on Haiku 5.5 searches and pulls docs, read-only Opus on call as the advisor give Claude Code this setup and the prompt below ↓ “Set up my Claude Code exactly like this: Main model Sonnet, advisor Opus, saved as advisorModel in my settings. One read-only subagent named exactly Explore, on claude-haiku-5-5, to replace the built-in one. One line in CLAUDE.md: ask the advisor before locking a plan, after the same error twice, and before calling a task done, not more often. Check what could turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) and only report it. Show every change as a diff first. Don’t edit anything until I say go.” before you turn it on: every advisor call re-reads the whole transcript with no cache. on a 200k session that’s about $0.80 in input, against $0.04 for a normal request. keep it to a few calls the built-in Explore agent runs on your main model unless a subagent is named exactly Explore. any other name does nothing turning the advisor on or off keeps your prompt cache. switching models rebuilds it it needs the Anthropic API, and it stays off if telemetry is disabled bookmark it before your next long session

THIS IS F*CKING BRILLIANT. Anthropic’s docs describe one of the smartest ways to run Opus three models work on one task and each does only the part it’s cheapest at. start Claude Code like this: claude -> model sonnet -> advisor opus you stop paying Opus prices for work that doesn’t need Opus > Sonnet runs the session and edits the code > Haiku 5.5 searches the repo and docs, at up to 40x less per token than Opus 5.5 > Opus waits as the advisor and reads the whole session, tool calls included Claude usually calls Opus at three points: > before it locks a plan > when the same error comes back > right before it says it’s done Sonnet drives. Haiku scouts. Opus signs off and if you go one step lower, most of an agent’s day is tiny choices like picking a file or a tool, or deciding whether to retry. Jev takes those first, so Sonnet and Opus only see the moments that are really open the whole setup Sonnet runs the main session Explore on Haiku 5.5 searches and pulls docs, read-only Opus on call as the advisor give Claude Code this setup and the prompt below ↓ “Set up my Claude Code exactly like this: Main model Sonnet, advisor Opus, saved as advisorModel in my settings. One read-only subagent named exactly Explore, on claude-haiku-5-5, to replace the built-in one. One line in CLAUDE.md: ask the advisor before locking a plan, after the same error twice, and before calling a task done, not more often. Check what could turn the advisor off (CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY) and only report it. Show every change as a diff first. Don’t edit anything until I say go.” before you turn it on: every advisor call re-reads the whole transcript with no cache. on a 200k session that’s about $0.80 in input, against $0.04 for a normal request. keep it to a few calls the built-in Explore agent runs on your main model unless a subagent is named exactly Explore. any other name does nothing turning the advisor on or off keeps your prompt cache. switching models rebuilds it it needs the Anthropic API, and it stays off if telemetry is disabled bookmark it before your next long session

rvaniaaa

62,223 Aufrufe • vor 9 Tagen

this is f*cking gold. I told Fable 5 it's a retiring engineer on its last week, and its final task is to leave everything behind for the team replacing it. It read my entire git history. Every mistake, every dead end, every fix that finally worked. Then it started writing them into skill files so the cheaper models replacing it never repeat what I got wrong. Fable leaves July 12. What it leaves behind is up to you. (full breakdown in the article below)

this is f*cking gold. I told Fable 5 it's a retiring engineer on its last week, and its final task is to leave everything behind for the team replacing it. It read my entire git history. Every mistake, every dead end, every fix that finally worked. Then it started writing them into skill files so the cheaper models replacing it never repeat what I got wrong. Fable leaves July 12. What it leaves behind is up to you. (full breakdown in the article below)

Prajwal Tomar

125,537 Aufrufe • vor 3 Monaten

I genuinely don't understand why everyone isn't using this yet Andrej Karpathy, a co-founder of OpenAI, posted a simple idea that hit 16 million views: 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, and Claude reads it, links it, and 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: > Install Obsidian, create a vault, open it in Claude Code > Paste Karpathy's wiki idea file and tell Claude to build it > Claude makes three folders: raw for sources, wiki for its pages, a CLAUDE.md that runs it > Drop any source into raw and say "ingest this" > Ask questions across everything, forever Five minutes to set up, and you never start from a blank chat again. Full step-by-step guide with Claude and Obsidian, link below. Bookmark this

I genuinely don't understand why everyone isn't using this yet Andrej Karpathy, a co-founder of OpenAI, posted a simple idea that hit 16 million views: 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, and Claude reads it, links it, and 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: > Install Obsidian, create a vault, open it in Claude Code > Paste Karpathy's wiki idea file and tell Claude to build it > Claude makes three folders: raw for sources, wiki for its pages, a CLAUDE.md that runs it > Drop any source into raw and say "ingest this" > Ask questions across everything, forever Five minutes to set up, and you never start from a blank chat again. Full step-by-step guide with Claude and Obsidian, link below. Bookmark this

Ridark

7,033,768 Aufrufe • vor 4 Monaten

Claude Code tip: if Opus 5.5 is already your main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."

Claude Code tip: if Opus 5.5 is already your main model, Fable 5.1 has been sitting idle this whole time. wire it in with /advisor start it with /advisor fable Opus 5.5 writes every line. Fable 5.1 reads the whole session, every tool call, and says nothing until one of three moments: → a plan gets proposed: is this actually the right move, or just the first one? → the same error comes back twice: is the search stuck, or is this a dead end? → the task gets marked done: what got missed while it was moving fast? Opus 5.5 ships. Fable 5.1 catches what would've shipped broken. Jev engineering makes the same move one layer down: forks that don't need a real thinker, which file, which tool, retry or give up, get routed to Jev and answered in under half a second. the expensive model only ever sees the forks that genuinely split. the tree this runs on: > Opus 5.5, high effort, owns the main session > explorer, medium effort, reads the code > worker, medium effort, edits and runs tests > researcher, medium effort, pulls the docs > Fable 5.1 outside all of it, on call, never writing a line itself drop the tree and this prompt into Claude Code: "Rebuild my Claude Code setup around this tree: 1. Look in ~/.claude/agents and .claude/agents for subagents that already cover explorer, worker and researcher. Draft new ones only for roles that are missing. Set each to model: opus, effort: medium. If an existing subagent is pinned to a different model, list it, don't touch it. 2. Set the main session's effortLevel to high in ~/.claude/settings.json, and set advisorModel to fable. 3. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, any variable blocking feature-flag fetches, and CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort. Report what you find. Change nothing yet. 4. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a large plan, when an error repeats, and before marking a long task done. Show every change as a diff first. Don't touch anything until I say go."

Ryven

36,121 Aufrufe • vor 20 Tagen

My girlfriend's parents came over for dinner Saturday. First time at my place. Her dad walked in. Looked around. Saw the laptop, the second monitor, the three terminal panels. "So this is where you work." "Yeah." "What, just the laptop?" "Just the laptop. And the repos." He raised an eyebrow. "Repos?" "Open-source. Anyone can audit the code." He laughed. "So you code for free?" "No sir. The code makes money." "Sure it does." I didn't argue. I opened my laptop. One wallet I was tracking turned $640 into $11,800 in 31 days. Another flipped 287 trades with 76% winrate. One more pulled $3.4M in volume in two weeks. He put his beer down. "That's... from a script?" Exactly. Then I showed him the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He went quiet for a long time. Then: "How long have you been doing this?" "Eight months." "And you didn't tell us?" I didn't have a good answer. Her mom asked for the links before the pasta was done. Copytrade him: Fathers-in-law don't ask about the money. They ask why you didn't tell them. Then the mom does the rest.

My girlfriend's parents came over for dinner Saturday. First time at my place. Her dad walked in. Looked around. Saw the laptop, the second monitor, the three terminal panels. "So this is where you work." "Yeah." "What, just the laptop?" "Just the laptop. And the repos." He raised an eyebrow. "Repos?" "Open-source. Anyone can audit the code." He laughed. "So you code for free?" "No sir. The code makes money." "Sure it does." I didn't argue. I opened my laptop. One wallet I was tracking turned $640 into $11,800 in 31 days. Another flipped 287 trades with 76% winrate. One more pulled $3.4M in volume in two weeks. He put his beer down. "That's... from a script?" Exactly. Then I showed him the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. He went quiet for a long time. Then: "How long have you been doing this?" "Eight months." "And you didn't tell us?" I didn't have a good answer. Her mom asked for the links before the pasta was done. Copytrade him: Fathers-in-law don't ask about the money. They ask why you didn't tell them. Then the mom does the rest.

Lunar

45,349 Aufrufe • vor 4 Monaten

I just built a skill that lets Claude Code watch & analyze ANY video 🤯 Drop in any video file — UGC ads, competitor Meta ads, organic TikToks, screen recordings — and Claude hands you back a full creative teardown. All inside Claude Code. Perfect for media buyers and creative strategists who reverse-engineer competitor ads every week — and lose half a day doing it by hand. If your creative process starts with studying what's already working, you're scrubbing through competitor ads frame by frame, pausing to write down every hook, screenshotting the on-screen text, and by the tenth video you can't remember what made the first one land... This skill solves it: → Drop any video file into Claude Code → Skill routes it through the Gemini API for native video understanding → Returns a full creative teardown — hook breakdown, target audience, angle, beat-by-beat, on-screen text verbatim → Surfaces the steal-worthy patterns you can apply to your own creative → Same skill works on UGC ads, produced video ads, organic TikToks, and Loom recordings No manual scrubbing. No pausing every 5 seconds. No $200/mo ad intelligence platform. What you get: → Native video understanding via Gemini (not just transcripts) → Structured analysis — hook, angle, audience, pain point, CTA → Verbatim on-screen text and dialogue with timestamps → Hook variations generated directly from competitor ads → About 27 cents per 30-minute video Built 100% in Claude Code with the Gemini API. I recorded a full breakdown showing exactly how I built this, and I'm giving away the skill for free. Want the skill? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

I just built a skill that lets Claude Code watch & analyze ANY video 🤯 Drop in any video file — UGC ads, competitor Meta ads, organic TikToks, screen recordings — and Claude hands you back a full creative teardown. All inside Claude Code. Perfect for media buyers and creative strategists who reverse-engineer competitor ads every week — and lose half a day doing it by hand. If your creative process starts with studying what's already working, you're scrubbing through competitor ads frame by frame, pausing to write down every hook, screenshotting the on-screen text, and by the tenth video you can't remember what made the first one land... This skill solves it: → Drop any video file into Claude Code → Skill routes it through the Gemini API for native video understanding → Returns a full creative teardown — hook breakdown, target audience, angle, beat-by-beat, on-screen text verbatim → Surfaces the steal-worthy patterns you can apply to your own creative → Same skill works on UGC ads, produced video ads, organic TikToks, and Loom recordings No manual scrubbing. No pausing every 5 seconds. No $200/mo ad intelligence platform. What you get: → Native video understanding via Gemini (not just transcripts) → Structured analysis — hook, angle, audience, pain point, CTA → Verbatim on-screen text and dialogue with timestamps → Hook variations generated directly from competitor ads → About 27 cents per 30-minute video Built 100% in Claude Code with the Gemini API. I recorded a full breakdown showing exactly how I built this, and I'm giving away the skill for free. Want the skill? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

Mike Futia

42,240 Aufrufe • vor 4 Monaten

Anthropic didn't build his memory system. He built it himself, and what you're looking at is the proof. Same source, no gatekeeping. The Obsidian CEO published it, anyone can install it. That's not a screensaver on his second monitor. It's his vault. Every point of light is a note. Every cluster is a project his AI already understands without being told again. He doesn't even touch the keyboard to move through it. One hand up, and the whole cluster tilts and spins, like he's turning a globe that happens to be his own head. A year ago he opened a new AI tab every morning and explained himself from scratch. Who he is, what he's building, what he wants. 200+ hours a year, just re-introducing himself to a machine. Then he stopped writing prompts and started writing one file instead. It loaded before every session. His goals, his projects, his blind spots. Claude read it first, every time, without asking. Now the cluster on that screen keeps growing on its own. New notes link themselves. Nothing gets explained twice. He's not showing off code. He's showing off the machine that finally stopped forgetting him.

Anthropic didn't build his memory system. He built it himself, and what you're looking at is the proof. Same source, no gatekeeping. The Obsidian CEO published it, anyone can install it. That's not a screensaver on his second monitor. It's his vault. Every point of light is a note. Every cluster is a project his AI already understands without being told again. He doesn't even touch the keyboard to move through it. One hand up, and the whole cluster tilts and spins, like he's turning a globe that happens to be his own head. A year ago he opened a new AI tab every morning and explained himself from scratch. Who he is, what he's building, what he wants. 200+ hours a year, just re-introducing himself to a machine. Then he stopped writing prompts and started writing one file instead. It loaded before every session. His goals, his projects, his blind spots. Claude read it first, every time, without asking. Now the cluster on that screen keeps growing on its own. New notes link themselves. Nothing gets explained twice. He's not showing off code. He's showing off the machine that finally stopped forgetting him.

Superior

122,474 Aufrufe • vor 3 Monaten

I still don't understand why everyone is not using this yet. Thanks to it, a year ago I increased my income to 17,000 dollars a month Andrey Karpathy, co-founder of OpenAI, published a simple idea that got 16 million views: stop using AI to write code, use it to build a second brain You point Claude Code to a folder, drop any source in there (an article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. It compounds like interest: the more you feed it, the smarter it gets Here is the gist: Install Obsidian, create a vault, open it in Claude Code Paste the file with Karpathy's wiki idea and tell Claude to build it Claude creates three folders: raw for sources, wiki for its pages, CLAUDE which runs everything Drop any source into raw and say "ingest this" Ask questions across everything, forever Five minutes to set up, and you never start with an empty chat again The full step-by-step guide is in the article. Save to bookmarks

I still don't understand why everyone is not using this yet. Thanks to it, a year ago I increased my income to 17,000 dollars a month Andrey Karpathy, co-founder of OpenAI, published a simple idea that got 16 million views: stop using AI to write code, use it to build a second brain You point Claude Code to a folder, drop any source in there (an article, transcript, PDF) and Claude reads it, links it, and saves it into a living wiki of everything you know. It compounds like interest: the more you feed it, the smarter it gets Here is the gist: Install Obsidian, create a vault, open it in Claude Code Paste the file with Karpathy's wiki idea and tell Claude to build it Claude creates three folders: raw for sources, wiki for its pages, CLAUDE which runs everything Drop any source into raw and say "ingest this" Ask questions across everything, forever Five minutes to set up, and you never start with an empty chat again The full step-by-step guide is in the article. Save to bookmarks

Bober_smart

2,883,175 Aufrufe • vor 2 Monaten

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.

Kirill

33,091 Aufrufe • vor 2 Monaten

My Tinder date showed up 10 minutes late. She ordered an oat latte. Looked around. Looked at me. "So. What do you do?" "Building trading systems." "Like crypto?" "No. Open-source. Anyone can audit the code." She raised an eyebrow. "So you code for free?" "No. The code makes money." "Sure it does." I didn't argue. I opened my laptop. One wallet I was tracking turned $1,300 into $19,700 in 24 days. Another flipped 232 trades with 82% winrate. One more pulled $5.8M in volume in five weeks. She stopped stirring her coffee. "That's... from a script?" Exactly. Then I showed her the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. She went quiet for a long time. Then: "I do product marketing at a startup. $82K. I cried in the parking lot last Tuesday." I didn't say anything. She finished her coffee. Looked at me. "How long have you been doing this?" "Eight months." "And you're on Tinder?" I didn't have a good answer. She opened her phone. Unmatched me on Hinge. Then handed it back: "No. Send me the GitHub links instead." Copytrade him: Tinder dates don't ask about the money. They ask why you're on the app. Then they keep the links and leave you unmatched.

My Tinder date showed up 10 minutes late. She ordered an oat latte. Looked around. Looked at me. "So. What do you do?" "Building trading systems." "Like crypto?" "No. Open-source. Anyone can audit the code." She raised an eyebrow. "So you code for free?" "No. The code makes money." "Sure it does." I didn't argue. I opened my laptop. One wallet I was tracking turned $1,300 into $19,700 in 24 days. Another flipped 232 trades with 82% winrate. One more pulled $5.8M in volume in five weeks. She stopped stirring her coffee. "That's... from a script?" Exactly. Then I showed her the repos. All free. All public. First: 86M+ trades on Polymarket. Every outcome since day one. Free to download. Second: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution. Third: ML + heuristics. I fed 14,000 wallets into Claude. One prompt. 4 minutes. Found 47 traders with 70%+ winrate. Bot mirrors them with 60-second delay. She went quiet for a long time. Then: "I do product marketing at a startup. $82K. I cried in the parking lot last Tuesday." I didn't say anything. She finished her coffee. Looked at me. "How long have you been doing this?" "Eight months." "And you're on Tinder?" I didn't have a good answer. She opened her phone. Unmatched me on Hinge. Then handed it back: "No. Send me the GitHub links instead." Copytrade him: Tinder dates don't ask about the money. They ask why you're on the app. Then they keep the links and leave you unmatched.

Lunar

48,925 Aufrufe • vor 4 Monaten

$My trainer at the gym asked what I do for work. "Trading systems. Open-source." He laughed. "Like day trading?" "No. Anyone can see how it works. All the code is public." He put down his weights. "So you just look at code all day?" I didn't argue. I opened my laptop. One wallet I was tracking returned 71% in a single month. Another processed $4.1M in volume. One more turned $500 into $8,200. His face changed. "That's... from some code?" Exactly. Then I showed him the repos. All public. All free. First one: Every trade ever made. 86M+ trades. Free to download. Snapshot saves 2+ days of research. Second one: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution layer. Third one: ML + heuristics. Flagged that \$500 → \$8,200 wallet before anyone noticed. LLM auto market making. Open source from Polymarket team. My trainer went quiet. Then he asked: "Can my son run this? He's into computers." Profile: I said yes. Then I showed him how to start. Most people think you need a finance degree or a fund. You don't. You just need to read the code and start.$

My trainer at the gym asked what I do for work. "Trading systems. Open-source." He laughed. "Like day trading?" "No. Anyone can see how it works. All the code is public." He put down his weights. "So you just look at code all day?" I didn't argue. I opened my laptop. One wallet I was tracking returned 71% in a single month. Another processed $4.1M in volume. One more turned $500 into $8,200. His face changed. "That's... from some code?" Exactly. Then I showed him the repos. All public. All free. First one: Every trade ever made. 86M+ trades. Free to download. Snapshot saves 2+ days of research. Second one: Market making bot. Both sides of the book. Gas optimized. Google Sheets execution layer. Third one: ML + heuristics. Flagged that \$500 → \$8,200 wallet before anyone noticed. LLM auto market making. Open source from Polymarket team. My trainer went quiet. Then he asked: "Can my son run this? He's into computers." Profile: I said yes. Then I showed him how to start. Most people think you need a finance degree or a fund. You don't. You just need to read the code and start.

Lunar

36,068 Aufrufe • vor 4 Monaten