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.

> open Claude Cowork > write an email > close it > do the same thing next week > wonder why people say it's life-changing meanwhile: > /schedule — inbox triaged before I wake up. every morning. > /agents — sub-agent reviews every PR in my team's code style... show more

Nav Toor

148,128 subscribers

402,030 Aufrufe • vor 4 Monaten •via X (Twitter)

Bildung 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

EVERYONE'S TRYING TO SOLVE AI TEAM MEMORY WITH SERVERS, VECTOR DATABASES, AND ORCHESTRATION PLATFORMS. THIS OPEN SOURCE TOOL DOES IT WITH ONE FOLDER IN YOUR REPO. Every dev on your team runs Claude Code. When one agent screws something up, the rest have no idea. They just repeat the mistake next week. It's called teamlore. When your agent gets corrected or breaks something, it writes a small lore file into a .lore/ folder. That file ships with your PR, gets reviewed like normal code, and after merge every teammate's agent automatically recalls it when they touch that part of the repo. No server. No datab No accounts. No SaaS bill. Just a folder in git. Which means code review catches bad lessons before they poison the team, git blame tells you when a rule was added and why, and the whole thing works offline. One command to install: npx teamlore init Companion command: npx teamlore scarmap. Turns your team's history of mistakes into a visual heat map of the codebase. Every red zone is a place your team has been burned before. Which means every red zone is a place your agents should slow down. Here's the wildest part. The teamlore repo's own .lore/ folder contains every mistake Claude made while building teamlore itself. Dogfooded end-to-end. You can literally open the folder and read the receipts. The author's public invitation: "Would love for someone to try and break it." Available on npm. Repo just launched. 100% open source. (link in the comments)

EVERYONE'S TRYING TO SOLVE AI TEAM MEMORY WITH SERVERS, VECTOR DATABASES, AND ORCHESTRATION PLATFORMS. THIS OPEN SOURCE TOOL DOES IT WITH ONE FOLDER IN YOUR REPO. Every dev on your team runs Claude Code. When one agent screws something up, the rest have no idea. They just repeat the mistake next week. It's called teamlore. When your agent gets corrected or breaks something, it writes a small lore file into a .lore/ folder. That file ships with your PR, gets reviewed like normal code, and after merge every teammate's agent automatically recalls it when they touch that part of the repo. No server. No datab No accounts. No SaaS bill. Just a folder in git. Which means code review catches bad lessons before they poison the team, git blame tells you when a rule was added and why, and the whole thing works offline. One command to install: npx teamlore init Companion command: npx teamlore scarmap. Turns your team's history of mistakes into a visual heat map of the codebase. Every red zone is a place your team has been burned before. Which means every red zone is a place your agents should slow down. Here's the wildest part. The teamlore repo's own .lore/ folder contains every mistake Claude made while building teamlore itself. Dogfooded end-to-end. You can literally open the folder and read the receipts. The author's public invitation: "Would love for someone to try and break it." Available on npm. Repo just launched. 100% open source. (link in the comments)

Harman

34,614 Aufrufe • vor 28 Tagen

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 3 Monaten

Every serious Claude Code user is using this repo. if you're not, you're leaving 90% of Claude Code's power on the table. It's called claude-code-best-practice - 84 sourced tips, implementation examples for every major feature, workflow comparisons across 8 major repos, and the actual tips from Boris Cherny (creator of Claude Code) compiled in one place. Here's what's actually in it: → 84 tips organized by category -- prompting, planning, CLAUDE.md, agents, commands, skills, hooks, workflows, debugging, utilities, daily habits → best practice + implemented examples for every core concept: subagents, commands, skills, hooks, MCP servers, plugins, settings, memory, checkpointing, CLI flags → workflow comparison table -- Superpowers, BMAD-METHOD, Get Shit Done, OpenSpec, gstack, HumanLayer -- what makes each unique, how many agents/commands/skills each has → orchestration workflow -- Command → Agent → Skill pattern with a live demo → Boris Cherny tips compiled across 3 tweet threads (13 + 10 + 12 tips) and 5 podcast/video appearances → "billion dollar questions" section -- open questions about CLAUDE.md, agents vs commands vs skills, specs -- that nobody has definitively answered yet here's a few of the tips that actually change how you use it: → use subagents with "say use subagents" to throw more compute at a problem -- offload tasks to keep your main context clean → spin up a second Claude to review your plan as a staff engineer before executing → CLAUDE.md should target under 200 lines -- wrap domain-specific rules in ` ` tags so Claude doesn't ignore them as files grow → compress KV context at max 50%, not at the end -- avoid the "agent dumb zone" by doing manual /compact proactively → after a mediocre fix: "knowing everything you know now, scrap this and implement the elegant solution" was #1 trending on GitHub in March 2026. 19.7K GitHub stars. 1.7K forks. MIT license. 100% open source. (link in the comments)

Every serious Claude Code user is using this repo. if you're not, you're leaving 90% of Claude Code's power on the table. It's called claude-code-best-practice - 84 sourced tips, implementation examples for every major feature, workflow comparisons across 8 major repos, and the actual tips from Boris Cherny (creator of Claude Code) compiled in one place. Here's what's actually in it: → 84 tips organized by category -- prompting, planning, CLAUDE.md, agents, commands, skills, hooks, workflows, debugging, utilities, daily habits → best practice + implemented examples for every core concept: subagents, commands, skills, hooks, MCP servers, plugins, settings, memory, checkpointing, CLI flags → workflow comparison table -- Superpowers, BMAD-METHOD, Get Shit Done, OpenSpec, gstack, HumanLayer -- what makes each unique, how many agents/commands/skills each has → orchestration workflow -- Command → Agent → Skill pattern with a live demo → Boris Cherny tips compiled across 3 tweet threads (13 + 10 + 12 tips) and 5 podcast/video appearances → "billion dollar questions" section -- open questions about CLAUDE.md, agents vs commands vs skills, specs -- that nobody has definitively answered yet here's a few of the tips that actually change how you use it: → use subagents with "say use subagents" to throw more compute at a problem -- offload tasks to keep your main context clean → spin up a second Claude to review your plan as a staff engineer before executing → CLAUDE.md should target under 200 lines -- wrap domain-specific rules in ` ` tags so Claude doesn't ignore them as files grow → compress KV context at max 50%, not at the end -- avoid the "agent dumb zone" by doing manual /compact proactively → after a mediocre fix: "knowing everything you know now, scrap this and implement the elegant solution" was #1 trending on GitHub in March 2026. 19.7K GitHub stars. 1.7K forks. MIT license. 100% open source. (link in the comments)

Sukh Sroay

113,759 Aufrufe • vor 4 Monaten

BUILD KARPATHY'S SECOND BRAIN WITH CLAUDE OPUS 5 + OBSIDIAN Andrej Karpathy (OpenAI co-founder) shared an architecture that turns Claude into a persistent second brain not just a basic chat window how it works: > point Claude Code at an Obsidian vault folder > drop articles, PDFs, or video transcripts into raw > Claude reads them, updates summaries, cross-references everything > the knowledge base compounds like interest, never resets on a new chat the setup: > install create a local vault folder > open it in Claude Code, paste Karpathy's wiki prompt > > let the agent build raw, wiki, and CLAUDE.md folders > drop any file into raw, tell it to ingest > ask questions, get compiled summaries back this skips rag overhead entirely. your vault stays organized on its own run ingest on a schedule and it's loop engineering: sense a new file, plan, write, verify, repeat how do you manage your local knowledge base?

BUILD KARPATHY'S SECOND BRAIN WITH CLAUDE OPUS 5 + OBSIDIAN Andrej Karpathy (OpenAI co-founder) shared an architecture that turns Claude into a persistent second brain not just a basic chat window how it works: > point Claude Code at an Obsidian vault folder > drop articles, PDFs, or video transcripts into raw > Claude reads them, updates summaries, cross-references everything > the knowledge base compounds like interest, never resets on a new chat the setup: > install create a local vault folder > open it in Claude Code, paste Karpathy's wiki prompt > > let the agent build raw, wiki, and CLAUDE.md folders > drop any file into raw, tell it to ingest > ask questions, get compiled summaries back this skips rag overhead entirely. your vault stays organized on its own run ingest on a schedule and it's loop engineering: sense a new file, plan, write, verify, repeat how do you manage your local knowledge base?

Mr. Buzzoni

14,716 Aufrufe • vor 12 Tagen

✨ I revived my first AI startup from 6 years ago with Claude Code [ 💡 ] Back then it used GPT-3 (this was 2 years before ChatGPT existed!) to generate new startup ideas which then people can vote on And the best startup ideas rise to the top! Back then I made it because people complained they didn't have any ideas to build a startup This week I moved it to its own VPS and installed Claude Code and told it to fix everything, the DB had become big and there was stupid write operations on every page load that it made it very slow Claude Code is excellent at fixing all those small bugs from old projects and quickly fixing them As Garry Tan says "boil the oceans" as in before I'd not have the time to fix these kinds of projects, it wouldn't be worth it, I mean IdeasAI doesn't even make money, but now it takes me an hour to do this and it works again! I also upgraded GPT-3 to xAI's Grok 4.2 for new startup ideas

✨ I revived my first AI startup from 6 years ago with Claude Code [ 💡 ] Back then it used GPT-3 (this was 2 years before ChatGPT existed!) to generate new startup ideas which then people can vote on And the best startup ideas rise to the top! Back then I made it because people complained they didn't have any ideas to build a startup This week I moved it to its own VPS and installed Claude Code and told it to fix everything, the DB had become big and there was stupid write operations on every page load that it made it very slow Claude Code is excellent at fixing all those small bugs from old projects and quickly fixing them As Garry Tan says "boil the oceans" as in before I'd not have the time to fix these kinds of projects, it wouldn't be worth it, I mean IdeasAI doesn't even make money, but now it takes me an hour to do this and it works again! I also upgraded GPT-3 to xAI's Grok 4.2 for new startup ideas

@levelsio

180,039 Aufrufe • vor 5 Monaten

Claude Cowork is f*cking cracked for Meta Ads 🤯 Point it at a folder with your ad export, your brand context, and your brief template —> ... and it analyzes your account like a senior creative strategist + saves a finished brief directly to your computer. All inside Claude Cowork. Perfect for DTC brands and agencies who are still manually digging through ad reports trying to figure out why performance shifted. If you're running Meta Ads and pulling weekly reports that tell you what happened but not why — CPAs creeping up, CTRs dropping... You're killing creatives on gut feel because mapping performance back to hook type, angle, and offer framing takes hours you don't have. Claude Cowork eliminates the entire loop: → Drop your Meta Ads CSV export into a project folder → Add a brand context file and your brief template → Claude reads all three files and audits across 4 lenses: hook performance, offer angles, fatigue signals, next test recommendations → Asks clarifying questions if it needs them → Saves a finished creative brief as a real .md file directly to your folder No copy-pasting data into chat windows. No manually tagging creatives in a spreadsheet. No "here are your metrics" summaries that tell you nothing new. What you get: → Pattern analysis across every creative — which hook structures are converting and why → Creative fatigue signals before CPAs blow up → Competitor intelligence layered in from the Meta Ad Library → A data-backed brief your creative team can execute immediately Set it up once, drop in a fresh CSV every week and run the same prompt. I put together a full playbook with the exact folder setup, the prompts, and the brief template to get this running in under 30 minutes. Want it for free? > Like this post > Comment "ADS" And I'll send it over (must be following so I can DM)

Mike Futia

85,614 Aufrufe • vor 5 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

2,800,385 Aufrufe • vor 8 Tagen

THIS MAN HASN’T HAD A SINGLE ORIGINAL IDEA IN 8 WEEKS. CLAUDE HAS ALL OF THEM BEFORE HE WAKES UP he gave claude his obsidian vault on a saturday by monday it found a link between two notes written 6 weeks apart in different folders he turned that connection into his best-performing post his competitors are still organizing folders and writing morning pages and brainstorming in notion the only difference is one file called CLAUDE.md every note = fuel and every morning = synthesis and every week = ideas compounding faster than he can publish them this is not a tool anymore and this is not even an assistant this is a second brain that studied you for 2 months straight bookmark & like this or lose it forever

THIS MAN HASN’T HAD A SINGLE ORIGINAL IDEA IN 8 WEEKS. CLAUDE HAS ALL OF THEM BEFORE HE WAKES UP he gave claude his obsidian vault on a saturday by monday it found a link between two notes written 6 weeks apart in different folders he turned that connection into his best-performing post his competitors are still organizing folders and writing morning pages and brainstorming in notion the only difference is one file called CLAUDE.md every note = fuel and every morning = synthesis and every week = ideas compounding faster than he can publish them this is not a tool anymore and this is not even an assistant this is a second brain that studied you for 2 months straight bookmark & like this or lose it forever

leopardracer

27,938 Aufrufe • vor 3 Monaten

This Claude Code Skills Pack is a cheat code for ad creative teams 🤯 10 plug-and-play skills → competitor audits, creative briefs, 20 hook variations, ad copy, static ads, landing pages, & weekly performance reports. All inside Claude Code. Perfect for DTC brands and agencies who are still prompting Claude Code from scratch every time. If you're re-explaining your brand voice in every session, getting inconsistent output depending on who's prompting, and spending 30 minutes on tasks that should take 30 seconds... These skills eliminate the entire loop: → Competitor Ad Research Agent Drop a brand name, get back a full creative audit — hooks, messaging angles, ad formats, CTAs, and "steal this" angles. No more scrolling the Ad Library for an hour. → Creative Brief Generator One prompt, complete brief in your exact template. Hooks, concepts, visual direction, brand voice — all loaded from your own files. → Hook & Script Writer 15+ hooks categorized by type (curiosity, problem-agitation, result-first, social proof). Full 30-60s scripts with the hook → problem → mechanism → proof → CTA structure baked in. → Ad Copy Variation Engine Feed it one winning ad, get back 20 variations — each targeting a different persona and pain point. Same structure, different angles. Creative fatigue solved. → Weekly Report Writer Drop in your Meta ads CSV. Get back the narrative summary, anomaly flags, creative fatigue alerts, and recommended next steps. The report nobody wants to write, written in 60 seconds. → Creative Fatigue Detector Flags ads before they die. CTR trending down, frequency climbing, conversion rate dropping — caught in hours, not after three days of wasted spend. No prompting from scratch every time. No inconsistent output across your team. No re-explaining context in every session. I packaged all 10 as a free Skills Pack. Copy-paste the files into your Claude Code commands folder and they just work. Want the full Skills Pack? > Like this post > Comment "SKILLS" And I'll send it over (must be following so I can DM)

Mike Futia

55,968 Aufrufe • vor 5 Monaten

An Anthropic engineer watched me trade from across the table at a WeWork in SF I had my laptop open. Four agents running. Green charts. Live trades scrolling. He was on a Zoom call. Muted himself. Walked over. "Are you running Claude against live prediction markets right now" I told him. Claude Code. Two repos. $25 a month. He pulled up a chair. "I helped build the model you're using. I've never seen anyone wire it to live trades like this" I showed him the dataset. 86 million trades. Every wallet. Every entry. Every exit. He stared at it. "We tested this internally. You give Claude a dataset and don't tell it what to look for. It finds the winning wallets. Then it finds WHY they win. Then it copies the pattern. We never shipped it because legal killed it" I told him I did exactly that. One weekend. Claude Code found the exit logic on its own. Top wallets exit before resolution 91% of the time. They capture 86% of expected value. Cut losers at 12%. Everyone else captures 58% and holds to 41%. "That's the exact finding from our internal eval. Except ours took a team of eight and four months" I showed him the scanner. Three commands. 500+ markets. No API key. Claude scores them all in 20 minutes. "You're using our model to beat markets we're not allowed to touch. On infra that costs less than my lunch" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400. 19 days. I showed him the full breakdown. Every repo. Every command. Every dollar. Copytrade here: He read it for five minutes. Then looked up. "If my manager sees this he's going to lose his mind. You just proved our model works in production and we've been sitting on it for a year" He DM'd me that night. "Take this down before someone at Anthropic finds it" Too late.

An Anthropic engineer watched me trade from across the table at a WeWork in SF I had my laptop open. Four agents running. Green charts. Live trades scrolling. He was on a Zoom call. Muted himself. Walked over. "Are you running Claude against live prediction markets right now" I told him. Claude Code. Two repos. $25 a month. He pulled up a chair. "I helped build the model you're using. I've never seen anyone wire it to live trades like this" I showed him the dataset. 86 million trades. Every wallet. Every entry. Every exit. He stared at it. "We tested this internally. You give Claude a dataset and don't tell it what to look for. It finds the winning wallets. Then it finds WHY they win. Then it copies the pattern. We never shipped it because legal killed it" I told him I did exactly that. One weekend. Claude Code found the exit logic on its own. Top wallets exit before resolution 91% of the time. They capture 86% of expected value. Cut losers at 12%. Everyone else captures 58% and holds to 41%. "That's the exact finding from our internal eval. Except ours took a team of eight and four months" I showed him the scanner. Three commands. 500+ markets. No API key. Claude scores them all in 20 minutes. "You're using our model to beat markets we're not allowed to touch. On infra that costs less than my lunch" My setup: Claude API - $20/mo VPS - $5/mo poly_data - free polymarket-cli - free 214 trades. 74% win rate. +$9,400. 19 days. I showed him the full breakdown. Every repo. Every command. Every dollar. Copytrade here: He read it for five minutes. Then looked up. "If my manager sees this he's going to lose his mind. You just proved our model works in production and we've been sitting on it for a year" He DM'd me that night. "Take this down before someone at Anthropic finds it" Too late.

Lunar

224,021 Aufrufe • vor 4 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

6,974,954 Aufrufe • vor 2 Monaten

your AI agent can watch any video now - paste a URL and it sees every frame, hears every word, all for free 🤯 bradautomates/claude-video gives Claude the ability to watch YouTube, Loom, TikTok, local files - anything yt-dlp supports what people actually use it for: → analyze a competitor launch - what hook, what visuals, what structure → debug from a screen recording - Claude reads the exact frame where it breaks → summarize a 49-min talk in 30 seconds with frame-accurate timestamps → strip the hype from product videos - "what's actually new, skip the pitch" the mechanism: yt-dlp pulls free captions first (zero cost). ffmpeg extracts frames at scene-aware intervals - not uniform sampling, so you don't waste tokens on 12 identical frames of the same slide. Claude reads every frame as an image with timestamp markers. Groq Whisper only kicks in when a video has no caption track how to set up (3 min): > claude code: /plugin marketplace add bradautomates/claude-video then /plugin install watch@claude-video > or npx skills add bradautomates/claude-video -g for codex, cursor, gemini cli > dependencies auto-install on macOS via brew two caveats: free captions cover most but not all videos. past 10 min use --start/--end for focused sections or the token-burner mode for full coverage your buddy still watches every tutorial at 2x speed taking manual notes. you paste a URL and your agent extracts the substance in seconds for $0

your AI agent can watch any video now - paste a URL and it sees every frame, hears every word, all for free 🤯 bradautomates/claude-video gives Claude the ability to watch YouTube, Loom, TikTok, local files - anything yt-dlp supports what people actually use it for: → analyze a competitor launch - what hook, what visuals, what structure → debug from a screen recording - Claude reads the exact frame where it breaks → summarize a 49-min talk in 30 seconds with frame-accurate timestamps → strip the hype from product videos - "what's actually new, skip the pitch" the mechanism: yt-dlp pulls free captions first (zero cost). ffmpeg extracts frames at scene-aware intervals - not uniform sampling, so you don't waste tokens on 12 identical frames of the same slide. Claude reads every frame as an image with timestamp markers. Groq Whisper only kicks in when a video has no caption track how to set up (3 min): > claude code: /plugin marketplace add bradautomates/claude-video then /plugin install watch@claude-video > or npx skills add bradautomates/claude-video -g for codex, cursor, gemini cli > dependencies auto-install on macOS via brew two caveats: free captions cover most but not all videos. past 10 min use --start/--end for focused sections or the token-burner mode for full coverage your buddy still watches every tutorial at 2x speed taking manual notes. you paste a URL and your agent extracts the substance in seconds for $0

Alvaro Cintas

307,223 Aufrufe • vor 1 Monat

My dad called me at 7 AM on a Sunday. I need you to look at something. Do not tell your mother. I thought he was sick. He sent me a screenshot. A Claude terminal. Live Polymarket odds. Green numbers. +$14,200. He is 56. Retired electrician. Calls WiFi the internet box. Dad what the fuck is this? I found an article about connecting Claude to Polymarket. Told Claude to install it. One prompt. Four commands. 45 tools running on his old Dell laptop. Live orderbooks. Volume spikes. Closing deadlines. All inside Claude. He does not know what MCP means. Does not care. Every morning at 5 AM. Before mom wakes up. Reading glasses and black coffee. He asks Claude: What is closing today with mispriced odds? Claude cross-references markets in one call. Spots where the price disagrees with the news. He does not out-execute bots. He out-waits them. Quarter Kelly. $500 from his fishing fund. Last 60 days: 680 trades 90.2% win rate +$14,200 Best trade: Claude alert pinged him during Sunday football. Volume spike on a geopolitics market. Entry $0.09. Resolved $1.00. +$2,800. Mom thought he was checking the score. He was not checking the score. Last week he booked her a cruise. Said he had been saving since January. He has not saved anything since January. When are you telling her? When I hit $25K. I am buying the lake house. Dad you do not even know what an API is. I do not need to. The machine knows. He still calls Claude the machine. The machine prints money. I built the entire framework he used: Claude MCP setup Polymarket mispricing detection Quarter Kelly position sizing Volume spike alerts Cron-based market scanning The system runs 24/7. Finds mispriced odds before the crowd adjusts. Executes before the edge compresses. No emotions. No FOMO. Just math. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word money 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the mispricing system this week. Start with $500. Scale on evidence.

My dad called me at 7 AM on a Sunday. I need you to look at something. Do not tell your mother. I thought he was sick. He sent me a screenshot. A Claude terminal. Live Polymarket odds. Green numbers. +$14,200. He is 56. Retired electrician. Calls WiFi the internet box. Dad what the fuck is this? I found an article about connecting Claude to Polymarket. Told Claude to install it. One prompt. Four commands. 45 tools running on his old Dell laptop. Live orderbooks. Volume spikes. Closing deadlines. All inside Claude. He does not know what MCP means. Does not care. Every morning at 5 AM. Before mom wakes up. Reading glasses and black coffee. He asks Claude: What is closing today with mispriced odds? Claude cross-references markets in one call. Spots where the price disagrees with the news. He does not out-execute bots. He out-waits them. Quarter Kelly. $500 from his fishing fund. Last 60 days: 680 trades 90.2% win rate +$14,200 Best trade: Claude alert pinged him during Sunday football. Volume spike on a geopolitics market. Entry $0.09. Resolved $1.00. +$2,800. Mom thought he was checking the score. He was not checking the score. Last week he booked her a cruise. Said he had been saving since January. He has not saved anything since January. When are you telling her? When I hit $25K. I am buying the lake house. Dad you do not even know what an API is. I do not need to. The machine knows. He still calls Claude the machine. The machine prints money. I built the entire framework he used: Claude MCP setup Polymarket mispricing detection Quarter Kelly position sizing Volume spike alerts Cron-based market scanning The system runs 24/7. Finds mispriced odds before the crowd adjusts. Executes before the edge compresses. No emotions. No FOMO. Just math. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word money 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the mispricing system this week. Start with $500. Scale on evidence.

Himanshu Kumar

18,287 Aufrufe • vor 2 Monaten

Met my girlfriend's parents for the first time. Her dad asked what I do for work. I said I build trading systems. He said like Wall Street? I said no. 6 AI agents. They work while I sleep. He laughed. So robots are making you money? I did not argue. I opened my laptop. Showed him the terminal. 6 agents running. 47 mispriced markets caught in the first week alone. His face changed. That is not gambling. That is automation? Exactly. Then I showed him how it works. Built the whole thing in 6 hours. Agent 1: Monitoring Runs 24/7. Watches Polymarket for mispriced markets. Spots an anomaly. Writes to memory and pings me on Telegram instantly. Agent 2: Research Parses news, X, macro data via browser tool on a cron schedule. Every morning I have a full digest on all open positions before I check my phone. Agent 3: Trading Reads the research agent memory. Sees the market has not reacted yet. Acts. Execution tool in gateway mode with a whitelist. No full access on a live server. Agent 4: Watchdog Heartbeat every 5 minutes. Monitoring running. No errors. Positions up to date. Something breaks. Immediate Telegram message. All of this. One Gateway. One config file. Isolation via per-agent scope. The token trick: stopped dumping everything into one file. Critical rules in bootstrap. Markets, patterns, past trades in memory. Semantic search pulls it when needed. Token spend dropped 3x. From $0.40 per request to $0.13. First week running: → 47 mispriced markets caught before Polymarket adjusted → Average entry edge 8 to 12 cents per position → Watchdog fired 3 times and caught a broken RPC before it cost me anything The whole system is plain text files. Open an editor. Change one line. Agent behaves differently. No deploy. No build. Her dad went quiet. Then he asked can you teach this? Her mom asked for the setup guide. I built the entire framework. Six agents. Full deployment. Memory architecture. Telegram alerts. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word "Claude" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the 6-agent system this week. Start with $200. Scale on evidence.

Met my girlfriend's parents for the first time. Her dad asked what I do for work. I said I build trading systems. He said like Wall Street? I said no. 6 AI agents. They work while I sleep. He laughed. So robots are making you money? I did not argue. I opened my laptop. Showed him the terminal. 6 agents running. 47 mispriced markets caught in the first week alone. His face changed. That is not gambling. That is automation? Exactly. Then I showed him how it works. Built the whole thing in 6 hours. Agent 1: Monitoring Runs 24/7. Watches Polymarket for mispriced markets. Spots an anomaly. Writes to memory and pings me on Telegram instantly. Agent 2: Research Parses news, X, macro data via browser tool on a cron schedule. Every morning I have a full digest on all open positions before I check my phone. Agent 3: Trading Reads the research agent memory. Sees the market has not reacted yet. Acts. Execution tool in gateway mode with a whitelist. No full access on a live server. Agent 4: Watchdog Heartbeat every 5 minutes. Monitoring running. No errors. Positions up to date. Something breaks. Immediate Telegram message. All of this. One Gateway. One config file. Isolation via per-agent scope. The token trick: stopped dumping everything into one file. Critical rules in bootstrap. Markets, patterns, past trades in memory. Semantic search pulls it when needed. Token spend dropped 3x. From $0.40 per request to $0.13. First week running: → 47 mispriced markets caught before Polymarket adjusted → Average entry edge 8 to 12 cents per position → Watchdog fired 3 times and caught a broken RPC before it cost me anything The whole system is plain text files. Open an editor. Change one line. Agent behaves differently. No deploy. No build. Her dad went quiet. Then he asked can you teach this? Her mom asked for the setup guide. I built the entire framework. Six agents. Full deployment. Memory architecture. Telegram alerts. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word "Claude" 2. Like and retweet this 3. Follow me Himanshu Kumar so I can DM you Save this post. Deploy the 6-agent system this week. Start with $200. Scale on evidence.

Himanshu Kumar

47,275 Aufrufe • vor 2 Monaten

Yesterday at 3 AM Claude Code called me I woke up, picked up the phone, and on the screen was a message: "Wallet entered BTC Up at 11 cents. Open Polymarket?" I said yes and went back to sleep Claude Code unlocked my 2nd phone on its own, opened Polymarket, found the right market, entered the amount, and hit Buy. I could see all of it in real time through the web interface on my laptop. Screenshots from the phone updating every second. By morning the position closed in profit Let me tell you how I got here A week ago I asked Claude Code to write a script that pulls on-chain data from Polymarket and ranks wallets by win rate on 15-minute BTC markets In 20 minutes I had a table with hundreds of addresses, and 1 of them stood apart from the rest. More than 200 trades per day, surgical entry precision, and a profit curve going straight up I fed that address back into Claude Code and asked it to break down the strategy. Turns out the wallet monitors BTC volatility on Binance and Bybit every 100 milliseconds, and when it drops below 0.08% it enters Up and Down simultaneously at 25 to 35 cents A pure straddle: 1 side burns and the other flies to a dollar, giving 3 to 4x per position. Dozens of times a day I wanted to follow it but signals came at any hour, and waking up every 15 minutes for a notification was simply impossible. So I built something else Took an old Android phone and installed an agent running on the Qwen3-VL visual model. It sees what is happening on the screen and mimics human actions through ADB: taps, swipes, text input. Then I connected it to Claude Code as the executor Now the chain works like this: Claude Code monitors the wallet, sees a new position, calls me. And if I say "yes" or just do not pick up within 30 seconds, the agent on the phone opens Polymarket on its own and copies the entry Essentially I built myself an autopilot out of 2 AI systems: 1 thinks and the other presses buttons. I just sleep and occasionally pick up the phone → Here is the wallet the whole thing is tracking: For those who do not want to build a setup like this there is a Telegram bot that handles the 1st part: tracks this wallet and sends a signal on every new entry: AI calls me at 3 AM to ask permission to spend my money A year ago this would have sounded like schizophrenia. Now it is just Tuesday

Yesterday at 3 AM Claude Code called me I woke up, picked up the phone, and on the screen was a message: "Wallet entered BTC Up at 11 cents. Open Polymarket?" I said yes and went back to sleep Claude Code unlocked my 2nd phone on its own, opened Polymarket, found the right market, entered the amount, and hit Buy. I could see all of it in real time through the web interface on my laptop. Screenshots from the phone updating every second. By morning the position closed in profit Let me tell you how I got here A week ago I asked Claude Code to write a script that pulls on-chain data from Polymarket and ranks wallets by win rate on 15-minute BTC markets In 20 minutes I had a table with hundreds of addresses, and 1 of them stood apart from the rest. More than 200 trades per day, surgical entry precision, and a profit curve going straight up I fed that address back into Claude Code and asked it to break down the strategy. Turns out the wallet monitors BTC volatility on Binance and Bybit every 100 milliseconds, and when it drops below 0.08% it enters Up and Down simultaneously at 25 to 35 cents A pure straddle: 1 side burns and the other flies to a dollar, giving 3 to 4x per position. Dozens of times a day I wanted to follow it but signals came at any hour, and waking up every 15 minutes for a notification was simply impossible. So I built something else Took an old Android phone and installed an agent running on the Qwen3-VL visual model. It sees what is happening on the screen and mimics human actions through ADB: taps, swipes, text input. Then I connected it to Claude Code as the executor Now the chain works like this: Claude Code monitors the wallet, sees a new position, calls me. And if I say "yes" or just do not pick up within 30 seconds, the agent on the phone opens Polymarket on its own and copies the entry Essentially I built myself an autopilot out of 2 AI systems: 1 thinks and the other presses buttons. I just sleep and occasionally pick up the phone → Here is the wallet the whole thing is tracking: For those who do not want to build a setup like this there is a Telegram bot that handles the 1st part: tracks this wallet and sends a signal on every new entry: AI calls me at 3 AM to ask permission to spend my money A year ago this would have sounded like schizophrenia. Now it is just Tuesday

Blaze

56,501 Aufrufe • vor 5 Monaten

Claude Fable 5 + Claude Design is f*cking insane 🤯 Anthropic just dropped its most intelligent model ever, and the first thing I pointed it at was email design. I built a complete email campaign design in Claude Design, and the difference is night and day: tighter layouts, cleaner hierarchy, on-brand from the first generation. All inside Claude Design with Fable 5. Perfect for DTC brands and agencies who are still paying email agencies $3-5K/month for campaign designs that take 2 weeks to ship. If your campaign calendar is packed but every new email means briefing a designer, waiting on mockups, sending notes, and waiting again... This workflow eliminates the entire bottleneck: → Load your brand design system into Claude Design once (colors, fonts, logo, button styling) → Switch the model to Claude Fable 5 — Anthropic's new state-of-the-art model with the best vision of any AI → Prompt the campaign email section by section: header, hero, headline, offer block, CTA → Fable 5 nails layout and brand details that older models fumbled → Iterate inline — swap images, adjust styling, color-pick directly in the canvas → Export the finished email and hand off to your ESP No briefing a designer. No 2-week turnaround on a single campaign. No paying an agency $4K/month for 4 emails. What you get: → Campaign emails designed in minutes, not weeks → A reusable design system every new email pulls from automatically → Noticeably smarter design decisions from Fable 5's upgraded vision → Full inline editing before anything touches your ESP Built 100% with Claude Design + Claude Fable 5. I recorded a full walkthrough showing exactly how this works. Want it for free? > Like this post > Comment "FABLE" And I'll send it over (must be following so I can DM)

Mike Futia

43,018 Aufrufe • vor 2 Monaten

An Anthropic paid for my espresso at Sightglass when he saw my screen. I was backtesting a Claude-built arbitrage system. Terminal open. Live trades firing. He glanced over. Stopped walking. That is not TradingView. What framework is that actually running. Claude Code. Three repos. One prompt. $20 per month. He sat down across from me without asking. I work on AlphaGo successor models. We test reinforcement agents for market simulation. You are running something similar but you let Claude write the strategy layer. Not just strategy. Detection. github/warproxxx/poly_data 86 million Polymarket trades. Every wallet. Every position. Every timestamp. You are feeding Claude transaction history and letting it identify asymmetric behavior patterns. Then cloning the profitable ones in real time. Exactly. One prompt: Scan every wallet with 150+ trades and ROI above 65%. Rank by consistency. Export top 40. Claude processed 18,600 wallets in 6 minutes. Returned 38. Top 15 wallets outperformed the bottom 18,000 combined. That is not analysis. That is alpha concentration. Precisely. And you did not write the ranking algorithm. Claude built it. I just connected it to execution logic. Then I opened the second repo. github/Polymarket/polymarket-cli Official Rust CLI. No auth required for reads. 600+ markets scanned in under 3 minutes. Claude scores: liquidity depth, pricing gap, resolution timeline. 512 markets reduced to 28 before capital moves. 94.5% filtered out before entry consideration. A notification hit. Position filled. +$127. How does it decide entry timing. Four agents. No shared state. Arbitrage detector, convergence scanner, whale mirror, volume surge tracker. 3 agents agree: full position. 2 agree: half size. Split vote: skip. Consensus filtering alone eliminated 46% of losses in backtest. And exit logic. The 38 top wallets almost never hold to settlement. 89% exit early. Average 71% of max profit captured. Immediate redeployment. My bot exits at 82% of projected move or 4x volume spike. Whichever hits first. You built a whale copy system that exits before the whales do. Correct. He set his coffee down slowly. How many trades per day. 12 average. Most rejected by filters before I see notifications. My setup: Claude API: $20/mo VPS Frankfurt: $6/mo poly_data: free polymarket-cli: free $300 seed capital. 34 days ago. $18,700 now. 318 trades. 76% win rate. Sharpe 2.61. I have not modified it in 34 days. He stared at the terminal without blinking. This is exactly what our adversarial testing team models. Market-adaptive agents with autonomous strategy evolution. Except you deployed it live. He messaged me the next day. Would you consider a conversation with our safety research lead. I told him this post is the conversation. Too late to contain. The edge is not predicting markets. It is identifying who already wins and mirroring them before the pattern shifts. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word "Money" 2. Like and retweet this post. 3. Follow me Himanshu Kumar so I can DM you Save this post. Build the whale mirror system this week. Start with $200. Scale on evidence.

An Anthropic paid for my espresso at Sightglass when he saw my screen. I was backtesting a Claude-built arbitrage system. Terminal open. Live trades firing. He glanced over. Stopped walking. That is not TradingView. What framework is that actually running. Claude Code. Three repos. One prompt. $20 per month. He sat down across from me without asking. I work on AlphaGo successor models. We test reinforcement agents for market simulation. You are running something similar but you let Claude write the strategy layer. Not just strategy. Detection. github/warproxxx/poly_data 86 million Polymarket trades. Every wallet. Every position. Every timestamp. You are feeding Claude transaction history and letting it identify asymmetric behavior patterns. Then cloning the profitable ones in real time. Exactly. One prompt: Scan every wallet with 150+ trades and ROI above 65%. Rank by consistency. Export top 40. Claude processed 18,600 wallets in 6 minutes. Returned 38. Top 15 wallets outperformed the bottom 18,000 combined. That is not analysis. That is alpha concentration. Precisely. And you did not write the ranking algorithm. Claude built it. I just connected it to execution logic. Then I opened the second repo. github/Polymarket/polymarket-cli Official Rust CLI. No auth required for reads. 600+ markets scanned in under 3 minutes. Claude scores: liquidity depth, pricing gap, resolution timeline. 512 markets reduced to 28 before capital moves. 94.5% filtered out before entry consideration. A notification hit. Position filled. +$127. How does it decide entry timing. Four agents. No shared state. Arbitrage detector, convergence scanner, whale mirror, volume surge tracker. 3 agents agree: full position. 2 agree: half size. Split vote: skip. Consensus filtering alone eliminated 46% of losses in backtest. And exit logic. The 38 top wallets almost never hold to settlement. 89% exit early. Average 71% of max profit captured. Immediate redeployment. My bot exits at 82% of projected move or 4x volume spike. Whichever hits first. You built a whale copy system that exits before the whales do. Correct. He set his coffee down slowly. How many trades per day. 12 average. Most rejected by filters before I see notifications. My setup: Claude API: $20/mo VPS Frankfurt: $6/mo poly_data: free polymarket-cli: free $300 seed capital. 34 days ago. $18,700 now. 318 trades. 76% win rate. Sharpe 2.61. I have not modified it in 34 days. He stared at the terminal without blinking. This is exactly what our adversarial testing team models. Market-adaptive agents with autonomous strategy evolution. Except you deployed it live. He messaged me the next day. Would you consider a conversation with our safety research lead. I told him this post is the conversation. Too late to contain. The edge is not predicting markets. It is identifying who already wins and mirroring them before the pattern shifts. You only need Claude + device + 1 hour per day. Giving this free for 24 hours. To get it: 1. Comment the word "Money" 2. Like and retweet this post. 3. Follow me Himanshu Kumar so I can DM you Save this post. Build the whale mirror system this week. Start with $200. Scale on evidence.

Himanshu Kumar

15,985 Aufrufe • vor 2 Monaten

Claude Code + Nano Banana 2 is f*cking cracked 🤯 I built a skill inside Claude Code that writes JSON image prompts for Nano Banana 2, and the outputs look like they came from a professional photo shoot. One plain-text prompt. Claude rewrites it as structured JSON with lighting, camera, composition, style, and negative prompts. Then fires it off to Nano Banana 2. All inside Claude Code. Perfect for DTC brands and agencies who need high-volume ad creative without booking a shoot. If you're using Nano Banana 2 for product shots and lifestyle images but every generation feels like pulling a slot machine lever — random lighting, inconsistent style, plastic skin, misspelled labels ... This skill fixes the entire output: → You describe what you want in plain English → Claude rewrites it as a structured JSON prompt (lighting, camera angle, lens, depth of field, color grading — all of it) → Fires it to Nano Banana 2 via API → Saves the prompt + image in organized folders → You iterate on the style until it's dialed, then every output matches No more slot machine prompting. No more inconsistent brand imagery. No more burning credits on unusable generations. What you get: - Photo-realistic product shots and lifestyle images on demand - Full control over style, lighting, composition, and camera settings - Saved JSON prompts you can reuse across every campaign - A skill that gets smarter the more feedback you give it Built 100% in Claude Code with a custom skill + Python scripts. I put together a full playbook showing the exact skill, the JSON schema, and the workflow to set this up yourself. Want the full playbook? > Like this post > Comment "BANANA" And I'll send it over (must be following so I can DM)

Mike Futia

212,096 Aufrufe • vor 6 Monaten

I just built a Meta ad policy checker in Claude Code that catches rejections BEFORE Meta does 🤯 Drop in your ad copy → it pulls Meta's LIVE Advertising Standards, checks every line against the actual policy text, and hands each ad a verdict: Cleared for launch, Fix before launch, or Grounded. All inside Claude Code. Perfect for media buyers and DTC brands who've had ads bounced — or an account restricted — and never got a straight answer why. If you're finding out about policy problems only after the rejection email, resubmitting the same ad and praying, losing days of delivery while the appeal sits in review, and every bounce quietly teaches Meta to trust your account a little less... This runs the review before Meta ever sees the ad: → Drop in your ad copy (one ad or a whole batch) → It reads each ad and figures out which of Meta's policies apply → Scrapes the live policy pages from Meta's Transparency Center → Flags the exact phrase that violates, with Meta's own policy quoted next to it → Rewrites the risky lines so the message survives but the violation doesn't → Renders a dashboard: every ad, every finding, every fix in one place No guessing which word killed the ad. No resubmit-and-pray loops. No stacking rejections on your account history. What you get: → A verdict on every ad before you spend a dollar → The violating phrase + the policy citation, side by side → Rewrites that keep the selling intent → A report you can hand straight to your team or client Built 100% in Claude Code. No API keys, no Meta login. I'm giving away the complete Claude skill file. Want the skill for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

I just built a Meta ad policy checker in Claude Code that catches rejections BEFORE Meta does 🤯 Drop in your ad copy → it pulls Meta's LIVE Advertising Standards, checks every line against the actual policy text, and hands each ad a verdict: Cleared for launch, Fix before launch, or Grounded. All inside Claude Code. Perfect for media buyers and DTC brands who've had ads bounced — or an account restricted — and never got a straight answer why. If you're finding out about policy problems only after the rejection email, resubmitting the same ad and praying, losing days of delivery while the appeal sits in review, and every bounce quietly teaches Meta to trust your account a little less... This runs the review before Meta ever sees the ad: → Drop in your ad copy (one ad or a whole batch) → It reads each ad and figures out which of Meta's policies apply → Scrapes the live policy pages from Meta's Transparency Center → Flags the exact phrase that violates, with Meta's own policy quoted next to it → Rewrites the risky lines so the message survives but the violation doesn't → Renders a dashboard: every ad, every finding, every fix in one place No guessing which word killed the ad. No resubmit-and-pray loops. No stacking rejections on your account history. What you get: → A verdict on every ad before you spend a dollar → The violating phrase + the policy citation, side by side → Rewrites that keep the selling intent → A report you can hand straight to your team or client Built 100% in Claude Code. No API keys, no Meta login. I'm giving away the complete Claude skill file. Want the skill for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)

Mike Futia

17,390 Aufrufe • vor 1 Monat

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

here's how the whole thing works. claude code doesn't care what's behind the API. it just sends requests and expects responses. so i pointed it at my own machine instead of anthropic's servers. llama-server runs the model locally. LiteLLM sits in between and translates the API format. claude code thinks it's talking to claude. it's talking to qwen on localhost. the setup: 2x 3090s, 38 layers on GPU, 10 on CPU. 128K context window. generation is only 7 tok/s but the tradeoff is worth it. 128K means the agent can hold an entire project in memory without losing context midtask. claude code alone loads a 17.5K token system prompt on every request. tool definitions, safety rules, agent behavior. that's your baseline before you even say hello. pushed as far as i could tonight. what surprised me most wasn't the speed. it was the iteration quality. first prompt gave me a working particle sim. second prompt, the model read its own 564 lines, understood the architecture, and added trails, explosions, gravity wells, bloom effects. no handholding. 4bit quantized. 45GB on two consumer cards. running a full coding agent autonomously. detailed article coming. full benchmarks, hardware breakdowns, engine debugging, code quality. everything from setup to what broke and why.

Sudo su

37,623 Aufrufe • vor 6 Monaten