Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Claude Code's new dynamic workflow is the real deal. 🤖 Why it matters: It's not just a chain of prompts — it's an autonomous agent swarm. 1. Set model to Opus 4.8 + reasoning effort /ultracode 2. Claude detects complexity, writes orchestration script on the fly 3. Spawns a... show more

EK

8,850 subscribers

197,752 views • 1 month ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Sonnet 5 is here. It's worse than Opus 4.8 on nearly every benchmark... Does that mean it's useless? Absolutely not. Use it with Claude Code Dynamic Workflows! 1. /model set to Sonnet 5 2. /effort set to Ultracode 3. Any complex task will kick off a dynamic workflow This will only become more powerful when Fable is back. You'll use Fable 5 as the superintelligent advisor and Sonnet 5 as the fast and efficient implementer.

Sonnet 5 is here. It's worse than Opus 4.8 on nearly every benchmark... Does that mean it's useless? Absolutely not. Use it with Claude Code Dynamic Workflows! 1. /model set to Sonnet 5 2. /effort set to Ultracode 3. Any complex task will kick off a dynamic workflow This will only become more powerful when Fable is back. You'll use Fable 5 as the superintelligent advisor and Sonnet 5 as the fast and efficient implementer.

Dan McAteer

660,317 views • 15 days ago

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

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

Kirill

412,127 views • 14 days ago

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

subagents are just recursive agents where you can apply different prompts + models depending on the task. since they’re just a primitive, Cursor cli can actually spawn subagents by calling cursor-agent in headless mode via shell commands. that’s what makes the cli so nice. you can extend it, experiment, and have a lot of fun exploring orchestration patterns. here’s one way to do it w. dynamic model selection: 1. create a subagents.mdc rule 2. drop in: ``` --- alwaysApply: true --- ALWAYS spawn subagents by running `cursor-agent -p [task] --output-format=text --force --model [model]` in the terminal. Each subagent should return a summary of the changes it made. Subagents should be used for ALL tasks You can adopt a fan-out pattern where you spawn subagents to perform parallel isolated tasks, and then fan-in the results. Use the following models: - `--model gpt-5` for reasoning, researching, and planning - `--model sonnet-4` for implementation ``` 3. start cursor cli and try it out you can also adjust the rule to be more explicit when it should use subagents, when not to, which models when etc.

eric zakariasson

54,017 views • 10 months ago

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

We just launched Claude Sonnet 4.5 and “Imagine with Claude”, a 5-day preview that creates dynamic experiences for you in real-time (and the first product I’ve worked on at Anthropic!). It pioneers the concept of “model-as-backend”, using a model to not only generate interfaces on the fly but also power all the functionality behind it – all made possible by our newest model, Claude Sonnet 4.5. Here’s a "choose your own adventure" version of my founder journey, as retold by Imagine with Claude:

Sean Strong

115,687 views • 9 months ago

Nike would pay you $3000 for this. Took me some 15 minutes to set up a Claude skill using Seedance 2.0 and Arcads. This is how it works: → I send a product image to Claude → Claude analyzes the product → Writes an ad script → Triggers arcads api with image and prompt → Arcads generates a product ad → Claude updates my Notion database RT + comment "AGENT" and I'll send you the skills .md, full setup, and a guide for free.

Nike would pay you $3000 for this. Took me some 15 minutes to set up a Claude skill using Seedance 2.0 and Arcads. This is how it works: → I send a product image to Claude → Claude analyzes the product → Writes an ad script → Triggers arcads api with image and prompt → Arcads generates a product ad → Claude updates my Notion database RT + comment "AGENT" and I'll send you the skills .md, full setup, and a guide for free.

Kritarth Mittal | Soshals

12,248 views • 3 months ago

Claude Code's effort parameter is something you need to keep in mind before starting any task It's not just about picking the right model anymore (Haiku, Sonnet, Opus). Now you also need to think about which effort level to use before each task. One tip I always go back to: when Opus can't solve a problem, just adding ultrathink makes things click, it's almost magic. We wrote a post at Hedgineer benchmarking each effort level by cost and time Read it here:

Claude Code's effort parameter is something you need to keep in mind before starting any task It's not just about picking the right model anymore (Haiku, Sonnet, Opus). Now you also need to think about which effort level to use before each task. One tip I always go back to: when Opus can't solve a problem, just adding ultrathink makes things click, it's almost magic. We wrote a post at Hedgineer benchmarking each effort level by cost and time Read it here:

Daniel San

66,147 views • 4 months ago

This is how you unlock the next billion software developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!

This is how you unlock the next billion software developers. The new Replit ⠕ Agent 3 (they just launched) is the most advanced vibe-coding agent in the world. 1. Smarter than any other vibe-coding model (10x more autonomous than the previous version). 2. It thinks harder and lasts longer than any other model (up to 200 minutes running fully autonomously). 3. The agent can now use an actual browser to test and fix its own code. 4. 3x faster and 10x more cost-effective than any other "Computer Use" for testing. 5. It can build other agents and automations to take care of repetitive tasks. Seeing the agent test the application autonomously is science fiction!

Santiago

167,056 views • 10 months ago

Everyone is dunking on Sonnet 5 for losing to Opus 4.8 on benchmarks. They're all making the same mistake, judging a teammate by a solo test. Sonnet 5 was never built to win alone. Set the model to Sonnet 5, effort to Ultracode, and any complex task auto-kicks a dynamic workflow where it plans, spawns agents, executes and checks its own work, fast and cheap. When Fable 5 comes back, the setup gets stupid good. Fable 5 decides what to build, Sonnet 5 actually builds it. You stop paying flagship prices to do grunt work.

Everyone is dunking on Sonnet 5 for losing to Opus 4.8 on benchmarks. They're all making the same mistake, judging a teammate by a solo test. Sonnet 5 was never built to win alone. Set the model to Sonnet 5, effort to Ultracode, and any complex task auto-kicks a dynamic workflow where it plans, spawns agents, executes and checks its own work, fast and cheap. When Fable 5 comes back, the setup gets stupid good. Fable 5 decides what to build, Sonnet 5 actually builds it. You stop paying flagship prices to do grunt work.

0xMarioNawfal

98,313 views • 14 days ago

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:

BREAKING: Anthropic just dropped Opus 4.8—and it is a MONSTER We've been testing for about a week Every 📧 and our verdict is they could've just called it Opus 5, it's that good. Here's our vibe check: - Beats GPT-5.5 on Senior Engineer bench. On our toughest benchmark Opus 4.8 scores a 63—a hair higher than GPT-5.5's score of 62, and a full 30 points higher than Opus 4.7. It tackled a ground-up rewrite of a production codebase, and actually built something that works. HOWEVER: Coding performance varied a lot at different reasoning levels. We recommend using it on xhigh for best results. - Incredibly good writer. Opus 4.8 scored a 79.6 on our writing benchmark—measuring models on real-world writing tasks we do all of the time like essay writing, promo email writing, and more. It beats GPT-5.5 by 6 points. It produces well-written prose with fewer "AI-isms". It's also very good at writing in your voice given the right context. HOWEVER: Writing performance also varied with reasoning levels. Medium reasoning had higher incidence of AI-isms—we found best results with high. - Beast at knowledge work. Opus 4.8 is very good at general knowledge work tasks like report creation, research and more. It produced the best PowerPoint one-shot we've ever seen on our deck generation benchmark. - Emotionally intelligent, willing to question the frame. I've also found it to be quite good at talking through psychological or interpersonal issues. It has a high EQ, and it's also good at not glazing and helping to expand your perspective. Its thought process feels extremely rich and dynamic. THE BAD: These days a model is only as good as its harness, and Codex is still a far superior harness to the Claude Desktop app. This has kept me using Codex + GPT-5.5 as my daily driver, but I am flipping back and forth a lot more between Codex and Claude. Anthropic is back baby! Read the rest on Every 📧:

Dan Shipper 📧

353,332 views • 1 month ago

Claude Fable 5 orchestrating Grok 4.5 is now my favorite real workflow. all you need is this free Claude Code plugin that makes Grok the default implementer. Fable writes the specs and reviews every diff, Grok 4.5 does the typing through the Grok CLI. - Grok handles the volume, Fable handles the judgment - Every diff gets cross-vendor review for free - Specs run as parallel agents when they're independent I've been testing it for a few days and the part that sold me is watching Fable refuse to write code. It sends specs down, judges what comes back, and that's it. setup: 1. claude plugin marketplace add DannyMac180/fable-advisor && claude plugin install fable-advisor 2. Install the Grok CLI from then grok login 3. /model fable It's open source, so you can read the agent files and tweak the routing however you want.

Claude Fable 5 orchestrating Grok 4.5 is now my favorite real workflow. all you need is this free Claude Code plugin that makes Grok the default implementer. Fable writes the specs and reviews every diff, Grok 4.5 does the typing through the Grok CLI. - Grok handles the volume, Fable handles the judgment - Every diff gets cross-vendor review for free - Specs run as parallel agents when they're independent I've been testing it for a few days and the part that sold me is watching Fable refuse to write code. It sends specs down, judges what comes back, and that's it. setup: 1. claude plugin marketplace add DannyMac180/fable-advisor && claude plugin install fable-advisor 2. Install the Grok CLI from then grok login 3. /model fable It's open source, so you can read the agent files and tweak the routing however you want.

Alvaro Cintas

96,949 views • 5 days ago

warp code feels like a combination of a cli agent and cursor-style ux design it's a cli that looks like an ide because it gives you: - editor code view - project explorer - one-click to view command output - switch between agent/cli - context/credit spend tracking - task lists - shared context with warp drive there is a learning curve because it's a different workflow, but the agent was top of terminal bench until recently and i can see why would love to see them add: - subagents - an agent sdk - sidebar fonts increasing with cmd +/- not being paid to post this, btw (feel like i have to add that these days 😉) i have been using warp for a long while as a terminal and sometimes agent on the $15/mo plan

warp code feels like a combination of a cli agent and cursor-style ux design it's a cli that looks like an ide because it gives you: - editor code view - project explorer - one-click to view command output - switch between agent/cli - context/credit spend tracking - task lists - shared context with warp drive there is a learning curve because it's a different workflow, but the agent was top of terminal bench until recently and i can see why would love to see them add: - subagents - an agent sdk - sidebar fonts increasing with cmd +/- not being paid to post this, btw (feel like i have to add that these days 😉) i have been using warp for a long while as a terminal and sometimes agent on the $15/mo plan

Ian Nuttall

32,665 views • 9 months ago

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!

Visualizer of our MultiAgentRouter 🤖 The MultiAgentRouter is an all-new multi-agent structure that leverages a hierarchical pattern to select the most specialized agent for your task. Here's how it works: Step 1. You give a task. Step 2. The Boss Agent Routes your task to the most specialized Agent Step 3. The selected agent returns your response! Get started with it now below ⬇️ Thanks to WE!SS for the visualizer!!

swarms

32,313 views • 1 year ago

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Visa just gave your AI a debit card. A real, spendable Visa card created by an AI chatbot in under 10 seconds. No human types in a card number or visits a checkout page. The machine handles it all. A tool called AgentCard just went live on Claude Desktop Anthropic’s AI assistant. You say create a card and the AI generates a one-time virtual Visa, preloaded with whatever amount you set. Then it spends it, anywhere Visa is accepted on your behalf. Visa, Mastercard, Google, Stripe, OpenAI, and Anthropic have all been building toward this moment for over a year. Visa calls it the trusted agent protocol, Mastercard calls it agent pay. Google published an open standard for agent payments and the infrastructure is already live. Santander and Mastercard just completed Europe’s first real AI‑agent payment in a live banking environment Now the part no one wants to talk about. Your AI agent can be manipulated and prompt injection a known, unsolved vulnerability can trick an agent into buying things you never asked for. The agent holds the card, makes the call and the agent can be fooled. Who is liable when an AI makes a bad purchase? You? Anthropic? Visa? The merchant? No one has answered this yet, regulators haven’t caught up, and no court has tested it.

Milk Road AI

70,591 views • 4 months ago

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

ANTHROPIC JUST TURNED AI AGENTS INTO GIT REPOS Anthropic shipped "ant" - a CLI that runs every Claude API endpoint straight from your terminal. The headline isn't the terminal access. It's that you can now version-control an AI agent as YAML in Git and have CI sync it to the Claude Platform, the same way you ship code. - Every API resource is a subcommand: messages, models, files, agents, sessions - Define an agent in a YAML file, check it into your repo, and keep it in sync with one update command - Spin up a session, send it an event, then pull every event and tool call back from the same CLI - Claude Code knows how to drive ant out of the box - it shells out and reads the results with no glue code Agents just stopped being prompts you babysit and became infrastructure you deploy.

BuBBliK

200,080 views • 1 month ago

Beauty ads just changed forever. Free Claude Opus 4.8 + GPT Image 2 + Seedance 2.0 workflow to spin up 100s of video ads. No studio, no model, no macro lens, no shoot day. Here's what nobody in beauty marketing wants to say out loud. That glossy lip shot. The droplet hitting the surface in slow motion. The whip-pan into the next scene. The crystalline product splash. All the stuff that used to need a real set, a real camera op, and a full shoot day. You can generate every frame of it from a text prompt now, and stitch it into a finished ad before your coffee goes cold. The workflow is almost stupidly simple: → Tell Claude Opus 4.8 the beauty shot you want (dewy skin macro, gloss-on-lips contact, ripple transition, the works) → Claude turns it into a shot-by-shot storyboard plus a prompt for every frame → GPT Image 2 generates the photoreal stills, frame by frame → Seedance 2.0 animates each one into a clip with that buttery slow-mo glide → You drop the clips into HeyOz and assemble the full ad in one place The real unlock is volume. This isn't one hero video. Once the workflow is dialed, you spin up hundreds of variations. Different shades, different models, different hooks, different transitions. The exact creative volume Meta rewards, minus the production cost that used to make it impossible. Old way: one shoot, one look, $10k+, weeks of waiting. New way: a hundred angles, any look, a few dollars each, same afternoon. I wrote up the entire workflow. The Claude storyboard prompt, the GPT Image 2 frame prompts, the Seedance motion settings, the full assembly flow. Completely free, no email gate. Want it? Comment "GLOSS" and I'll send it straight over. (make sure you're following so it can actually reach you)

Beauty ads just changed forever. Free Claude Opus 4.8 + GPT Image 2 + Seedance 2.0 workflow to spin up 100s of video ads. No studio, no model, no macro lens, no shoot day. Here's what nobody in beauty marketing wants to say out loud. That glossy lip shot. The droplet hitting the surface in slow motion. The whip-pan into the next scene. The crystalline product splash. All the stuff that used to need a real set, a real camera op, and a full shoot day. You can generate every frame of it from a text prompt now, and stitch it into a finished ad before your coffee goes cold. The workflow is almost stupidly simple: → Tell Claude Opus 4.8 the beauty shot you want (dewy skin macro, gloss-on-lips contact, ripple transition, the works) → Claude turns it into a shot-by-shot storyboard plus a prompt for every frame → GPT Image 2 generates the photoreal stills, frame by frame → Seedance 2.0 animates each one into a clip with that buttery slow-mo glide → You drop the clips into HeyOz and assemble the full ad in one place The real unlock is volume. This isn't one hero video. Once the workflow is dialed, you spin up hundreds of variations. Different shades, different models, different hooks, different transitions. The exact creative volume Meta rewards, minus the production cost that used to make it impossible. Old way: one shoot, one look, $10k+, weeks of waiting. New way: a hundred angles, any look, a few dollars each, same afternoon. I wrote up the entire workflow. The Claude storyboard prompt, the GPT Image 2 frame prompts, the Seedance motion settings, the full assembly flow. Completely free, no email gate. Want it? Comment "GLOSS" and I'll send it straight over. (make sure you're following so it can actually reach you)

Ahad Shams

10,957 views • 1 month ago

I'm going to quit my job to dedicate myself 100% to Claude. I asked it to do this: Analyze undervalued markets on Polymarket to find arbitrage opportunities and detect the wallets that are taking advantage of them so I can copy them. I turned $2K into $11K overnight. It monitored +1,000 wallets. I realized something very quickly. There are arbitrage bots against which I can't compete without knowing how to program. But I can find them. And copy them. Claude built me a monitoring terminal connected to a copytrading bot on Telegram. It's not a script. Not even a bot. It's an AI agent that improves every time it finds a new wallet. It analyzes the behavior of each wallet. How it operates. Its arbitrage patterns. The size of its positions. The exact moment it enters. • 70% hit rate. • 7 wallets being copied right now out of more than 500 monitored. The bot never stops. Never bets. It just follows the math and seeks profit. You only need: • Claude • A device • 1 hour a day I'm going to share it for free for the next 24 hours. To get it: 1. Comment “claude” 2. Like and RT 3. Follow me

I'm going to quit my job to dedicate myself 100% to Claude. I asked it to do this: Analyze undervalued markets on Polymarket to find arbitrage opportunities and detect the wallets that are taking advantage of them so I can copy them. I turned $2K into $11K overnight. It monitored +1,000 wallets. I realized something very quickly. There are arbitrage bots against which I can't compete without knowing how to program. But I can find them. And copy them. Claude built me a monitoring terminal connected to a copytrading bot on Telegram. It's not a script. Not even a bot. It's an AI agent that improves every time it finds a new wallet. It analyzes the behavior of each wallet. How it operates. Its arbitrage patterns. The size of its positions. The exact moment it enters. • 70% hit rate. • 7 wallets being copied right now out of more than 500 monitored. The bot never stops. Never bets. It just follows the math and seeks profit. You only need: • Claude • A device • 1 hour a day I'm going to share it for free for the next 24 hours. To get it: 1. Comment “claude” 2. Like and RT 3. Follow me

Marry Evan

17,782 views • 2 days ago

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

This is the best AI agent-first notes app I've found. It's called . It has the potential to be a productized version of Karpathy's "LLM Wiki" knowledge bases. Here's what I did: 1. Imported "Learning, Fast and Slow" a Continual Learning paper 2. Asked OpenKnowledge to create a visual explainer 3. Read the explainer and had Claude explain to me 4. Created a new section of my own understanding 5. Saved the durable version in my Obsidian vault because it's markdown Free and open-source. Absolutely incredible learning tool.

Dan McAteer

16,683 views • 18 days ago

I’M QUITTING MY JOB TO GO ALL-IN ON CLAUDE Just told it: “Find mispriced Polymarket markets wallets exploiting arbitrage and build me a way to copy them” $2K → $12K in one night. No signals. No guessing. It scanned 1,000+ wallets Tracked behavior, timing, sizing Then filtered the ones that actually have edge. I realized something: You can’t beat these bots without code. But you don’t have to. You just copy them. So Claude built a monitoring terminal. → finds profitable wallets → tracks their trades in real time → executes through a TG copytrading bot Bot: This isn’t a script. It’s an AI agent that improves with every wallet it analyzes. → learns behavior → detects arbitrage patterns → adapts sizing + timing Now running: • ~500 wallets monitored • 7 actively copytraded • ~70% win rate Never sleeps. Never hesitates. Never gambles. Just math. Giving This Free for 24 hours. To get it: 1. Comment the word 'Claude' 2. Like and Retweet this post 3. Follow me Discover (so i can DM you)

I’M QUITTING MY JOB TO GO ALL-IN ON CLAUDE Just told it: “Find mispriced Polymarket markets wallets exploiting arbitrage and build me a way to copy them” $2K → $12K in one night. No signals. No guessing. It scanned 1,000+ wallets Tracked behavior, timing, sizing Then filtered the ones that actually have edge. I realized something: You can’t beat these bots without code. But you don’t have to. You just copy them. So Claude built a monitoring terminal. → finds profitable wallets → tracks their trades in real time → executes through a TG copytrading bot Bot: This isn’t a script. It’s an AI agent that improves with every wallet it analyzes. → learns behavior → detects arbitrage patterns → adapts sizing + timing Now running: • ~500 wallets monitored • 7 actively copytraded • ~70% win rate Never sleeps. Never hesitates. Never gambles. Just math. Giving This Free for 24 hours. To get it: 1. Comment the word 'Claude' 2. Like and Retweet this post 3. Follow me Discover (so i can DM you)

Discover

338,439 views • 3 months ago

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

37,580 views • 4 months ago

Anthropic has introduced an update to Claude Managed Agents, releasing several powerful new features designed to improve agentic workflows and autonomy. 🔹Dreaming (Research Preview): Agents can now "dream" by reviewing past sessions during idle time. This process extracts patterns, spots recurring mistakes, and curates memories so the agent continually learns and improves over time without human intervention. 🔹Outcomes (Public Beta): This feature allows developers to set a specific quality bar by writing a rubric. A separate grader agent then evaluates the output, forcing the primary agent to iterate on the work until it meets the defined success criteria. 🔹Multiagent Orchestration (Public Beta): A lead agent can now break down complex jobs and delegate specific tasks to specialized sub-agents, which work in parallel to execute the broader objective. 🔹Webhooks (Public Beta): Users can subscribe to webhooks to receive automatic notifications the moment an agentic task is completed.

Anthropic has introduced an update to Claude Managed Agents, releasing several powerful new features designed to improve agentic workflows and autonomy. 🔹Dreaming (Research Preview): Agents can now "dream" by reviewing past sessions during idle time. This process extracts patterns, spots recurring mistakes, and curates memories so the agent continually learns and improves over time without human intervention. 🔹Outcomes (Public Beta): This feature allows developers to set a specific quality bar by writing a rubric. A separate grader agent then evaluates the output, forcing the primary agent to iterate on the work until it meets the defined success criteria. 🔹Multiagent Orchestration (Public Beta): A lead agent can now break down complex jobs and delegate specific tasks to specialized sub-agents, which work in parallel to execute the broader objective. 🔹Webhooks (Public Beta): Users can subscribe to webhooks to receive automatic notifications the moment an agentic task is completed.

Wes Roth

53,266 views • 2 months ago