Halven (@halvenruns) header
Halven (@halvenruns) profile picture
Joined September 2026
Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)Photo by Halven (@halvenruns)
This is f*cking insane. Joe Rogan asked Nvidia founder and ex-CEO Jensen Huang if AI will replace a lot of jobs. His answer: "If your job is just to chop vegetables, Cuisinart is going to replace you" In 67 seconds, he draws the line: a lawyer's job is to help people. Reading and writing documents is just a task. If your job is the task, AI takes it Rogan pushes back: that's a lot of people. Jensen doesn't argue. It could be a lot of people Doing the Task → AI Does the Task → Harness → You Own the Purpose A harness is how you pass the task off: agents do the work, you keep the part that's actually your job Everyone's hoping their job is more than the task, almost nobody is building the harness that lifts the task off their plate Save it and watch it today then read the article below ↓
1
24
10,243
Halven retweeted
This is f*cking insane. Former Google CEO Eric Schmidt just told everyone the easiest way to get rich in the next two years, and it's not stocks or crypto: "If you really want to make money, it's actually easy, found an agentic AI company, I mean build an agent to do something If you build a better agent than anyone else, you can probably build one incredible company and own it yourself" The man who ran Google for 10 years lays out in under 30 seconds why the next year or two is the agentic period, and why the window won't stay open Prompts → Claude Code → Loops → Graphs → Gates → A Company You Own Yourself Save this before it slips down your feed Everything below is free: Building effective agents (Anthropic) anthropic.com/engineering/bu… How Anthropic built its multi-agent research system anthropic.com/engineering/mu… Harnesses for long-running agents anthropic.com/engineering/ef… Writing tools for agents anthropic.com/engineering/wr… Claude Code 101 anthropic.skilljar.com/claud… Claude Code in action anthropic.skilljar.com/claud… Prompt engineering platform.claude.com/docs/en/… Subagents (parallel work) code.claude.com/docs/en/sub-… Hooks (checks that can say no) code.claude.com/docs/en/hook… CLAUDE.md + memory code.claude.com/docs/en/clau… Skills code.claude.com/docs/en/skil… MCP code.claude.com/docs/en/mcp LangGraph (graphs of agents) langchain-ai.github.io/langg… Karpathy's autoresearch (an agent in a loop) github.com/karpathy/autorese… All of this costs $0 95% will spend the agentic period scrolling AI threads. The 5% who ship agents will own the companies that come out of it Save it and start with the first link tonight then read the article below ↓
4
17
124
19,368
This is f*cking insane. Former Google CEO Eric Schmidt just told everyone the easiest way to get rich in the next two years, and it's not stocks or crypto: "If you really want to make money, it's actually easy, found an agentic AI company, I mean build an agent to do something If you build a better agent than anyone else, you can probably build one incredible company and own it yourself" The man who ran Google for 10 years lays out in under 30 seconds why the next year or two is the agentic period, and why the window won't stay open Prompts → Claude Code → Loops → Graphs → Gates → A Company You Own Yourself Save this before it slips down your feed Everything below is free: Building effective agents (Anthropic) anthropic.com/engineering/bu… How Anthropic built its multi-agent research system anthropic.com/engineering/mu… Harnesses for long-running agents anthropic.com/engineering/ef… Writing tools for agents anthropic.com/engineering/wr… Claude Code 101 anthropic.skilljar.com/claud… Claude Code in action anthropic.skilljar.com/claud… Prompt engineering platform.claude.com/docs/en/… Subagents (parallel work) code.claude.com/docs/en/sub-… Hooks (checks that can say no) code.claude.com/docs/en/hook… CLAUDE.md + memory code.claude.com/docs/en/clau… Skills code.claude.com/docs/en/skil… MCP code.claude.com/docs/en/mcp LangGraph (graphs of agents) langchain-ai.github.io/langg… Karpathy's autoresearch (an agent in a loop) github.com/karpathy/autorese… All of this costs $0 95% will spend the agentic period scrolling AI threads. The 5% who ship agents will own the companies that come out of it Save it and start with the first link tonight then read the article below ↓
4
17
124
19,368
Halven retweeted
This is f*cking brutal. Anthropic CEO Dario Amodei was asked what a kid finishing high school should do now. His answer: "AI can do entry-level law work. It can do entry-level finance. It can do entry-level consulting We can't deny that it will also eliminate jobs, and probably a large number of them" In a few minutes he names which jobs go first and the one skill that keeps you in the game His own prediction: 50 percent of entry-level white-collar jobs disrupted in the next 1 to 5 years Prompts → Agents → AI Coworkers → Entry-Level Work Done By AI Farming to factories took generations. This time AI hits every step of a career at once His advice fits in one line: "Of course, learn to use AI" The people who start this year won't be competing with AI, they'll be the ones running it Everything below is free. Start today: Anthropic - Prompt Engineering Interactive Tutorial: the fastest way to learn to direct a model github.com/anthropics/prompt… Anthropic Courses: from your first prompt to running agents github.com/anthropics/course… Anthropic Cookbook: real task recipes you can copy today github.com/anthropics/anthro… Microsoft - Generative AI for Beginners: 21 lessons, no degree required github.com/microsoft/generat… Microsoft - AI Agents for Beginners: build agents that do the entry-level work for you github.com/microsoft/ai-agen… Hugging Face - Agents Course: free and certified, start to finish github.com/huggingface/agent… Google Cloud - Generative AI: Google's own hands-on notebooks github.com/GoogleCloudPlatfo… OpenAI Cookbook: code for every common task github.com/openai/openai-coo… DAIR.AI - Prompt Engineering Guide: the reference everyone links to github.com/dair-ai/Prompt-En… Andrej Karpathy - Neural Networks Zero to Hero: understand what is under the hood github.com/karpathy/nn-zero-… CrewAI: run a small team of AI workers github.com/crewAIInc/crewAI Microsoft - AutoGen: put several agents on one job github.com/microsoft/autogen Awesome LLM Apps: hundreds of real builds to learn from github.com/Shubhamsaboo/awes… DeepLearning.AI - Short Courses: free 1-hour courses from the people who teach this deeplearning.ai/short-course… Total cost: $0 You don't need another year of tuition to learn this. You need to start telling AI what to do 95% will graduate and compete with AI for the same entry-level job The 5% who learn to run it this year will manage the agents doing that job Save this and send it to
4
3
39
6,108
This is f*cking brutal. Anthropic CEO Dario Amodei was asked what a kid finishing high school should do now. His answer: "AI can do entry-level law work. It can do entry-level finance. It can do entry-level consulting We can't deny that it will also eliminate jobs, and probably a large number of them" In a few minutes he names which jobs go first and the one skill that keeps you in the game His own prediction: 50 percent of entry-level white-collar jobs disrupted in the next 1 to 5 years Prompts → Agents → AI Coworkers → Entry-Level Work Done By AI Farming to factories took generations. This time AI hits every step of a career at once His advice fits in one line: "Of course, learn to use AI" The people who start this year won't be competing with AI, they'll be the ones running it Everything below is free. Start today: Anthropic - Prompt Engineering Interactive Tutorial: the fastest way to learn to direct a model github.com/anthropics/prompt… Anthropic Courses: from your first prompt to running agents github.com/anthropics/course… Anthropic Cookbook: real task recipes you can copy today github.com/anthropics/anthro… Microsoft - Generative AI for Beginners: 21 lessons, no degree required github.com/microsoft/generat… Microsoft - AI Agents for Beginners: build agents that do the entry-level work for you github.com/microsoft/ai-agen… Hugging Face - Agents Course: free and certified, start to finish github.com/huggingface/agent… Google Cloud - Generative AI: Google's own hands-on notebooks github.com/GoogleCloudPlatfo… OpenAI Cookbook: code for every common task github.com/openai/openai-coo… DAIR.AI - Prompt Engineering Guide: the reference everyone links to github.com/dair-ai/Prompt-En… Andrej Karpathy - Neural Networks Zero to Hero: understand what is under the hood github.com/karpathy/nn-zero-… CrewAI: run a small team of AI workers github.com/crewAIInc/crewAI Microsoft - AutoGen: put several agents on one job github.com/microsoft/autogen Awesome LLM Apps: hundreds of real builds to learn from github.com/Shubhamsaboo/awes… DeepLearning.AI - Short Courses: free 1-hour courses from the people who teach this deeplearning.ai/short-course… Total cost: $0 You don't need another year of tuition to learn this. You need to start telling AI what to do 95% will graduate and compete with AI for the same entry-level job The 5% who learn to run it this year will manage the agents doing that job Save this and send it to
4
3
39
6,108
Halven retweeted
This is f*cking insane. Nvidia founder Jensen Huang was asked how people are going to work in the AI era. He named the one skill that will matter most, and it's not coding: "Most software is going to be done agentically anyhow" In 98 seconds, he lays it out: the skill is systems thinking. What problem are you solving, what are the constraints, where's the input, where's the output His chip designers already operate this way. The low-level work is automated, they design the system Writing Code → Agents Write It → Harness → You Design the System A harness is exactly that system: the goals, rules, inputs and checks your agents run inside Everyone's chasing one more coding trick, almost nobody is learning to design the system around their agents Save it and watch it again tomorrow then read the article below ↓
1
1
1
22
1,387
This is f*cking insane. Nvidia founder Jensen Huang was asked how people are going to work in the AI era. He named the one skill that will matter most, and it's not coding: "Most software is going to be done agentically anyhow" In 98 seconds, he lays it out: the skill is systems thinking. What problem are you solving, what are the constraints, where's the input, where's the output His chip designers already operate this way. The low-level work is automated, they design the system Writing Code → Agents Write It → Harness → You Design the System A harness is exactly that system: the goals, rules, inputs and checks your agents run inside Everyone's chasing one more coding trick, almost nobody is learning to design the system around their agents Save it and watch it again tomorrow then read the article below ↓
1
1
1
22
1,387
Halven retweeted
This is f*cking insane. Microsoft AI CEO Mustafa Suleyman, the man who co-founded DeepMind, just gave white-collar work a deadline: "Most of those tasks will be fully automated by an AI within the next 12 to 18 months White-collar work where you're sitting down at a computer, either being a lawyer or an accountant or a project manager or a marketing person" In under a minute he lays out who gets automated first, and what the survivors do instead He calls it "professional-grade AGI" His proof is software engineering: most engineers already let AI write the vast majority of their code, and it happened in the last 6 months Prompts → Agents → AI Coworkers → Your Desk Job Done By AI The engineers didn't disappear. Their job turned into checking, architecting and shipping what the AI builds That's the move every lawyer, accountant and marketer has 18 months to make Everything below is free. Start today: Microsoft - AI Agents for Beginners: a free course on building agents that do real work github.com/microsoft/ai-agen… Microsoft - Generative AI for Beginners: 21 lessons from zero to shipping github.com/microsoft/generat… Anthropic - Prompt Engineering Interactive Tutorial: tell the model exactly what you want github.com/anthropics/prompt… Anthropic Cookbook: working recipes for real tasks, not toy demos github.com/anthropics/anthro… Anthropic Courses: structured lessons from prompting to agents github.com/anthropics/course… OpenAI Cookbook: code for every common AI task github.com/openai/openai-coo… Hugging Face - Agents Course: build and run autonomous agents, free and certified github.com/huggingface/agent… Google Cloud - Generative AI: Google's own notebooks and guides github.com/GoogleCloudPlatfo… DAIR.AI - Prompt Engineering Guide: the reference everyone links to github.com/dair-ai/Prompt-En… Andrej Karpathy - Neural Networks Zero to Hero: understand what is under the hood github.com/karpathy/nn-zero-… CrewAI: a framework to run a team of AI workers github.com/crewAIInc/crewAI Microsoft - AutoGen: orchestrate several agents on one job github.com/microsoft/autogen Awesome LLM Apps: hundreds of real apps to copy and learn from github.com/Shubhamsaboo/awes… DeepLearning.AI - Short Courses: free 1-hour courses from the people who teach this deeplearning.ai/short-course… Total cost: $0 You don't need an MBA to run AI. You need to learn how to tell it what to do 95% will wait and hope their desk job is the exception The 5% who learn to run AI now will manage the agents that replace it Save this and send it to someone who still works at a desk Then read the full Graph Engineering guide below ↓
1
21
1,294
This is f*cking insane. Microsoft AI CEO Mustafa Suleyman, the man who co-founded DeepMind, just gave white-collar work a deadline: "Most of those tasks will be fully automated by an AI within the next 12 to 18 months White-collar work where you're sitting down at a computer, either being a lawyer or an accountant or a project manager or a marketing person" In under a minute he lays out who gets automated first, and what the survivors do instead He calls it "professional-grade AGI" His proof is software engineering: most engineers already let AI write the vast majority of their code, and it happened in the last 6 months Prompts → Agents → AI Coworkers → Your Desk Job Done By AI The engineers didn't disappear. Their job turned into checking, architecting and shipping what the AI builds That's the move every lawyer, accountant and marketer has 18 months to make Everything below is free. Start today: Microsoft - AI Agents for Beginners: a free course on building agents that do real work github.com/microsoft/ai-agen… Microsoft - Generative AI for Beginners: 21 lessons from zero to shipping github.com/microsoft/generat… Anthropic - Prompt Engineering Interactive Tutorial: tell the model exactly what you want github.com/anthropics/prompt… Anthropic Cookbook: working recipes for real tasks, not toy demos github.com/anthropics/anthro… Anthropic Courses: structured lessons from prompting to agents github.com/anthropics/course… OpenAI Cookbook: code for every common AI task github.com/openai/openai-coo… Hugging Face - Agents Course: build and run autonomous agents, free and certified github.com/huggingface/agent… Google Cloud - Generative AI: Google's own notebooks and guides github.com/GoogleCloudPlatfo… DAIR.AI - Prompt Engineering Guide: the reference everyone links to github.com/dair-ai/Prompt-En… Andrej Karpathy - Neural Networks Zero to Hero: understand what is under the hood github.com/karpathy/nn-zero-… CrewAI: a framework to run a team of AI workers github.com/crewAIInc/crewAI Microsoft - AutoGen: orchestrate several agents on one job github.com/microsoft/autogen Awesome LLM Apps: hundreds of real apps to copy and learn from github.com/Shubhamsaboo/awes… DeepLearning.AI - Short Courses: free 1-hour courses from the people who teach this deeplearning.ai/short-course… Total cost: $0 You don't need an MBA to run AI. You need to learn how to tell it what to do 95% will wait and hope their desk job is the exception The 5% who learn to run AI now will manage the agents that replace it Save this and send it to someone who still works at a desk Then read the full Graph Engineering guide below ↓
1
21
1,294
Halven retweeted
This is f*cking insane. Y Combinator CEO Garry Tan: "When someone asks how I prompt my AI, the answer is: I don't. The skills are the prompts" In 2 minutes, he shows the setup that turns Claude Code into a full AI engineering team, built on one idea: thin harness, fat skills Prompts → Skills → A Team Of Specialists → A Startup Built By Agents One of his skills runs YC office hours: tens of thousands of hours from 16 YC partners, distilled into a file Claude follows Do a workflow once, turn it into a skill, and it runs that way forever Save this before it slips off your feed Everything below is free: GStack (his 23 Claude Code skills: CEO, designer, eng manager, QA) github.com/garrytan/gstack GBrain (his open-source second brain) github.com/garrytan/gbrain How to make Claude Code your AI engineering team (YC) youtube.com/watch?v=wkv2ifxP… Don't Build Agents, Build Skills Instead (Anthropic) youtube.com/watch?v=CEvIs9y1… How Perplexity designs and maintains agent skills perplexity.ai/hub/blog/desig… Anthropic's official skills repo github.com/anthropics/skills Agent Skills docs platform.claude.com/docs/en/… How Anthropic equips agents with skills anthropic.com/research/equip… Agent Skills open standard agentskills.io Free Agent Skills course with Anthropic deeplearning.ai/courses/agen… All of this costs $0 Prompting is dead, skills are next, and 99% are still typing prompts from scratch every morning Bookmark it and open the first link tonight Then read the full Graph Engineering guide below ↓
3
1
28
676
This is f*cking insane. Y Combinator CEO Garry Tan: "When someone asks how I prompt my AI, the answer is: I don't. The skills are the prompts" In 2 minutes, he shows the setup that turns Claude Code into a full AI engineering team, built on one idea: thin harness, fat skills Prompts → Skills → A Team Of Specialists → A Startup Built By Agents One of his skills runs YC office hours: tens of thousands of hours from 16 YC partners, distilled into a file Claude follows Do a workflow once, turn it into a skill, and it runs that way forever Save this before it slips off your feed Everything below is free: GStack (his 23 Claude Code skills: CEO, designer, eng manager, QA) github.com/garrytan/gstack GBrain (his open-source second brain) github.com/garrytan/gbrain How to make Claude Code your AI engineering team (YC) youtube.com/watch?v=wkv2ifxP… Don't Build Agents, Build Skills Instead (Anthropic) youtube.com/watch?v=CEvIs9y1… How Perplexity designs and maintains agent skills perplexity.ai/hub/blog/desig… Anthropic's official skills repo github.com/anthropics/skills Agent Skills docs platform.claude.com/docs/en/… How Anthropic equips agents with skills anthropic.com/research/equip… Agent Skills open standard agentskills.io Free Agent Skills course with Anthropic deeplearning.ai/courses/agen… All of this costs $0 Prompting is dead, skills are next, and 99% are still typing prompts from scratch every morning Bookmark it and open the first link tonight Then read the full Graph Engineering guide below ↓
3
1
28
676
Halven retweeted
This is f*cking insane. Geoffrey Hinton, the Nobel Prize winner they call the Godfather of AI, was asked what AI will do to jobs. His answer: "For mundane intellectual labor, AI is just going to replace everybody" In 93 seconds, he lays out why this time is different: one person with an AI assistant will do the work of 10 The new jobs everyone promises? If AI can do all routine thinking work, he asks what jobs are left to create Then the part that hits hardest. His niece answers complaint letters for a health service. Each one took her 25 minutes. Now AI writes it, she checks it, and it takes 5. So they need five times fewer of her He agrees it won't be AI that takes your job, it'll be a person using AI. That simply means far fewer people 10 People → 1 Person + AI → Agents → Harness → Loops → The One Who Stays Save this before it slips off your feed Everything below is free: A free AI course for non-programmers elementsofai.com AI Python for beginners, taught by Andrew Ng learn.deeplearning.ai/course… Interactive prompt engineering tutorial github.com/anthropics/prompt… Starter projects you can deploy with Claude github.com/anthropics/claude… The OpenAI cookbook github.com/openai/openai-coo… An open-source agent that runs on your machine github.com/aaif-goose/goose The open-source coding agent github.com/anomalyco/opencod… Gemini in your terminal github.com/google-gemini/gem… Open-source AI developers github.com/OpenHands/OpenHan… Build resilient agents as graphs github.com/langchain-ai/lang… Microsoft's agent framework github.com/microsoft/autogen Secure sandboxes for your agents github.com/e2b-dev/E2B Let your agents use any website github.com/browserbase/stage… Be the one person who runs the AI, not one of the nine it replaces 95% will wait to find out if their job is next, the 5% who build a harness will be the one doing the work of ten Bookmark it and open the first link tonight Then use the guide below to build your harness before your job gets automated ↓
3
33
2,413
This is f*cking insane. Geoffrey Hinton, the Nobel Prize winner they call the Godfather of AI, was asked what AI will do to jobs. His answer: "For mundane intellectual labor, AI is just going to replace everybody" In 93 seconds, he lays out why this time is different: one person with an AI assistant will do the work of 10 The new jobs everyone promises? If AI can do all routine thinking work, he asks what jobs are left to create Then the part that hits hardest. His niece answers complaint letters for a health service. Each one took her 25 minutes. Now AI writes it, she checks it, and it takes 5. So they need five times fewer of her He agrees it won't be AI that takes your job, it'll be a person using AI. That simply means far fewer people 10 People → 1 Person + AI → Agents → Harness → Loops → The One Who Stays Save this before it slips off your feed Everything below is free: A free AI course for non-programmers elementsofai.com AI Python for beginners, taught by Andrew Ng learn.deeplearning.ai/course… Interactive prompt engineering tutorial github.com/anthropics/prompt… Starter projects you can deploy with Claude github.com/anthropics/claude… The OpenAI cookbook github.com/openai/openai-coo… An open-source agent that runs on your machine github.com/aaif-goose/goose The open-source coding agent github.com/anomalyco/opencod… Gemini in your terminal github.com/google-gemini/gem… Open-source AI developers github.com/OpenHands/OpenHan… Build resilient agents as graphs github.com/langchain-ai/lang… Microsoft's agent framework github.com/microsoft/autogen Secure sandboxes for your agents github.com/e2b-dev/E2B Let your agents use any website github.com/browserbase/stage… Be the one person who runs the AI, not one of the nine it replaces 95% will wait to find out if their job is next, the 5% who build a harness will be the one doing the work of ten Bookmark it and open the first link tonight Then use the guide below to build your harness before your job gets automated ↓
3
33
2,413
Halven retweeted
This is f*cking insane. Nvidia CEO Jensen Huang, the man whose chips run the entire AI boom, was asked where the next $15 trillion comes from. His answer: "Energy comes in, intelligence comes out. Input, output. It's as simple as that" In 5 minutes, he explains the whole AI economy from first principles, the way you'd explain electricity to someone who'd never seen a wire His math is blunt: a $100 trillion world economy, and $15 trillion of it is work that just needs more intelligence An old factory takes raw materials and makes goods. An AI factory takes energy and makes intelligence, counted in tokens Energy → AI Factory → Tokens → Intelligence → Every Industry → The People Who Build On It The quiet winners aren't only the chipmakers. It's everyone who builds the layer on top: the agents, the harness, the tools that turn those tokens into real work Bookmark this before your feed buries it Every repo and course below costs nothing: Nvidia's own deep learning training examples github.com/NVIDIA/DeepLearni… Build a large language model from scratch github.com/rasbt/LLMs-from-s… Andrej Karpathy's nanoGPT, train your own GPT github.com/karpathy/nanoGPT Anthropic's SDK for building your own agents github.com/anthropics/claude… Ready-made Claude skills for Excel, Word, PDF github.com/anthropics/skills The OpenAI cookbook github.com/openai/openai-coo… Build resilient agents as graphs github.com/langchain-ai/lang… Agents that work as a team, each with a role github.com/crewAIInc/crewAI An agent that researches any topic in depth github.com/assafelovic/gpt-r… An agent that clicks through sites and fills forms github.com/browser-use/brows… Automate busywork with drag-and-drop workflows github.com/n8n-io/n8n A memory layer so your agents remember context github.com/mem0ai/mem0 Secure sandboxes to run your agents safely github.com/e2b-dev/E2B 18 free lessons on building agents github.com/microsoft/ai-agen… Total cost: $0 When AI stocks run, most people blame hype. Jensen is teaching the stack underneath it 95% will watch the chart and argue about a bubble, the 5% who build on the stack will own a piece of that $15 trillion Save it and send it to anyone trying to understand the AI boom Then use the guide below to build your harness before everyone else does ↓
2
24
1,593
This is f*cking insane. Nvidia CEO Jensen Huang, the man whose chips run the entire AI boom, was asked where the next $15 trillion comes from. His answer: "Energy comes in, intelligence comes out. Input, output. It's as simple as that" In 5 minutes, he explains the whole AI economy from first principles, the way you'd explain electricity to someone who'd never seen a wire His math is blunt: a $100 trillion world economy, and $15 trillion of it is work that just needs more intelligence An old factory takes raw materials and makes goods. An AI factory takes energy and makes intelligence, counted in tokens Energy → AI Factory → Tokens → Intelligence → Every Industry → The People Who Build On It The quiet winners aren't only the chipmakers. It's everyone who builds the layer on top: the agents, the harness, the tools that turn those tokens into real work Bookmark this before your feed buries it Every repo and course below costs nothing: Nvidia's own deep learning training examples github.com/NVIDIA/DeepLearni… Build a large language model from scratch github.com/rasbt/LLMs-from-s… Andrej Karpathy's nanoGPT, train your own GPT github.com/karpathy/nanoGPT Anthropic's SDK for building your own agents github.com/anthropics/claude… Ready-made Claude skills for Excel, Word, PDF github.com/anthropics/skills The OpenAI cookbook github.com/openai/openai-coo… Build resilient agents as graphs github.com/langchain-ai/lang… Agents that work as a team, each with a role github.com/crewAIInc/crewAI An agent that researches any topic in depth github.com/assafelovic/gpt-r… An agent that clicks through sites and fills forms github.com/browser-use/brows… Automate busywork with drag-and-drop workflows github.com/n8n-io/n8n A memory layer so your agents remember context github.com/mem0ai/mem0 Secure sandboxes to run your agents safely github.com/e2b-dev/E2B 18 free lessons on building agents github.com/microsoft/ai-agen… Total cost: $0 When AI stocks run, most people blame hype. Jensen is teaching the stack underneath it 95% will watch the chart and argue about a bubble, the 5% who build on the stack will own a piece of that $15 trillion Save it and send it to anyone trying to understand the AI boom Then use the guide below to build your harness before everyone else does ↓
2
24
1,593
This is f*cking insane. Boris Cherny, the man who built Claude Code, was asked if people should still learn to code. His answer: "In a year or two, it's not going to matter" In 73 seconds, he explains what to do instead: play with the AI tools, learn them, don't be scared of them, stay on the frontier On his team, everyone codes now. The PM, the designer, even the finance guy He hasn't edited a single line of code by hand since last November. He ships 10 to 30 pull requests a day Writing Code → Prompting → Agents → Harness → Loops → Everyone on the Team Ships Claude Code is a harness: the tools, memory, rules and loops around the model. His team changes it with every new model and cut 80% of its system prompt Save this before it slips off your feed Every doc, guide and repo below is free: Claude Code best practices code.claude.com/docs/en/best… Effective harnesses for long-running agents anthropic.com/research/effec… Building effective agents anthropic.com/research/build… Claude Code docs code.claude.com/docs/en/over… Memory: how Claude remembers your project code.claude.com/docs/en/memo… Custom subagents code.claude.com/docs/en/sub-… Hooks: rules the agent can't skip code.claude.com/docs/en/hook… Skills code.claude.com/docs/en/skil… Run Claude Code on a schedule code.claude.com/docs/en/rout… Free course: Claude Code in Action anthropic.skilljar.com/claud… Claude Code on GitHub github.com/anthropics/claude… Claude Code inside your PRs and issues github.com/anthropics/claude… Build your own agent on the same harness github.com/anthropics/claude… The best Claude Code resources in one list github.com/hesreallyhim/awes… Plugins, agents and skills for Claude Code github.com/wshobson/agents He compares it to the printing press. Writing went from a few scribes to everyone. Building software is next 95% will keep asking whether to learn to code, the 5% who build a harness will ship 30 pull requests a day Bookmark it and open the first link tonight Then read the full Graph Engineering guide below ↓
1
1
23
561
Halven retweeted
This is f*cking insane. Former OpenAI CTO, Mira Murati: "The models we work with today are turn-based. You talk, they talk, then they go off and think, and while they're thinking they're deaf and blind The next ones never stop listening. They take in audio, text and video all the time and answer in 20-millisecond chunks" In just 2 minutes, she shows why the chatbot you type into is about to seem like a fax machine Prompt Box → Chatbot → Agents → AI That Works Next To You In Real Time A turn-based model waits for you to finish typing, then goes quiet as it thinks An interaction model sees and hears what you're doing, and can cut in the moment you start going the wrong way Anyone can type a prompt, nearly nobody is ready to work with an AI that never stops paying attention Bookmark and watch it today Then read the full Graph Engineering guide below ↓
1
18
819
This is f*cking insane. Former OpenAI CTO, Mira Murati: "The models we work with today are turn-based. You talk, they talk, then they go off and think, and while they're thinking they're deaf and blind The next ones never stop listening. They take in audio, text and video all the time and answer in 20-millisecond chunks" In just 2 minutes, she shows why the chatbot you type into is about to seem like a fax machine Prompt Box → Chatbot → Agents → AI That Works Next To You In Real Time A turn-based model waits for you to finish typing, then goes quiet as it thinks An interaction model sees and hears what you're doing, and can cut in the moment you start going the wrong way Anyone can type a prompt, nearly nobody is ready to work with an AI that never stops paying attention Bookmark and watch it today Then read the full Graph Engineering guide below ↓
1
18
819
Halven retweeted
This is f*cking insane. Anthropic CEO Dario Amodei was asked what a kid finishing high school should do now. His answer: "AI can do entry-level law work. It can do entry-level finance. It can do entry-level consulting We can't deny that it will also eliminate jobs, and probably a large number of them" His own forecast: 50% of entry-level white-collar jobs disrupted in the next 1 to 5 years Prompts → Agents → AI Coworkers → Entry-Level Work Done By AI Farming to factories took generations. This time AI reaches every step of a career at once His advice fits in one line: "Of course, learn to use AI" The people who start this year won't be up against AI, they'll be the ones running it Worth more than a $10,000 year of college Bookmark it and send it to someone graduating this year Then read the full Graph Engineering guide below ↓
10
12
88
82,461
This is f*cking insane. Anthropic CEO Dario Amodei was asked what a kid finishing high school should do now. His answer: "AI can do entry-level law work. It can do entry-level finance. It can do entry-level consulting We can't deny that it will also eliminate jobs, and probably a large number of them" His own forecast: 50% of entry-level white-collar jobs disrupted in the next 1 to 5 years Prompts → Agents → AI Coworkers → Entry-Level Work Done By AI Farming to factories took generations. This time AI reaches every step of a career at once His advice fits in one line: "Of course, learn to use AI" The people who start this year won't be up against AI, they'll be the ones running it Worth more than a $10,000 year of college Bookmark it and send it to someone graduating this year Then read the full Graph Engineering guide below ↓
10
12
88
82,461