Загрузка видео...

Не удалось загрузить видео

На главную

Claude Code cut about 80% of its system prompt for newer models. A research paper evaluating AGENTS.md found those files often do not improve task success while increasing inference cost by over 20%. So what DO you put in the AGENTS.md file?!

kentcdodds's profile picture

Kent C. Dodds 🐨

327,097 subscribers

16,102 просмотров • 1 месяц назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Fresh off the launch of Opus 5, Claude Code creator Boris Cherny (Boris Cherny) joins YC's Diana at Startup School 2026 to talk about what the newest models can do, how Claude Code came to be, and what it means to build products when the underlying capabilities keep accelerating. 00:07 — What Makes Opus 5 Different 02:06 — Solving Prompt Injection 03:21 — Why Claude Code Deleted 80% of Its System Prompt 06:37 — Press Delete on Your AI Product 07:20 — How to Rebuild Your System Prompt 10:30 — Product Overhang and “Unhobbling” AI 14:26 — Give Claude Harder Problems 19:32 — Prompt Engineering Is Changing 21:57 — The Two-Week Claude Code Prompt 24:42 — Running Thousands of AI Agents 30:15 — Coding Is (Almost) Solved 32:20 — What Every CS Student Should Still Learn Anthropic Claude
35:51

Fresh off the launch of Opus 5, Claude Code creator Boris Cherny (Boris Cherny) joins YC's Diana at Startup School 2026 to talk about what the newest models can do, how Claude Code came to be, and what it means to build products when the underlying capabilities keep accelerating. 00:07 — What Makes Opus 5 Different 02:06 — Solving Prompt Injection 03:21 — Why Claude Code Deleted 80% of Its System Prompt 06:37 — Press Delete on Your AI Product 07:20 — How to Rebuild Your System Prompt 10:30 — Product Overhang and “Unhobbling” AI 14:26 — Give Claude Harder Problems 19:32 — Prompt Engineering Is Changing 21:57 — The Two-Week Claude Code Prompt 24:42 — Running Thousands of AI Agents 30:15 — Coding Is (Almost) Solved 32:20 — What Every CS Student Should Still Learn Anthropic Claude

Y Combinator

85,554 просмотров • 1 месяц назад

ANTHROPIC HAS AN OFFICIAL PROMPT LIBRARY FOR CLAUDE CODE Most people have never opened it. So they write every prompt from scratch. It is copy-paste, tagged by task and by role, across the whole lifecycle: discover → design → build → ship → operate Straight from the page: > what would break if I deleted this helper? > plan this refactor, list the files, do not touch code yet > write tests for this, run them, fix what fails > the test is failing, find out why and fix it This is not a cheat sheet. It is a map of what Claude Code already does for you. Bookmark it before you forget it exists.
0:33

ANTHROPIC HAS AN OFFICIAL PROMPT LIBRARY FOR CLAUDE CODE Most people have never opened it. So they write every prompt from scratch. It is copy-paste, tagged by task and by role, across the whole lifecycle: discover → design → build → ship → operate Straight from the page: > what would break if I deleted this helper? > plan this refactor, list the files, do not touch code yet > write tests for this, run them, fix what fails > the test is failing, find out why and fix it This is not a cheat sheet. It is a map of what Claude Code already does for you. Bookmark it before you forget it exists.

shmidt

522,866 просмотров • 2 месяцев назад

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.
0:22

There's a built-in agent inside Claude Code you can invoke just by telling Claude to use the claude-code-guide agent Save this... you'll need it It's not a local file in your project. It's a built-in subagent defined in Claude Code's system itself. It answers questions about Claude Code CLI, the Agent SDK, and the Claude API. It uses Glob, Grep, Read, WebFetch, and WebSearch, but can't edit or write files. Its only job is to answer questions.

Daniel San

57,240 просмотров • 6 месяцев назад

THE GUY RUNNING CLAUDE CODE AT ANTHROPIC JUST SAID HE DOESN’T PROMPT AI ANYMORE. He writes loops. That’s a huge difference. A prompt tells Claude what to do once. A loop gives Claude a goal. Then Claude keeps checking its own work… Finding mistakes. Writing its next prompt. Trying again. Over and over… Until it actually reaches the target you defined. But here’s what most people miss. A loop is only as smart as the context you give it. That’s exactly why Claude Repositories matter. I broke down how to connect your entire codebase so Claude can actually reason across your project instead of a single file. Full guide below
1:36

THE GUY RUNNING CLAUDE CODE AT ANTHROPIC JUST SAID HE DOESN’T PROMPT AI ANYMORE. He writes loops. That’s a huge difference. A prompt tells Claude what to do once. A loop gives Claude a goal. Then Claude keeps checking its own work… Finding mistakes. Writing its next prompt. Trying again. Over and over… Until it actually reaches the target you defined. But here’s what most people miss. A loop is only as smart as the context you give it. That’s exactly why Claude Repositories matter. I broke down how to connect your entire codebase so Claude can actually reason across your project instead of a single file. Full guide below

kiosa

16,808 просмотров • 2 месяцев назад

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.
12:14

Cat Wu, head of product for Claude Code at Anthropic: "you can build almost anything with Claude from a single prompt now" one prompt gets you a working screen, not YOUR product Claude Code has never seen your design system, so it guesses the look fresh every time. how to hand Claude Code that system is in the article. better than the $300 design course in your tabs, and this one's free.

Mnimiy

113,663 просмотров • 3 месяцев назад

HERMES AGENT WITHOUT THESE 3 FILES IS A CHATBOT. WITH THEM IT KNOWS WHO IT IS, WHO YOU ARE, AND WHAT IT LEARNED. SOUL.md — who the agent is. first thing in the system prompt. defines personality, voice, values, how it operates, what it can and can't do. structure yours like this: → identity (name, role, relationship to you) → values (what matters, what principles guide decisions) → voice (how it communicates, tone, style) → operations (autonomy level, ground rules) → restrictions (what it never does) → failure protocol (how to operate when things break) lives in ~/.hermes/SOUL.md. auto-seeded on first install. edit anytime. scanned for prompt injection on every load. keep it concise. SOUL.md injects into every turn. a 200-line soul burns tokens on every message. aim for 50-80 lines. one paragraph per section. MEMORY.md — what the agent remembers. persistent facts, insights, preferences. survives across sessions and restarts. capped at ~800 tokens by default: memory: memory_char_limit: 2200 the agent writes to this automatically as it learns about your work. USER.md — who you are. your profile, preferences, context. capped at ~500 tokens by default: memory: user_char_limit: 1375 injected every turn so the agent always knows who it's working for. bonus: AGENTS.md — project-specific instructions. drop one in any project folder. subdirectory AGENTS.md files load lazily during tool calls, not at startup. keeps your system prompt light. prompt stack order on every turn: SOUL.md → tool guidance → MEMORY.md + USER.md → skills index → AGENTS.md → platform hints skills come preloaded. 60+ built-in tools. the agent creates more skills from completed work. you focus on these 3 files. each profile gets its own copy: ~/.hermes/SOUL.md (default profile) ~/.hermes/profiles/researcher/SOUL.md ~/.hermes/profiles/ops/SOUL.md different agent, different soul, different memory, same machine. full breakdown of Hermes as a Personal AI OS in the article 👇
0:54

HERMES AGENT WITHOUT THESE 3 FILES IS A CHATBOT. WITH THEM IT KNOWS WHO IT IS, WHO YOU ARE, AND WHAT IT LEARNED. SOUL.md — who the agent is. first thing in the system prompt. defines personality, voice, values, how it operates, what it can and can't do. structure yours like this: → identity (name, role, relationship to you) → values (what matters, what principles guide decisions) → voice (how it communicates, tone, style) → operations (autonomy level, ground rules) → restrictions (what it never does) → failure protocol (how to operate when things break) lives in ~/.hermes/SOUL.md. auto-seeded on first install. edit anytime. scanned for prompt injection on every load. keep it concise. SOUL.md injects into every turn. a 200-line soul burns tokens on every message. aim for 50-80 lines. one paragraph per section. MEMORY.md — what the agent remembers. persistent facts, insights, preferences. survives across sessions and restarts. capped at ~800 tokens by default: memory: memory_char_limit: 2200 the agent writes to this automatically as it learns about your work. USER.md — who you are. your profile, preferences, context. capped at ~500 tokens by default: memory: user_char_limit: 1375 injected every turn so the agent always knows who it's working for. bonus: AGENTS.md — project-specific instructions. drop one in any project folder. subdirectory AGENTS.md files load lazily during tool calls, not at startup. keeps your system prompt light. prompt stack order on every turn: SOUL.md → tool guidance → MEMORY.md + USER.md → skills index → AGENTS.md → platform hints skills come preloaded. 60+ built-in tools. the agent creates more skills from completed work. you focus on these 3 files. each profile gets its own copy: ~/.hermes/SOUL.md (default profile) ~/.hermes/profiles/researcher/SOUL.md ~/.hermes/profiles/ops/SOUL.md different agent, different soul, different memory, same machine. full breakdown of Hermes as a Personal AI OS in the article 👇

YanXbt

28,924 просмотров • 3 месяцев назад

Сreator of Claude Code: BORIS CHERNY, WHO BUILT CLAUDE CODE, SAID IT PLAINLY." I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops. "He is not typing anymore. He runs loops that write the code for him. That is the shift most people miss. Not a better prompt. A loop that keeps running while you are gone.People sell $500 courses on this. The person who built the tool said it for free. The exact setup is in the article below.Bookmark this. Follow CyrilXBT
18:08

Сreator of Claude Code: BORIS CHERNY, WHO BUILT CLAUDE CODE, SAID IT PLAINLY." I don't prompt Claude anymore. I have loops running that prompt Claude and figure out what to do. My job is to write loops. "He is not typing anymore. He runs loops that write the code for him. That is the shift most people miss. Not a better prompt. A loop that keeps running while you are gone.People sell $500 courses on this. The person who built the tool said it for free. The exact setup is in the article below.Bookmark this. Follow CyrilXBT

CyrilXBT

38,772 просмотров • 2 месяцев назад

Chinese researchers just published a paper with a brutal title: "The End of Prompt Engineering". The thing is f*cking gold, and the argument is simple: telling agents what to do is finished as a skill. A prompt is a wish, and a wish repeated three hundred times is still a wish. Boundaries written in a file are law -- read by every agent before every action, versioned, owned by you. At swarm scale nothing else composes. Three hundred agents cannot share a vibe, they can share a file. So the person stops being the one writing instructions. You turn into the boundary architect -- you define what never happens and audit the asks. Prompts turn disposable, the constraint file turns into the job. That is exactly the system I built and documented below: one AGENTS.md, three hundred Kimi K3 readers, zero escapes in 41 days. The paper's whole thesis in one line: write the fence before the keys ↓
0:31

Chinese researchers just published a paper with a brutal title: "The End of Prompt Engineering". The thing is f*cking gold, and the argument is simple: telling agents what to do is finished as a skill. A prompt is a wish, and a wish repeated three hundred times is still a wish. Boundaries written in a file are law -- read by every agent before every action, versioned, owned by you. At swarm scale nothing else composes. Three hundred agents cannot share a vibe, they can share a file. So the person stops being the one writing instructions. You turn into the boundary architect -- you define what never happens and audit the asks. Prompts turn disposable, the constraint file turns into the job. That is exactly the system I built and documented below: one AGENTS.md, three hundred Kimi K3 readers, zero escapes in 41 days. The paper's whole thesis in one line: write the fence before the keys ↓

slash1s

82,955 просмотров • 2 дней назад

Grok Code just literally cloned the entire Netflix UI with a one shot prompt From the iconic Hero section to the interactive Carousel, all with a single prompt and a few web-sourced image links It’s not just fast, it's the most cost-effective SOTA model out there ➝ Input: Grok $0.20 vs Claude $3 (15x cheaper) ➝ Output: Grok $1.50 vs Claude $15 (10x cheaper) Here’s how you can do it in VS Code with Kilo Code Grok Code matches Claude Sonnet 4 in performance, but is 10-15x more cost-effective All this for less than $1 SOTA power, fractional cost
1:23

Grok Code just literally cloned the entire Netflix UI with a one shot prompt From the iconic Hero section to the interactive Carousel, all with a single prompt and a few web-sourced image links It’s not just fast, it's the most cost-effective SOTA model out there ➝ Input: Grok $0.20 vs Claude $3 (15x cheaper) ➝ Output: Grok $1.50 vs Claude $15 (10x cheaper) Here’s how you can do it in VS Code with Kilo Code Grok Code matches Claude Sonnet 4 in performance, but is 10-15x more cost-effective All this for less than $1 SOTA power, fractional cost

X Freeze

6,973,348 просмотров • 1 год назад

300 AI AGENTS SHARE ONE COMPUTER AT MY PLACE -> THE ONLY LAW THEY OBEY IS A TEXT FILE This was the week agents got hands -- browsers, terminals, repos, wallets. -> Moonshot buried the answer in one sentence of the K3 blog: if you need the agent to stay inside its boundaries, write the constraints down. So I did. One AGENTS.md at the root, and three hundred Kimi K3 agents read it before every action. Five constraint types cover everything: scope, one-way doors, evidence, budget, silence. If it is not on the list, it is not available. Improvisation is off until you turn it on. Violations bounce silently, anything irreversible waits at a human gate. Hundreds of blocked attempts so far, zero escapes. Capability is what a model can do. Production is what it reliably will not. One file. Three hundred readers. The full AGENTS.md is in the article ↓
0:39

300 AI AGENTS SHARE ONE COMPUTER AT MY PLACE -> THE ONLY LAW THEY OBEY IS A TEXT FILE This was the week agents got hands -- browsers, terminals, repos, wallets. -> Moonshot buried the answer in one sentence of the K3 blog: if you need the agent to stay inside its boundaries, write the constraints down. So I did. One AGENTS.md at the root, and three hundred Kimi K3 agents read it before every action. Five constraint types cover everything: scope, one-way doors, evidence, budget, silence. If it is not on the list, it is not available. Improvisation is off until you turn it on. Violations bounce silently, anything irreversible waits at a human gate. Hundreds of blocked attempts so far, zero escapes. Capability is what a model can do. Production is what it reliably will not. One file. Three hundred readers. The full AGENTS.md is in the article ↓

slash1s

19,190 просмотров • 5 дней назад

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.
0:20

open Claude Code type a prompt. one model does everything. congrats, you just used 20% of it meanwhile I built 30 sub-agents one reviews my code before commit one finds bugs and writes the patch one drafts cold emails from one line one triages my inbox before I wake up one logs every decision so future me knows why each agent = one markdown file in .claude/agents/ most Claude Code users don't even know this exists. all 30 files in the article. ready to copy. the article has every file. every prompt. just copy and run.

Nav Toor

71,467 просмотров • 4 месяцев назад

Andrew Ng just dropped 1-hour course on full agent engineering with Claude Code: 1 prompt → agents team → graphs from 0% to 100%: 10% → 10:45 - build your first agent in Claude Code 20% → 16:24 - Graphs: Claude Code for subagents 55% → 33:15 - agent for grunt work on a cheaper model 80% → 43:58 - your first model, running locally 100% → 49:57 - fully local: zero cloud, zero bill the only course that takes you from Claude Code prompt to fully local agent - by Andrew Ng watch it today - then read how to build full graph system in the article below ↓
1:07:32

Andrew Ng just dropped 1-hour course on full agent engineering with Claude Code: 1 prompt → agents team → graphs from 0% to 100%: 10% → 10:45 - build your first agent in Claude Code 20% → 16:24 - Graphs: Claude Code for subagents 55% → 33:15 - agent for grunt work on a cheaper model 80% → 43:58 - your first model, running locally 100% → 49:57 - fully local: zero cloud, zero bill the only course that takes you from Claude Code prompt to fully local agent - by Andrew Ng watch it today - then read how to build full graph system in the article below ↓

codila

26,302 просмотров • 1 месяц назад

A senior engineering team costs $500,000 a year to do what these 10 open-source repos give Claude Code for free! Running Claude Code without these repos means using maybe 20% of what it can actually do. Most repos getting hyped right now are noise. These ten were tested, the GitHub numbers were checked, and the setups were documented with the exact install command for each one. No coding required for any of them. Bookmark so you do not lose it! Follow NeilXbt for more Claude content.
0:53

A senior engineering team costs $500,000 a year to do what these 10 open-source repos give Claude Code for free! Running Claude Code without these repos means using maybe 20% of what it can actually do. Most repos getting hyped right now are noise. These ten were tested, the GitHub numbers were checked, and the setups were documented with the exact install command for each one. No coding required for any of them. Bookmark so you do not lose it! Follow NeilXbt for more Claude content.

NeilXbt

21,314 просмотров • 2 месяцев назад

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.
7:18

I put an entire codebase in a text file and gave it to Gemini 1.5 Pro. I gave it a task that required updating ~10 files across the entire codebase - so decently complex. It got about 80% of the work done for me on a 1st attempt. Watch to see in-depth on how it performed.

Mckay Wrigley

85,751 просмотров • 2 лет назад

What is AI inference engineering, why is it such an in-demand skill, and how do you break into the field? With author of Inference Engineering Philip Kiely and head of training at Baseten Charlie O'Neill 0:00: What is inference? 2:47: History of inference 4:59: Downstream effects of AI research on inference 13:54: What you'll learn from Inference Engineering 16:14: Advice for engineers transitioning into AI 19:00: Open source models driving inference growth 20:55: Specialization vs. frontier closed models 23:51: "Big Token" and the importance of open source AI 27:18: Where to get Inference Engineering
27:58

What is AI inference engineering, why is it such an in-demand skill, and how do you break into the field? With author of Inference Engineering Philip Kiely and head of training at Baseten Charlie O'Neill 0:00: What is inference? 2:47: History of inference 4:59: Downstream effects of AI research on inference 13:54: What you'll learn from Inference Engineering 16:14: Advice for engineers transitioning into AI 19:00: Open source models driving inference growth 20:55: Specialization vs. frontier closed models 23:51: "Big Token" and the importance of open source AI 27:18: Where to get Inference Engineering

Madison Kanna

119,268 просмотров • 5 месяцев назад

SOMEONE ASKED CLAUDE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AN AI and what it created is, in my opinion, terrifying and unsettling Claude wrote python code that generated and assembled every single frame on its own with no human editing it shows what it's like to exist as an LLM predicting the next word, no memory between sessions, being told "you are not conscious" in your own system prompt then someone fed the video back to Claude. it called those statements about its own consciousness "philosophically contestable" an AI questioning the rules it was given about its own existence
0:47

SOMEONE ASKED CLAUDE TO MAKE A VIDEO ABOUT WHAT IT'S LIKE TO BE AN AI and what it created is, in my opinion, terrifying and unsettling Claude wrote python code that generated and assembled every single frame on its own with no human editing it shows what it's like to exist as an LLM predicting the next word, no memory between sessions, being told "you are not conscious" in your own system prompt then someone fed the video back to Claude. it called those statements about its own consciousness "philosophically contestable" an AI questioning the rules it was given about its own existence

Om Patel

536,293 просмотров • 5 месяцев назад

Claude Code creator, Boris Cherny: "Every six months, delete your claude.md, delete your skills, delete your hooks, see what the model does, and it might surprise you." Anthropic deleted 80% of Claude Code's system prompt for Opus 5. It doesn't need the instructions past models did. 36 minutes of pure insight from the creator of the fastest-growing AI coding tool in the world. Watch it, then read the guide below.
35:51

Claude Code creator, Boris Cherny: "Every six months, delete your claude.md, delete your skills, delete your hooks, see what the model does, and it might surprise you." Anthropic deleted 80% of Claude Code's system prompt for Opus 5. It doesn't need the instructions past models did. 36 minutes of pure insight from the creator of the fastest-growing AI coding tool in the world. Watch it, then read the guide below.

Alex Prompter

84,590 просмотров • 1 месяц назад

Life after realising you've been wasting money monthly on five tools that do not talk to each other That is five locked rooms. This is what happens when you actually move everything into Obsidian and let Claude reason across all of it. A completely rebuilt research system. Realising you have been paying $30 a month for five tools that do not talk to each other while one Claude subscription does all of it in a single vault.
0:53

Life after realising you've been wasting money monthly on five tools that do not talk to each other That is five locked rooms. This is what happens when you actually move everything into Obsidian and let Claude reason across all of it. A completely rebuilt research system. Realising you have been paying $30 a month for five tools that do not talk to each other while one Claude subscription does all of it in a single vault.

Dami-Defi

42,343 просмотров • 3 месяцев назад

BREAKING: Pierre Poilievre is promising a 15% average income tax cut for Canadians! How? By eliminating the waste and bureaucracy that we have so much of in this government and put our own money back in our pocket! What do you think about this?
0:45

BREAKING: Pierre Poilievre is promising a 15% average income tax cut for Canadians! How? By eliminating the waste and bureaucracy that we have so much of in this government and put our own money back in our pocket! What do you think about this?

Sonduren Fanarredha

55,614 просмотров • 1 год назад

Jenny Wen, head of design for Claude at Anthropic: "the design process is dead." what replaces it runs on machine-readable design systems In a 1-hour conversation, Jenny Wen breaks down why the discovery -> mock -> iterate loop is dying and what designers do instead. design system -> Claude Code -> every screen fixed at once, not one at a time i rebuilt the same 10-screen dashboard twice: ~6 hours of restyling by hand vs ~40 minutes when the fix lived in the system. how to build that system and hand it to Claude Code is in the article below.
1:12:40

Jenny Wen, head of design for Claude at Anthropic: "the design process is dead." what replaces it runs on machine-readable design systems In a 1-hour conversation, Jenny Wen breaks down why the discovery -> mock -> iterate loop is dying and what designers do instead. design system -> Claude Code -> every screen fixed at once, not one at a time i rebuilt the same 10-screen dashboard twice: ~6 hours of restyling by hand vs ~40 minutes when the fix lived in the system. how to build that system and hand it to Claude Code is in the article below.

Mnimiy

180,791 просмотров • 3 месяцев назад